JP4492642B2 - Red-eye correction device, red-eye correction method, and red-eye correction program - Google Patents

Description

  The present invention relates to a red-eye correction device, a red-eye correction method, and a red-eye correction program for correcting red eyes generated in a color image expressed by image data having multiple gradations for a large number of pixels.

Conventionally, when a person is photographed with a digital camera or the like in a dark environment such as at night, red eyes may appear in the human eye. Red eye refers to a phenomenon in which a so-called black eye portion becomes red or gold. As a device for correcting such red-eye, a rectangular region for correcting red-eye is designated, and a portion where the hue is within a predetermined range and the saturation is equal to or greater than a predetermined value is automatically extracted as a red-eye region from the rectangular region. For example, a device that converts the color into a predetermined color is known (see, for example, Patent Document 1). The apparatus can manually specify a red-eye area when the red-eye area cannot be extracted automatically, thereby improving the operation efficiency of correcting the red-eye.
A technique for automatically extracting an eye area from an area including the eye is also known (see, for example, Patent Document 2).

JP 2001-148780 (paragraphs 0019-0052, FIGS. 1-7) JP-A-10-75374 (paragraphs 0015-0049, FIG. 1-3)

In the above-described conventional technology, there is a problem in that an uncomfortable feeling is felt when an image in which the red-eye area is replaced with a predetermined color is viewed. In particular, since the non-red-eye area is uniformly replaced with a predetermined color, if a portion where the color changes suddenly between the inside and outside of the area subjected to red-eye correction occurs, an image with a sense of incongruity will be generated. Therefore, there is a desire to correct the red eye so as not to make the user feel uncomfortable with the image in which the red eye is generated.
The present invention has been made in view of the above problems, and a red-eye correction device and a red-eye correction capable of correcting red eyes so as not to make a sense of incongruity more reliably for an image in which red eyes are generated in the eyes. The object is to provide a method and red-eye correction program.

In order to achieve the above object, the invention according to claim 1 obtains image data of a second image different from the first image of color expressed by image data having multiple gradations for each pixel, A correction for determining an iris region from the second image based on the image data, acquiring information representing the eye color based on the image data of the region, and correcting red eyes in the first image When the image data of the first image for the pixels in the correction area corresponding to the correction area information representing the area is within the range corresponding to the range information representing the range of the red-eye color in the color space of the image data, When the image data of the first image is replaced with image data corresponding to information representing the same color, and the same pixel is a boundary portion of the same correction area, the replacement amount of the same image data is the same. To the extent that it is included in the correction area It is constituted having a color replacement unit to Flip amount.
That is, image data of a second image different from the first image of color expressed by image data having multiple gradations for each pixel is acquired, and an iris is obtained from the second image based on the image data. Area is determined, information indicating the eye color is acquired based on the image data of the area, and the correction area information corresponding to the correction area information indicating the correction area for correcting the red eye in the first image is obtained. When the image data of the first image for a pixel is within a range corresponding to range information indicating a range of red-eye colors in the color space of the image data, the image data of the first image is When the pixel is replaced with image data corresponding to information representing the color and the pixel is a boundary portion of the correction region, the replacement amount of the image data is an amount corresponding to the degree to which the pixel is included in the correction region. The Therefore, the image data cannot be completely replaced with the data representing the eye color when the boundary portion of the red eye correction area is within the range of the red eye color. It changes smoothly without changing suddenly. As a result, it is possible to correct the red eye so that the image in which the red eye is generated in the eye part does not feel uncomfortable .
Moreover, you may comprise like the invention concerning Claim 2. That is, image data of a second image different from the first image is acquired, an iris region is determined from the second image based on the acquired image data, and image data of the determined region Information representing the eye color is acquired based on the above. When the image data of the first image is within the range corresponding to the acquired range information for the pixels of the correction region corresponding to the acquired correction region information, the second image is obtained from the image data of the first image. When the image data is replaced with image data corresponding to the information representing the eye color from the image and the pixel is a boundary portion of the correction area, the replacement amount of the image data is the degree to which the pixel is included in the correction area. The amount depends on the condition. Therefore, the image data cannot be completely replaced with the data representing the eye color when the boundary portion of the red eye correction area is within the range of the red eye color. It changes smoothly without changing suddenly. As a result, it is possible to correct the red eye so that the image in which the red eye is generated in the eye part does not feel uncomfortable .

Further, in order to achieve the above object, correction area acquisition means for acquiring correction area information representing a correction area for correcting red eyes among color images represented by image data having multiple gradations for a number of pixels, Red-eye range acquisition means for acquiring range information representing a range of red-eye color in the color space of the image data, and the image data is acquired for the pixels in the correction area corresponding to the acquired correction area information. If it is within the range corresponding to the range information, the original image data is replaced with image data representing the eye color, and if the same pixel is the boundary portion of the same correction area, the replacement amount of the same image data is the same. It may be configured to include a color replacement unit that makes an amount corresponding to the degree to which the pixel is included in the correction region.
The present red-eye correction device corrects red-eye generated in a color image represented by image data having multiple gradations for a large number of pixels. Here, correction area information representing a correction area for correcting red eyes in the image is acquired by the correction area acquisition means, and range information indicating a range of red-eye colors in the color space of the image data by the red eye range acquisition means Is acquired. Regarding the pixels in the correction area corresponding to the acquired correction area information, when the image data is within the range corresponding to the acquired range information, the image data is replaced as follows.
That is, the original image data is replaced with the image data representing the eye color, but when the pixel to be replaced is a boundary portion of the correction area, the replacement amount of the image data includes the same pixel in the correction area. The amount depends on the degree.
Therefore, the image data cannot be completely replaced with the data representing the eye color when the boundary portion of the red eye correction area is within the range of the red eye color. It changes smoothly without changing suddenly. As a result, it is possible to correct the red eye so that the image in which the red eye is generated in the eye part does not feel uncomfortable.
According to the above-described invention, it is possible to correct the red eye so that the image in which the red eye is generated in the eye portion does not feel uncomfortable.

  The eye color may be various colors such as black, brown, and blue. Further, the color of the eye to be replaced may be uniform, may have a pattern, or the iris portion and the pupil portion may be different colors so as to achieve higher image quality.

When the red-eye correction device is configured by the various means described above, the eye portion of the color image represented by the multi-tone image data for each of a plurality of element colors for each of a plurality of pixels in a dot matrix shape is used. Correction area acquisition means for acquiring correction area information representing a correction area for correcting a generated red eye, and range information representing a range of red eye colors in the color space of the image data having each of the plurality of element colors as coordinate axes Red eye range acquisition means for acquiring image data of the target pixel while moving the target pixel sequentially with the image data of each pixel as a replacement target for the pixel of the correction region corresponding to the acquired correction region information When it is within the range corresponding to the acquired range information and all the same target pixel is included in the same correction area, the original image data for the same target pixel When the target pixel is replaced with image data representing the color of the eye and the target pixel is a boundary portion of the correction region, the same image is replaced when replacing the original image data with the image data representing the same color for the target pixel. A color replacement unit that sets the data replacement amount to an amount corresponding to the degree to which the target pixel is included in the correction area may be provided. The present red-eye correction device corrects red-eye generated in a color image expressed by image data having multiple gradations for each of a plurality of element colors for each of a number of pixels in a dot matrix. Here, for the pixels in the correction area corresponding to the acquired correction area information, the target pixels are sequentially moved using the image data of each pixel as a replacement target. Then, when the image data of the target pixel is within the range corresponding to the acquired range information, the image data is replaced as follows.
That is, when all the target pixels are included in the correction region, the original pixel data is replaced with image data representing the eye color for the target pixel. On the other hand, when the target pixel is a boundary portion of the correction area, the replacement amount of the image data includes the target pixel in the correction area when the target pixel is replaced with the image data representing the eye color from the original image data. The amount is determined according to the degree to be received. Therefore, by the same operation as described above, the color does not change suddenly inside and outside the region for correcting the red eye, and changes smoothly.
According to the above-described invention, it is possible to correct the red eye so that the image in which the red eye is generated in the eye portion does not feel uncomfortable.

