JP2003050999A - Device and method for image processing and medium with recorded image processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a device and a method for image processing, which can perform proper processing by automatically deciding the kind of image data, and a medium where an image processing program is recorded. SOLUTION: The number of colors in use can be counted (step S104) by totaling a distribution of luminance of respective pixels selected by thinning out the image data (step S102), and consequently it is judged that an image is a natural image as the kind of the image data when the number of colors in use is large. According to the decision result, a contrast enlargement process (step S110), a chroma emphasis process (step S112), or an edge emphasis process (S114) can automatically be selected, which is suitable to the natural image, and color conversion by gradation pre-conversion (step S508) when the image is natural image or color conversion (step S506) by cache plus interpolation operation when not is performed even in a printing process to automatically select a color converting process with a small processing quantity.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus, an image processing method and a medium recording an image processing program, and more particularly to an image processing apparatus and an image processing method for executing a predetermined processing according to the