  The plurality of element colors may be various, and may be composed of, for example, three colors of red (R), green (G), and blue (B), or from luminance data, blue color difference data, and red color difference data. It may be configured. It may be composed of three colors of cyan (C), magenta (M), and yellow (Y), or may be composed of four colors including black (K). Further, it may be composed of brightness data and two types of chromaticity data like each component of the Lab space that does not depend on the device.

Here, when the pixel is a boundary portion of the correction region, the color replacement unit determines a replacement ratio of the image data when replacing the original image data with the image data representing the eye color for the pixel. A configuration may be adopted in which the same pixel is included in the correction region. In other words, the ratio of replacement of the original image data with the image data representing the eye color in the pixels in the boundary portion is the ratio in which the pixels are included in the correction region. It is possible to replace the image data of the pixels in the boundary portion so as to make it feel like this.
According to the above invention, it is possible to make the boundary portion of the correction region feel natural with a simple configuration.

Further, as an example of replacing the image data of the pixel at the boundary portion, the color replacement unit divides the pixel into a predetermined number of divided regions, and the same divided region of the divided region whose center is inside the correction region. The ratio of all the numbers may be the replacement ratio of the image data. That is, the ratio of the pixels divided into a predetermined number of segmented regions and replaced with the image data representing the eye color from the original image data in the pixels at the boundary portion is the number of segmented regions whose center is inside the correction region. By setting the ratio, it can be easily obtained.
According to the above invention, it is possible to provide a simple example of a process for replacing the image data of the pixels in the boundary portion.

When a brightness information acquisition unit that acquires brightness information representing the brightness of the image data after replacement is provided, the color replacement unit replaces the image data with the brightness corresponding to the acquired brightness information. It is good. That is, the replaced image data is image data representing brightness corresponding to the brightness information.
According to the above invention, the brightness of the corrected image can be adjusted according to the brightness information, so that the convenience is improved and the red eye can be corrected without a sense of incongruity.
Here, the brightness information acquisition means receives the operation input for setting the brightness of the image data after being replaced by the color replacement means, and acquires the brightness information that is information representing the brightness, The color replacement unit may be configured to replace the image data with the luminance corresponding to the acquired brightness information when replacing the image data representing the eye color. That is, the image data after replacement is image data to be converted into an image having a luminance corresponding to the brightness information. Therefore, since the brightness of the replaced image data can be adjusted according to the brightness information, the convenience is improved and the red-eye can be corrected without a sense of incongruity.

As an example of the correction area, the correction area is a substantially circular area, and the correction area information includes information indicating the diameter of the correction area that is substantially circular, and information indicating the center coordinates of the correction area in the image. May be. Here, the information representing the diameter may be information representing the diameter or information representing the radius.
As an example of a configuration for acquiring the correction area information as described above, the correction area acquisition means receives an operation input for setting the radius of the correction area that is substantially circular, acquires information indicating the diameter, and Information representing the center coordinates may be acquired by receiving an operation input for designating the center position of the red eye of the displayed image. Then, the user can set the correction area with a simple configuration.
Of course, the correction area may have various shapes other than the circular area as described above. For example, the correction area may be an elliptical area, a rectangular area, a polygonal area, or the like.

  Various configurations of the range information representing the range of red-eye color are possible. As one example, the range information is information in which a range of red-eye colors in the color space of the image data is expressed as a distance from a predetermined red-eye target color, and the color replacement means The distance between the red-eye target color and the color of the pixel is calculated from the coordinates of the red-eye target color and the image data of the pixel in the correction area, and the distance is within the distance corresponding to the acquired range information. In some cases, the image data may be replaced. That is, the distance between the red-eye target color and the pixel color is calculated, and the image data is replaced when the distance is within the distance corresponding to the range information.

As an example of a suitable arithmetic expression for calculating the distance Distance between the red-eye target color and the pixel color when the image data is multi-gradation data for each of RGB, as in the invention according to claim 6 You may comprise. Here, change N to N + 1 and N-1, such as to change the N + 1 to N, since minor differences between the coefficients of the arithmetic expression is little effect on the value of the distance Distance, as set forth in claim 6 Included in the invention. Further, even an expression obtained by multiplying the right side of the arithmetic expression by a predetermined coefficient represents the distance between the red-eye target color and the pixel color, and thus is included in the invention described in claim 6 .

As an example of a suitable configuration for determining whether or not the image data of the pixel in the correction area is within the distance corresponding to the range information using the arithmetic expression, the configuration according to the invention according to claim 7 is used. May be. Since it is sufficient to determine whether the image data is within the range corresponding to the range information based on the ratio of the distance Distance to the longest distance from the red-eye target color in the color space of the image data, the range information is set to 0 to 0. A range of 1 can be used.

When a plurality of eye colors for replacing the image data are provided, the color replacement unit receives an input for selecting one of the plurality of eye colors and acquires information representing the color after replacement. The image data may be replaced so that the color corresponds to the information. Then, it is possible to replace the red-eye portion with a color of the eye that is more desired.
According to the above-described invention, the red-eye portion can be replaced with the color of the eye according to the desire, so that convenience is improved and the red-eye can be corrected so as not to make a sense of incongruity more reliably.
In addition, selection input such as a person in which country or region may be accepted and replaced with image data of eye color corresponding to the input person. Then, it becomes possible to correct to the eye color most suitable for the person.

By the way, the correction area acquisition means determines an eye area from the image based on the image data of each pixel, and acquires information representing the area as the correction area information. That is, since the eye area is determined as the correction area from the image based on the image data of each pixel, the red eye correction area is automatically extracted. The determined eye region may be a region including a white eye or an iris region.
According to the above invention, since the region for correcting the red eye is automatically extracted, the operation for correcting the red eye is reduced and the convenience is improved.

Further, the color replacement means obtains image data of another image in which no red-eye is generated, determines an iris region from the other image based on the image data, and performs the above-described operation based on the image data of the region. Acquires information representing the color of the eye, and corresponds to information representing the color of the eye from the original image data when the image data is within the range corresponding to the acquired range information for the pixels in the correction area When the pixel is replaced with the corrected image data and the pixel is a boundary portion of the correction region, the replacement amount of the image data is set in accordance with the degree to which the pixel is included in the correction region. Information representing the eye color is obtained from another image in which no red eye has occurred, and the red eye portion is corrected to the eye color.
Here, it may be determined whether or not the person who is trying to correct the red eye and another image are the same person, and the image data may be replaced when the person is the same person.

In this way, if the information representing the eye color is obtained from another image and the red eye is corrected, it will be more sure that the user will not feel a sense of incongruity. A correction area acquisition unit that determines an eye area from a color image based on the image data of each pixel and acquires correction area information representing the area; and a range of red-eye color in the color space of the image data A red-eye range acquisition unit that acquires range information representing the image, and acquires image data of another image in which no red eye has occurred, determines an iris region from the other image based on the image data, and images of the region Information representing the eye color is acquired based on the data, and the image data of the pixels in the correction area corresponding to the acquired correction area information is within a range corresponding to the acquired range information. Rutoki may be configured to and a color replacement means for replacing the image data corresponding to the information representing the color of the eye from the original image data. That is, image data of another image in which no red eye is generated is acquired, an iris region is determined from another image based on the acquired image data, and an eye color is determined based on the image data of the determined region. Information to represent is acquired. For the pixels in the correction area corresponding to the acquired correction area information, when the image data is within the range corresponding to the acquired range information, the original image data is changed to information representing the eye color from another image. Replaced with corresponding image data. In other words, information representing the eye color is acquired from another image in which no red eye is generated, and the red eye portion is corrected to the eye color.
According to the above-described invention, it is possible to correct the red eye so that the image in which the red eye is generated in the eye portion does not feel uncomfortable.

Further, when the brightness information acquisition means is provided, the image data after replacement becomes image data representing brightness corresponding to the brightness information, and it is possible to correct red eyes without a sense of incongruity. Correction area acquisition means for acquiring correction area information representing a correction area for correcting red eyes among color images represented by multi-tone image data for each pixel, and red eyes in the color space of the image data Corresponding to the red-eye range acquisition means for acquiring range information representing the range to be color, brightness information acquisition means for acquiring brightness information representing the brightness after replacement of the image data, and the acquired correction area information When the image data is within a range corresponding to the acquired range information for the pixel of the correction area to be corrected, the image data representing the eye color from the original image data and the acquisition It may be configured to and a color replacement means for replacing the image data representing the brightness corresponding to the brightness information. That is, for the pixels in the correction area corresponding to the acquired correction area information, when the image data is within the range corresponding to the acquired range information, the image data representing the eye color is obtained from the original image data. Thus, it is replaced with image data representing the brightness corresponding to the acquired brightness information.
According to the above-described invention, it is possible to correct the red eye so that the image in which the red eye is generated in the eye portion does not feel uncomfortable.

By the way, the above-described red-eye correction device may be implemented independently, or may be implemented together with other methods in a state of being incorporated in a certain device, and includes various aspects as an idea of the invention. However, it can be changed as appropriate.
In addition, the above-described method for correcting red eyes naturally proceeds in accordance with a predetermined procedure, and there is naturally an invention in that procedure. Therefore, the present invention can also be applied as a method, and the invention according to claims 8 and 10 basically has the same effect.

When trying to implement the present invention, a predetermined program may be executed by the red-eye correction device. Therefore, the present invention can also be applied as the program, and the invention according to claims 9 and 11 basically has the same effect. Furthermore, it is conceivable that a medium on which the program is recorded is distributed and the program is appropriately read from the recording medium into a computer. That is, the present invention can be applied to a computer-readable recording medium that records the program, and basically has the same effect.
Of course, it is needless to say that the configurations described in claims 2 to 7 can be made to correspond to the method, the program, and the medium on which the program is recorded.
Here, the recording medium may be any recording medium developed in the future in addition to the magnetic recording medium and the magneto-optical recording medium. There is no limitation on the replication stage such as primary replica and secondary replica. The idea of the present invention also includes a case where a part is realized by hardware, and a case where a part is recorded on a recording medium and read as needed.

As described above, according to the inventions according to claims 1 to 3 and claims 8 to 11 , an image in which red eyes are generated in the eye part is more reliably prevented from feeling uncomfortable. Red eyes can be corrected.

According to the fourth aspect of the present invention, the correction area can be easily specified with a simple configuration.
According to the fifth aspect of the present invention, since the image data is replaced when the pixel color is within the distance corresponding to the range information from the red-eye target color, the red-eye portion to be corrected more reliably is the eye color. It can be corrected.
According to the sixth aspect of the present invention, it is possible to provide a suitable arithmetic expression for calculating the distance between the red-eye target color and the pixel color, and to correct the red-eye portion to be corrected more reliably to the eye color. Thus, it is possible to obtain a corrected image with good image quality.

According to the seventh aspect of the present invention, the range of red eyes can be expressed in the range of 0 to 1, so that the configuration can be simplified.

Hereinafter, embodiments of the present invention will be described in the following order.
(1) System configuration including red-eye correction device:
(2) Red-eye correction device configuration:
(3) Operation of the red-eye correction device:
(4) Summary:

(1) System configuration including red-eye correction device:
FIG. 1 shows a schematic configuration of a system including a red-eye correction device and peripheral devices according to an embodiment of the present invention. The system includes a personal computer (PC) 10 that is a red-eye correction device according to the present invention, a color-printable inkjet printer 20 that is an image output device, a digital camera 30, and the like. This red-eye correction device is a device that corrects the red-eye color generated in the eye when a person is photographed with a digital camera or the like, and is configured so that the user can easily correct the red-eye. It is assumed that the user of the present red-eye correction device is an amateur for computer image correction, and includes professional photographers and the like. Of course, even those who are familiar with computer image correction can easily correct red eyes with this apparatus.
The PC 10 includes a CPU 11 that is the center of arithmetic processing, and the CPU 11 controls the entire PC 10 via a system bus 10a. The bus 10a is connected to a ROM 12, a RAM 13, a CD-ROM drive 15, a flexible disk (FD) drive 16, various interfaces (I / F) 17a to 17e, and the like. A hard disk (HD) 14 is also connected via a hard disk drive. A so-called desktop PC is employed as the computer of this embodiment, but a computer having a general configuration can be employed as the computer.

The HD 14 stores an operating system (OS), an application program (APL), and the like as software. At the time of execution, the CPU 11 appropriately transfers these software to the RAM 13 and executes the program while appropriately accessing the RAM 13 as a temporary work area. Note that the red-eye correction program of the present embodiment realizes various functions in cooperation with the APL and the OS, but may be a single APL or may be incorporated in the OS.
The peripheral device I / F (PIF) 17a is connected to a digital camera 30, a color scanner (not shown), and the like. A display 18a, which is a display means for displaying an image based on image data, is connected to the CRTI / F 17b, and a keyboard 18b and a mouse 18c are connected to the input I / F 17c as operation input devices. Further, the printer 20 is connected to the printer I / F 17e through, for example, a parallel I / F cable.
The HD 14 is a medium on which the red-eye correction program according to the present invention is recorded. The medium may be, for example, a CD-ROM, an FD 16a, a magneto-optical disk, a nonvolatile memory, or the like. Of course, it is also possible to connect the communication I / F 17d such as a modem to the Internet network, access a predetermined server, and download and execute the red-eye correction program.

The printer 20 that prints an image subjected to red-eye correction prints on a medium using cyan (C), magenta (M), yellow (Y), and black (K) inks. Of course, various image output devices such as a printer that uses inks other than four colors, a bubble printer that generates bubbles in the ink passage and ejects ink, and a laser printer can be employed.
As shown in FIG. 2, in the printer 20, a CPU 21, ROM 22, RAM 23, communication I / O 24, control IC 25, ASIC 26, I / F 27, and the like are connected via a bus 20a. The communication I / O 24 is connected to the printer I / F 17e of the PC 10, and the printer 20 receives a print job including data converted to CMYK and a page description language transmitted from the PC 10 via the communication I / O 24. . The ASIC 26 outputs applied voltage data based on CMYK data to the head drive unit 26 a while transmitting and receiving a predetermined signal to and from the CPU 21. Then, the head drive unit 26a generates a voltage pattern applied to the piezo element built in the print head, and causes the print head to eject ink. The carriage mechanism 27a and the paper feed mechanism 27b connected to the I / F 27 perform the main scanning of the print head and the sub-scan by sequentially feeding out the media. Then, the CPU 21 controls each unit according to the program written in the ROM 22.

  In the PC 10, the BIOS is executed based on the above hardware, and the OS and APL are executed in the upper layer. Various drivers such as a printer driver for controlling the printer I / F 17e are incorporated in the OS, and the hardware is controlled. The printer driver can perform two-way communication with the printer 20 via the printer I / F 17e, receives print data from the APL, creates a print job, and sends the print job to the printer 20.

(2) Red-eye correction device configuration:
FIG. 3 schematically shows a configuration of a red-eye correction device realized by the function of the red-eye correction program. The red-eye correction program is composed of a plurality of modules, and various means U1 to U4 referred to in the present invention are configured corresponding to each module. Basically, based on the information acquired by the means U1 to U3, the color replacement means U4 performs processing for replacing the red-eye portion with the eye color on the image data.
In this embodiment, the above processing is performed on image data composed of RGB defined in the sRGB color space. The image data includes multiple gradations (for example, gradation value 0) for each of a plurality of element colors RGB for each of a large number of pixels in a dot matrix having a horizontal m0 × vertical n0 pixel (m0, n0 are integers of 2 or more). ˜255 (256 gradations) and data representing a color image. Of course, it is also possible to perform the above processing on image data composed of luminance (Y component), B color difference (U component), and R color difference (V component) in the YUV color system. Also, each component of the image data can have various gradation numbers, and other than 256 gradations, for example, 1024 gradations may be used.

The correction area acquisition unit U1 acquires correction area information representing a correction area for correcting the red-eye generated in the eye portion of the image represented by the image data. In the present embodiment, the correction area is a substantially circular area, and the radius Radius (information indicating the diameter) of the correction area and information indicating the center coordinates of the correction area are used as the correction area information. These pieces of information are acquired by an operation input to the PC 10.
It is also possible to determine the eye area from the image based on the image data of each pixel, and acquire information representing the eye area as correction area information. There are various methods for determining the eye area. For example, as disclosed in paragraph 0030 of Japanese Patent Laid-Open No. 10-75374, by extracting only the image data of the eye area based on the connectivity of pixels with low brightness, the eye area is extracted from the image. Can be determined. Further, since the eye color is not a skin color, a skin color region (for example, a pixel region where each RGB value of the image data falls within a predetermined range) is extracted, and a region surrounded by the extracted skin color region is predetermined. When the shape substantially coincides with the eye shape, the enclosed region may be determined as the eye region, and information representing the eye region may be acquired as correction region information.

  The red-eye range acquisition unit U2 acquires range information representing a range of red-eye colors in the color space of image data having the three element colors RGB as coordinate axes. In the present embodiment, the range of red-eye color in the same color space is represented as a distance from a predetermined red-eye target color. Then, a relative value of the same distance is accepted by an operation input, and the input value is acquired as a tolerance Tolerance (range information) for a red-eye color.

  The brightness information acquisition unit U3 acquires brightness information representing the brightness of the image data after being replaced by the color replacement unit. In the present embodiment, the brightness information is numerically expressed as intensity Intensity and the intensity is information indicating luminance. However, information indicating brightness can also be used as brightness information. The intensity is received as a numerical value by an operation input.

FIG. 4 shows a display example of a setting input screen for the means U1 to U3 to accept input of various information. The screen is provided with an image display field 91a, a cross pointer 91b, an eye color selection field 91c, a radius input field 91d, a tolerance input field 91e, an intensity input field 91f, and various buttons 91g-j.
In the image display column 91a, the input image data is displayed. A cross pointer 91b is displayed in the display field 91a, and the center coordinates of the correction area can be set and input by moving the pointer 91b with a mouse.

In the eye color selection column 91c, the corrected eye color can be selected. As eye color options, there are user settings, people by region such as Japanese, different images, etc. in addition to black, brown, blue and the like. When user settings are selected and input, a color palette is displayed and a desired eye color can be created. When a person by area is selected and input, the eye color corresponding to the person in the input area is selected. When another image is selected and input, information representing the eye color is acquired from the other image.
In the radius input field 91d, a knob that can slide in the left-right direction is displayed. The radius of the correction area can be adjusted by moving the knob with the mouse. In this embodiment, the radius decreases when the knob is moved to the left side, and the radius increases when the knob is moved to the right side.

Also in the tolerance input field 91e, a knob that can slide in the left-right direction is displayed. By moving the knob with the mouse, the tolerance Tolerance that represents the range of red eyes can be adjusted. In this embodiment, the tolerance is set to a value of 0 to 1. The tolerance is reduced when the knob is moved to the left (the left end is 0), and the tolerance is increased when the knob is moved to the right ( The right end is 1).
Also in the intensity input field 91f, a knob that can slide in the left-right direction is displayed. By moving the knob with the mouse, intensity Intensity representing brightness can be adjusted. In this embodiment, the strength is set to a value of 0 to 1. The strength is reduced when the knob is moved to the left (the left end is 0), and the strength is increased when the knob is moved to the right (the right end is 1). ).

  When the region extraction button 91g is clicked with the mouse, the eye region is automatically extracted from the image. When the image reference button 91h is clicked, information representing the eye color is automatically acquired from another image in which no red eye is generated. When the correction execution button 91i is clicked, the red-eye part is corrected to the eye color according to the set condition.

Returning to FIG. 3, the description will be continued. The color replacement unit U4 moves the target pixel sequentially using the image data of each pixel as a replacement target for the pixels in the correction area corresponding to the acquired correction area information, and the image data of the red eye part, that is, the target pixel is used as the range information. When it is within the corresponding range, the image data of the red-eye portion is replaced with image data representing the eye color. In the case of image data representing an image to be displayed on the display, since gamma correction is performed, after performing inverse gamma correction, the distance between the red-eye target color in the RGB color space and the color of the pixel in the correction area is calculated. Then, it is determined whether this distance is within a range corresponding to the range information. For example, in the case of gamma-corrected image data of γ = 2.2, assuming that each RGB value of the image data is R0, G0, B0 (all values from 0 to 255), the image after inverse gamma correction Each RGB value C2r, C2g, C2b (all values of 0 to 255) of the data can be calculated by the following arithmetic expression.
C2r = 255 × (R0 / 255) ^0.45 ... (1)
C2g = 255 × (G0 / 255) ^0.45 ... (2)
C2b = 255 × (B0 / 255) ^0.45 ... (3)

After the inverse gamma correction described above, the distance Distance between the red-eye target color and the color of the pixel in the correction area is calculated. Here, as a result of repeating the test while changing the calculation formula, the coordinate values of the red-eye target color are C1r (0 ≦ C1r ≦ N) and C1g (0 ≦ C1g ≦ N) in the order of RGB, where N is a positive integer. , C1b (0 ≦ C1b ≦ N), Ravg = (C1r + C2r) / 2, and the distance Distance is calculated by the following arithmetic expression, the red eye part to be corrected can be surely corrected to the eye color, A corrected image with good image quality could be obtained.
Distance = [{2 + Ravg / (N + 1)} × (C1r−C2r) ² + 4 × (C1g−C2g) ² + {2+ (N−Ravg) / (N + 1)} × (C1b−C2b) ² ] ^1/2
···(Four)
In this embodiment, since N = 255, it is calculated by the following arithmetic expression.
Distance = [(2 + Ravg / 256) × (C1r−C2r) ² + 4 × (C1g−C2g) ² + {2+ (255−Ravg) / 256} × (C1b−C2b) ² ] ^1/2
···(Five)

Here, a slight difference in each coefficient of the arithmetic expression, such as changing N to N + 1 or N-1, or changing N + 1 to N, hardly affects the value of the distance Distance. Therefore, for example, the distance Distance may be calculated by the following arithmetic expression.
Distance = [(2 + Ravg / 255) × (C1r−C2r) ² + 4 × (C1g−C2g) ² + {2+ (255−Ravg) / 255} × (C1b−C2b) ² ] ^1/2 (5) ')
Alternatively, the right side of the arithmetic expressions (4) and (5) may be an expression obtained by multiplying a predetermined coefficient. Even in this case, the distance between the red-eye target color and the pixel color is not changed.

Although the above arithmetic expressions (4) and (5) are good in that a good corrected image can be obtained, the distance Distance may be calculated by the following arithmetic expression in order to simplify the arithmetic processing. .
Distance = {(C1r−C2r) ² + (C1g−C2g) ² + (C1b−C2b) ² } ^1/2
... (6)

In determining whether the distance Distance is within the range of red-eye color, the distance Distance is converted to a value between 0 and 1. When the RGB coordinates in the RGB color space are represented by (R, G, B) (0 ≦ R ≦ N, 0 ≦ G ≦ N, 0 ≦ B ≦ N), as shown in FIG. Coordinates (0,0,0), (0,0, N), (0, N, 0), (0, N, N), (N, 0,0), (N, 0, N), ( N, N, 0), (N, N, N) and the red-eye target color coordinates (C1r, C1g, C1b) are obtained by the above equation (5), and the maximum distance MaxDistance is calculated. Based on the ratio of the distance Distance to the maximum value MaxDistance, it is determined whether or not it is within the range of red eye color. In the illustrated example, N = 255, and the distance between the coordinates (255, 255, 0) and the coordinates of the red-eye target color is the largest. That is, the maximum value MaxDistance of the distance is a value calculated by the following formula.
MaxDistance = [(2 + C1r / 256) × C1r ² + 4 × (C1g−255) ² + {2+ (255−C1r) / 256} × (C1b−255) ² ] ^1/2
... (7)

  Then, the ratio of the distance distance to the maximum distance value MaxDistance is always 1 or less. Since the tolerance Tolerance acquired by accepting the operation input from the setting input screen shown in FIG. 4 is a value of 0 to 1, it is within the range of red-eye color when Distance / MaxDistance ≦ Tolerance. The image data is replaced. Thus, since it is only necessary to determine whether the image data is within a range corresponding to the range information based on the distance distance ratio, the range information can be expressed in a range of 0 to 1, and the configuration is It can be simplified.

Returning to FIG. 3 again, the description will be continued. When the distance distance ratio is less than the tolerance Tolerance and all target pixels are included in the correction area, the image data representing the eye color from the original image data for the target pixel corresponds to the brightness information. Is replaced with image data representing the brightness. For example, when black is selected as the eye color, if the intensity Intensity having a value of 0 to 1 is used, each RGB value C3r, C3g, C3b of the image data after replacement (all of 0 to 255) Value) can be calculated by multiplying the minimum value of RGB values C2r, C2g, and C2b before replacement by intensity Intensity.
C3r = C3g = C3b = Minimum (C2r, C2g, C2b) x Intensity (8)
Then, the saturation of the red eye portion is reduced with respect to the image in which the red eye is generated in the eye portion, and the red eye is corrected to the eye color.

By replacing the image data using the above equation (8), the value of the image data before replacement is reflected in the value of the image data after replacement, so that the image quality of the image after red-eye correction is improved. Can do. Of course, in order to simplify the calculation for replacing the image data, the value of the replaced image data may be obtained by multiplying the predetermined value by the intensity Intensity as in the following calculation formula.
C3r = C3g = C3b = 255 × Intensity (9)
Here, the intensity Intensity represents the approximate luminance, and indirectly represents the luminance when the above equation (8) is used. Of course, since each RGB component value may be weighted differently when expressing luminance, C3r, C3g, C3g, C3b, C3b, C3r, C3g, C3b may be set to a different value.

Generally, when each RGB value of the eye color is represented by Er, Eg, Eb, the RGB value of the image data after replacement can be calculated by the following arithmetic expression.
C3r = Er × {Minimum (C2r, C2g, C2b) / 255} × Intensity (10)
C3g = Eg × {Minimum (C2r, C2g, C2b) / 255} × Intensity (11)
C3b = Eg × {Minimum (C2r, C2g, C2b) / 255} × Intensity (12)
Or
C3r ＝ Er × Intensity (13)
C3g ＝ Eg × Intensity (14)
C3b ＝ Eb × Intensity (15)
In the above formulas (10) to (12), the value of the original image data is reflected in the value of the image data after replacement, so that the image quality of the image after red-eye correction can be improved.
As described above, the color replacement unit U4 replaces the image data representing the brightness corresponding to the acquired brightness information with the image data representing the eye color.

  In addition, when the target pixel is the boundary portion of the correction area, the color replacement unit U4 determines the replacement amount of the image data when replacing the original pixel data with the image data representing the same color for the target pixel. The amount is determined according to the degree to which the target pixel is included in the correction area.

FIG. 6 is a diagram for explaining the image data replacement process at the boundary portion of the correction area. Here, the correction region 50 is a substantially circular region with the center coordinate 51 as the center. The pixels 52 in the correction area are pixels in which all parts are included in the correction area 50. That is, the image data of the pixel 52 is obtained by the above-described arithmetic expressions (8) to (15). On the other hand, the pixels 54 outside the correction area indicated by dotted lines in the figure are pixels in which all portions are out of the correction area 50. Therefore, the image data of the pixel 54 is not replaced.
The boundary portion pixel 53 is a pixel whose inside is the boundary portion of the correction region 50. For the pixel 53, when replacing the image data, the replacement ratio of the image data is the ratio at which the pixel 53 is included in the correction area 50. Specifically, the replacement ratio is determined as follows to replace the image data.

  First, the pixel 53 is substantially equally divided into a predetermined number of divided regions 55 of horizontal m1 × vertical n1 (m1, n1 are integers of 2 or more). In this embodiment, m1 = n1 = 4, and the pixel 53 is equally divided into 16 segment areas 55. Next, for each pixel 53, the number n2 of segmented regions in which the center of the segmented region 55 is inside the correction region 50 is obtained. Then, the ratio of the number n2 of the obtained divided areas to the number 16 of all the divided areas of the pixel 53, that is, n2 / 16 is set as the replacement ratio P of the image data. For example, in the case of the pixels 53a and 53b shown in the figure, the number n2 of the divided areas whose centers are inside the correction area 50 is 8, 13, respectively, so that the replacement ratio P of the image data is 8/16, 13/16. Become.

Here, the RGB values C3r, C3g, and C3b are once calculated by the above equations (8) to (15), and the RGB values C3r, C3g, and C3b that are the image data in the RGB color space are converted into images in the HIS color space. The component values H3, I3, and S3 of the data are converted, and the RGB values C2r, C2g, and C2b of the original image data are converted into the component values H2, I2, and S2 of the image data in the HIS color space. H2 and H3 are hue (Hue) component values, I2 and I3 are luminance (Intensity) component values, and S2 and S3 are saturation (Saturation) component values. Specifically, H2, H3, I2, I3, S2, and S3 can be calculated by the following arithmetic expression, with A1 being a predetermined 3 × 3 matrix.

Then, using the calculated H2, H3, I2, I3, S2, S3 and the replacement ratio P, the respective component values H4, I4, S4 of the image data after replacement in the HIS color space are calculated.
H4 = H2 (18)
I4 = I2− (I2−I3) × P (19)
S4 = S2− (S2−S3) × P (20)
Thereafter, the component values H4, I4, and S4 of the image data in the HIS color space are returned to the component values C4r, C4g, and C4b of the image data in the RGB color space.

As described above, when the pixel that is the boundary portion of the correction area is replaced with the image data representing the eye color from the original image data, the replacement ratio of the image data is the ratio that the pixel is included in the correction area.
As a result, the image data is not completely replaced with the eye color when the boundary portion of the correction area is within the range of the red eye color, so the color does not change suddenly inside and outside the correction area, and changes smoothly. . As a result, it is possible to correct the red eye so as not to make the user feel uncomfortable.

  Further, the color replacement unit U4 acquires image data of another image in which no red-eye is generated, determines an iris region from the other image based on the acquired image data, and based on the image data of the determined region It is also possible to acquire information representing the eye color. As a result, information representing the color of the eye is obtained from another image in which no red-eye is generated, and the red-eye portion of the correction area is corrected to the color of the eye, and the red-eye is corrected so as not to make the user feel uncomfortable more reliably. It becomes possible.

Note that when the red-eye portion is replaced with image data representing the eye color in the image data that has been subjected to inverse gamma correction, processing for returning to the image data that has been subjected to gamma correction is performed. The RGB values R1, G1, and B1 (all values from 0 to 255) of the image data after gamma correction can be calculated by the following arithmetic expression.
R1 = 255 × (C4r / 255) ^2.2 ... (22)
G1 = 255 × (C4g / 255) ^2.2 ... (23)
B1 = 255 × (C4b / 255) ^2.2 ... (24)

(3) Operation of the red-eye correction device:
FIG. 7 is a flowchart showing the red-eye correction process performed by the various means U1 to U4. Details of processing performed by the red-eye correction device will be described below according to the flowchart.
When the red-eye correction program according to the present embodiment is started, first, image data representing a color image before correction is input, and the setting input screen shown in FIG. 4 is displayed on the display (step S105; “Step” is omitted). Note that the position of the cross pointer 91b, the eye color selection column 91c, and the various input columns 91d to 91f are displayed under default conditions or previously input conditions. The region extraction button 91g can be clicked only when “another image” is selected and input in the eye color selection field 91c.

  The input image data is displayed in the image display field 91a. The input image data may be image data captured by the digital camera 30, a scanner or a video camera (not shown), or image data recorded on the FD 16a or the like. In addition, when inputting image data from a digital camera or the like, it is not necessary to read the entire data in a lump, and it may be partially read, or when it is called from another APL, it is used for data transfer. It may be only the passing of a pointer representing the buffer area to be used.

  When the setting input screen is displayed, it is determined whether or not an eye color selection input has been made in the eye color selection field 91c (S110). When the input for selecting the eye color is not accepted, the process proceeds to S130, and when the input for selecting the eye color is accepted, the process proceeds to S115. In S115, it is determined whether “another image” is selected and input from the selection field 91c. When an input for selecting “another image” is received, eye color determination processing is performed (S120), and the process proceeds to S130.

FIG. 8 is a flowchart showing the eye color determination process, and FIG. 9 schematically shows how the eye color is determined. First, when the image reference button 91h is clicked, an image file selection screen (not shown) is displayed, and an image file selection input for storing image data classified by pixel of an image in which no red-eye occurs is received. The image data of the file is read into the RAM, and the image data of another image 61 in which no red eye is generated is acquired (S205). Next, based on the image data of another image 61, an eye area 62 including a white eye is determined (S210). For example, a skin color region is extracted, and when the region surrounded by the extracted skin color region substantially matches a predetermined eye shape, the surrounded region is determined as an eye region including white eyes.
Further, an iris region 63 is determined from another image 61 based on the image data of the pixels in the eye region 62 including the white eye (S215). For example, a white-eye area (for example, a pixel area where each RGB value of the image data is equal to or greater than a predetermined value) is extracted, and an eye area excluding the extracted white-eye area is determined as an iris area.

Then, based on the image data of the iris region 63, information representing the eye color is acquired (S220), and this flow ends. Here, there are various kinds of information representing the color of the eye. For example, the RGB values of the image data may be averaged for all the pixels in the iris area, and the iris pattern may be left as it is. As described above, it may be image data for each pixel in the iris region.
Thus, since the eye area is determined as the correction area from the image based on the image data of each pixel, the area for correcting the red eye is automatically extracted, and the work for correcting the red eye is reduced, which is convenient. is there. In addition, information representing the color of the eye is obtained from another image that does not have red eyes, and the red eye portion is corrected to the eye color of another image that does not have red eyes, so that it does not feel uncomfortable more reliably. It is possible to correct red eyes.

If an input for selecting other than “another image” is received in S115, the process proceeds to S125, and information representing the eye color is acquired. Here, when an input for selecting one of a plurality of eye colors such as black, brown, and blue is received, each RGB value Er, Eg, Eb (representing the color after replacement) of the corresponding eye color Information). When the user setting is selected and input, a color palette is displayed, and an operation input to the color palette is received to obtain RGB values Er, Eg, and Eb of the corresponding eye color. When a person for each region is selected and input, the input for the region is selected with reference to a color table for each region (not shown) that associates the information representing the region with the RGB values that represent the eye color of the person in the region. The RGB values Er, Eg, Eb representing the eye color corresponding to the person in the designated area are acquired.
Thus, it is convenient because the eye color can be selected and the eye color corresponding to the person in the input area can be corrected. Therefore, it is possible to replace the red-eye portion with the color of the eye according to the desire, and it is possible to correct the red-eye so as not to make the user feel uncomfortable.

Thereafter, the process proceeds to S130, in which various parameters are sequentially acquired, and processing corresponding to operations on the various buttons 91g to 91j is performed. In S130, when an operation input for designating the center position of the red eye is received by moving the cross pointer 91b, the cross pointer 91b is moved to the corresponding position and displayed, and the image displayed in the image display column 91a is displayed. Information corresponding to the position of the cross pointer 91b is acquired as information representing the center coordinates of the red eye.
In S135, when an operation input for setting the radius of the correction area is received in the radius input field 91d, a numerical radius Radius corresponding to the position of the knob is acquired. The cross pointer 91b is displayed as a size approximately proportional to the radius Radius.
The information indicating the center coordinates of the red eye and the radius Radius are correction area information indicating a correction area for correcting the red eye. That is, the processing of S105 and S130 to S135 performed by the PC 10 constitutes a correction area acquisition unit.

  In S140, when an operation input for setting a red-eye range is accepted in the tolerance input field 91e, a numerical tolerance Tolerance corresponding to the position of the knob is acquired. The tolerance Tolerance is range information in which a range of red-eye colors in the RGB color space is expressed as a distance from a predetermined red-eye target color. That is, the processing of S105 and S140 performed by the PC 10 constitutes a red-eye range acquisition unit.

  In S145, when an operation input for setting the brightness of the image data is received in the intensity input field 91f, a numerical intensity Intensity corresponding to the position of the knob is acquired. The intensity Intensity is brightness information representing the brightness of the image data after replacement. That is, the processing of S105 and S145 performed by the PC 10 constitutes brightness information acquisition means.

When “another image” is selected and input in the eye color selection field 91c, the region extraction button 91g can be clicked. In S150, it is determined whether or not the region extraction button 91g has been clicked. When the button 91g is clicked, the eye area determination process in S155 is performed, and then the process proceeds to S160. If the button 91g is not clicked, the process proceeds to S160 without performing the process of S155.
In the eye area determination process in S155, an eye area is determined from the image based on the image data of each pixel, and information representing the area is acquired as correction area information. For example, as shown in FIG. 9, when a skin color region is extracted and the region surrounded by the extracted skin color region substantially matches the shape of a predetermined eye, the surrounded region is changed to the eye region ( Information including the eye area is acquired as correction area information. That is, the processing of S150 and S155 performed by the PC constitutes a correction area acquisition unit in another meaning.

In S160, it is determined whether or not the correction execution button 91i has been clicked. If the button 91i is clicked, the color replacement process of S165 is performed, and then the process proceeds to S170. If the button 91g is not clicked, the process proceeds to S170 without performing the process of S165.
FIG. 10 is a flowchart showing the color replacement process performed in S165.
First, using the above equation (7), each coordinate (0,0,0), (0,0,255), (0,255,0), (0,255,255), (255,0, 0), (255, 0, 255), (255, 255, 0), (255, 255, 255) and the coordinates (C1r, C1g, C1b) of the red-eye target color according to the above equation (5), respectively. The maximum value MaxDistance of the obtained distance is calculated (S305). Here, since the coordinates (C1r, C1g, C1b) are coordinates based on the inverse gamma correction, the calculated maximum value MaxDistance is a value based on the image data subjected to the inverse gamma correction.

  Next, the target pixel to be replaced with the image data is set in the correction area corresponding to the acquired correction area information (S310). When the correction area information is composed of information indicating the radius of the correction area and information indicating the center coordinates of the correction area, pixels included in the circular area corresponding to the information are extracted as a correction area. The target pixel is set from the correction area. And the process which replaces the image data of a target pixel is performed, moving a target pixel sequentially. In the present embodiment, a large number of pixels are arranged in an orderly manner in the vertical and horizontal directions, and the order of image data replacement processing starts from the uppermost leftmost pixel and continues to the rightmost pixel in order, and then one by one. From the leftmost pixel to the rightmost pixel in order, and finally the lowest rightmost pixel. Of course, the order of the replacement process can be changed as appropriate.

  Since the input image data (RGB values R0, G0, B0) has been subjected to gamma correction, after setting the target pixel, reverse gamma correction is performed using the above equations (1) to (3). Each RGB value C2r, C2g, C2b is calculated (S315). After that, the distance Distance between the red-eye target color (RGB values C1r, C1g, C1b) and the color of the pixel in the correction area (RGB values C2r, C2g, C2b) is calculated using the above equation (5) (S320). Then, it is determined whether or not the distance Distance is within the distance corresponding to the range information, that is, whether the ratio of the distance Distance to the maximum value MaxDistance is equal to or smaller than the tolerance Tolerance (S325). If the ratio is greater than the tolerance Tolerance, it is determined that it is not a red-eye part, and the image data is not replaced, and the process proceeds to S350. On the other hand, if the ratio is equal to or smaller than the tolerance Tolerance, it is determined that the portion is a red-eye portion, and the process proceeds to S330 to replace the image data. Thus, since the image data is replaced when the color of the target pixel is within the distance corresponding to the range information from the red-eye target color, it is possible to reliably correct the red-eye portion to be corrected to the eye color. is there.

In S330, it is determined whether or not the target pixel is a boundary portion of the correction area. If it is not a boundary part, the process proceeds to S335, and if it is a boundary part, the process proceeds to S340 to perform boundary color replacement processing.
In S335, which is performed when all the target pixels are included in the correction area, the original image data (RGB values C2r, C2g, C2b) corresponds to the intensity Intensity using the above formulas (10) to (12). The image data (RGB values C3r, C3g, C3b) representing the eye color of brightness is substituted, and the process proceeds to S345. Then, when all the target pixels are included in the correction area, the red color is corrected to the eye color for the target pixel. In addition, the brightness of the image based on the replaced image data can be adjusted in accordance with the setting of the intensity Intensity, which is convenient and further allows red eyes to be corrected without a sense of incongruity. Further, when the information indicating the color after replacement is acquired by receiving the selection input, the image data is replaced so that the color corresponding to the information indicating the color after replacement is obtained, so that the red-eye portion can be selected as desired. It can be replaced with the eye color, which is convenient and allows the red eye to be corrected so as not to make the user feel uncomfortable.

On the other hand, when the target pixel is the boundary portion of the correction area, the boundary color replacement process shown in FIG. 11 is performed (S340), and the process proceeds to S345.
First, the target pixel is equally divided into 4 × 4 divided areas, and the number n2 of divided areas whose center is inside the correction area is calculated (S405). Next, a ratio of the calculated number n2 to 16 which is the number of all the divided areas is calculated and set as a replacement ratio P of image data (S410).
Further, using the above formulas (10) to (12), the original image data (RGB values C2r, C2g, C2b) is converted into image data (RGB values C3r, C2r, C2b) representing the eye color with brightness corresponding to the intensity Intensity. C3g, C3b) are temporarily replaced (S415).
Thereafter, the image data in the RGB color space before and after replacement is converted into image data in the HIS color space (S420). That is, using the above equations (16) and (17), the RGB values C2r, C2g, and C2b are converted into the component values H2, I2, and S2 of the image data in the HIS color space, and the RGB values C3r, C3g, and C3b are converted. The image data in the HIS color space is converted into component values H3, I3, and S3.

Then, using the above equations (18) to (20), the respective component values H4, I4, and S4 of the image data after replacement are calculated so that the replacement ratio of the image data is the ratio that the target pixel is included in the correction area. (S425).
Thereafter, using the above equation (21), the component values H4, I4, and S4 of the image data in the HIS color space are converted into the RGB values C4r, C4g, and C4b, and returned to the image data in the RGB color space (S430). ), This flow ends.
Then, when the target pixel is a boundary portion of the correction area, the replacement amount of the image data is set to a ratio in which the target pixel is included in the correction area. That is, it is possible to replace the image data of the pixels in the boundary portion so as to make the boundary portion of the correction area feel natural with a simple configuration. In other words, since the image data is not completely replaced with data representing the eye color, the color does not change abruptly inside and outside the region for correcting the red eye and changes smoothly.

Returning to FIG. 10, the description will be continued. Since the image data after replacement (RGB values C3r, C3g, C3b or C4r, C4g, C4b) is data that has not been subjected to gamma correction, in S345, using the above equations (22) to (24), Gamma correction is performed on the image data, and image data after the gamma correction (RGB values R1, G1, B1) is calculated.
Thereafter, it is determined whether or not the processing of S310 to S345 has been performed for all the pixels in the correction area (S350). When the same process is performed for all the pixels in the correction area, this flow is terminated, and when it is not performed for all the pixels, the processes of S310 to S350 are repeatedly performed.
As described above, the processing of S105 to S125 and S165 of FIG. 7 performed by the PC 10 constitutes a color replacement unit.

  For example, as shown in FIG. 12, when the range of the red eye color exists over the inside and outside of the correction area 50, all the pixels 52 included in the correction area 50 are replaced with the original image data representing the eye color. The red-eye part is corrected to the eye color. On the other hand, the pixels 54 that are completely out of the correction area 50 are left as the original image data and are not corrected to the eye color. Here, with respect to the pixel 53 at the boundary portion of the correction area 50, the image data is replaced at a rate at which the pixel 53 is included in the correction area 50. Therefore, the image data is completely replaced with data representing the eye color. Absent. Therefore, the color does not change suddenly inside and outside the region for correcting the red eye and changes smoothly. As a result, it is possible to correct the red eye so that the image in which the red eye is generated in the eye part does not feel uncomfortable.

  After S160 or S165 in FIG. 7, it is determined whether or not the save button 91j has been clicked (S170). If the button 91j is clicked, the process proceeds to S175, the image data is stored in the HD 14, and this flow ends. On the other hand, if the button 91j is not clicked, the process returns to S110.

(4) Summary:
As described above, the user of the red-eye correction device can easily correct the red-eye by specifying the position of the red-eye with the cross pointer and inputting the radius, tolerance, intensity, and the like. is there. And when the boundary part of the region for correcting the red eye is within the range of the red eye color, the image data is not completely replaced with the data representing the eye color, so the color changes smoothly, and after the replacement The image data is image data representing the brightness corresponding to the brightness information. In addition, the red-eye portion can be corrected to the eye color of another image in which no red-eye is generated. Therefore, it is possible to correct the red eye so as not to make the user feel uncomfortable, and the red eye correcting device is a highly convenient device.

Note that the red-eye correction device and the peripheral device that can execute the red-eye correction program of the present invention can have various configurations.
For example, the printer may be integrated with a computer or may be a dedicated product that prints only a single color image. The flow described above may be partially or entirely executed by a printer or a dedicated image output device in addition to being executed in the PC.
According to the present invention, it is possible to provide a red-eye correction device and a red-eye correction program useful for correcting red eyes. It can also be applied as a red-eye correction method.

The block diagram which shows schematic structure of the system which consists of a red-eye correction apparatus and a peripheral device. The figure which shows the block configuration of a printer with PC. The figure which shows typically the various means which comprise a red-eye correction apparatus. The figure which shows the example of a display of a setting input screen. The schematic diagram which shows the maximum value MaxDistance of distance. The figure explaining the replacement process of the image data in the boundary part of a correction area | region. The flowchart which shows a red eye correction process. The flowchart which shows the color determination process of eyes. The figure which shows a mode that the color of eyes is determined. 6 is a flowchart showing color replacement processing. The flowchart which shows a boundary color replacement process. The figure which shows typically the mode of the image after correction | amendment, when the range made into the color of a red eye exists in the inside and outside of a correction area | region.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Personal computer, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Hard disk, 17a-e ... Interface, 18a ... Display, 18b ... Keyboard, 18c ... Mouse, 20 ... Inkjet printer, 30 ... Digital camera, 50 ... correction area 51 ... center coordinates 52 ... pixels in the correction area 53 ... pixels in the boundary area 54 ... pixels outside the correction area 55 ... partition area 61 ... different image 62 ... eye including white eye Area 63 ... iris area U1 ... correction area acquisition means U2 red eye range acquisition means U3 brightness information acquisition means U4 color replacement means

Claims (11)

Obtain image data of a second image different from the first image of color expressed by image data having multiple gradations for each pixel, and based on the image data, iris regions from the second image Information indicating the color of the eye is acquired based on the image data of the area, and pixels in the correction area corresponding to the correction area information indicating the correction area correcting the red eye in the first image are the same. When the image data of the first image is within a range corresponding to range information representing a range of red-eye colors in the color space of the image data, the image data of the first image represents the same color. Color replacement means for replacing the image data corresponding to the information and setting the replacement amount of the image data in accordance with the degree to which the pixel is included in the correction area when the pixel is a boundary portion of the correction area It is characterized by comprising Red-eye correction device. Correction area acquisition means for determining an eye area based on image data of each pixel from a color first image expressed by image data having multiple gradations for each pixel and acquiring correction area information representing the area When,
Red-eye range acquisition means for acquiring range information representing a range of red-eye colors in the color space of the image data;
Acquiring image data of a second image different from the first image, determining an iris region from the second image based on the image data, and determining an eye color based on the image data of the region; And when the image data of the first image is within a range corresponding to the acquired range information for the pixel of the correction region corresponding to the acquired correction region information, When the image data of one image is replaced with image data corresponding to information representing the same color, and when the pixel is a boundary portion of the correction area, the replacement amount of the image data is the same correction area. A red-eye correction device, comprising color replacement means for adjusting the amount contained in the image .   The color replacement unit determines whether the person of the first image and the person of the second image are the same, and when it is determined that they are the same, the correction area corresponding to the correction area information 3. The red-eye correction device according to claim 1, wherein the image data of the first image is replaced with image data corresponding to information representing the same color for the pixels. The correction area is a substantially circular area,
The correction area information, claims 1, characterized in that it is composed of information indicating the size of the correction area having the above generally circular, and the information representing the center coordinates of the corrected area in the image The red-eye correction device according to any one of 3 . The range information is information in which a range of red-eye color in the color space of the image data is expressed as a distance from a predetermined red-eye target color,
The color replacement means calculates a distance between the red-eye target color and the pixel color from the coordinates of the red-eye target color in the color space and the image data of the pixel in the correction area, and the distance is acquired. 5. The red-eye correction device according to claim 1 , wherein the image data is replaced when the distance is within a distance corresponding to the range information. 6. The image data is multi-gradation data for each of red, green, and blue.
The color replacement means sets N as a positive integer, and coordinates values of the red eye target color in the order of red, green, and blue, C1r (0 ≦ C1r ≦ N), C1g (0 ≦ C1g ≦ N), C1b (0 ≦ C1b ≦ N), the image data of the above pixels in the order of red, green and blue, C2r (0 ≦ C2r ≦ N), C2g (0 ≦ C2g ≦ N), C2b (0 ≦ C2b ≦ N), Ravg = (C1r + C2r) / 2, the distance Distance between the coordinates of the predetermined red-eye target color and the image data of the same pixel is approximately Distance = [{2 + Ravg / (N + 1)} × (C1r−C2r) ² + 4 × (C1g−C2g) The red-eye correction device according to claim 5 , wherein the red-eye correction device is calculated by an arithmetic expression of ² + {2+ (N−Ravg) / (N + 1)} × (C1b−C2b) ² ] ^1/2 . In the color space of the image data, the color replacement means has a red coordinate value R (0 ≦ R ≦ N), a green coordinate value G (0 ≦ G ≦ N), and a blue coordinate value B ( When 0 ≦ B ≦ N) and the coordinates in the same color space are represented by (R, G, B), each coordinate (0, 0, 0), (0, 0, N), (0, N, 0) , (0, N, N), (N, 0, 0), (N, 0, N), (N, N, 0), (N, N, N) and the distance between the coordinates of the red eye target color the maximum value is calculated, the ratio of the distance distance with respect to the maximum value according to claim 6, characterized in that the replacement of the image data when a range corresponding to the range information that has been the acquisition Red eye correction device. Obtain image data of a second image different from the first image of color expressed by image data having multiple gradations for each pixel, and based on the image data, iris regions from the second image Information indicating the color of the eye is acquired based on the image data of the area, and pixels in the correction area corresponding to the correction area information indicating the correction area correcting the red eye in the first image are the same. When the image data of the first image is within a range corresponding to range information representing a range of red-eye colors in the color space of the image data, the image data of the first image represents the same color. It is replaced with image data corresponding to the information, and when the same pixel is a boundary portion of the correction area, the replacement amount of the image data is set to an amount corresponding to the degree that the pixel is included in the correction area. Red eye correction method. Obtain image data of a second image different from the first image of color expressed by image data having multiple gradations for each pixel, and based on the image data, an iris region from the second image Information indicating the color of the eye is acquired based on the image data of the area, and pixels in the correction area corresponding to the correction area information indicating the correction area correcting the red eye in the first image are the same. When the image data of the first image is within a range corresponding to range information representing a range of red-eye colors in the color space of the image data, the image data of the first image represents the same color. A color replacement function that replaces image data corresponding to information and sets the amount of replacement of the image data according to the degree to which the pixel is included in the correction area when the pixel is the boundary of the correction area Realized on a computer Red-eye fix, characterized in that.   A correction area acquisition step of determining an eye area based on image data of each pixel from a color first image expressed by image data having multiple gradations for each pixel and acquiring correction area information representing the area When,
  A red-eye range acquisition step of acquiring range information representing a range of red-eye colors in the color space of the image data;
  Acquiring image data of a second image different from the first image, determining an iris region from the second image based on the image data, and determining an eye color based on the image data of the region; When the image data of the first image is within a range corresponding to the acquired range information for the pixels of the correction region corresponding to the acquired correction region information, When the image data of one image is replaced with image data corresponding to information representing the same color, and when the pixel is a boundary portion of the correction area, the replacement amount of the image data is the same correction area. And a color replacement step for setting the amount according to the degree contained in the red-eye correction method.   A correction area acquisition function for determining an eye area based on image data of each pixel from a color first image expressed by image data having multiple gradations for each pixel and acquiring correction area information representing the area When,
  A red-eye range acquisition function for acquiring range information representing a range of red-eye colors in the color space of the image data;
  Acquiring image data of a second image different from the first image, determining an iris region from the second image based on the image data, and determining an eye color based on the image data of the region; When the image data of the first image is within a range corresponding to the acquired range information for the pixels of the correction region corresponding to the acquired correction region information, When the image data of one image is replaced with image data corresponding to information representing the same color, and when the pixel is a boundary portion of the correction area, the replacement amount of the image data is the same correction area. A red-eye correction program for causing a computer to realize a color replacement function for an amount corresponding to a degree included in the computer.

Images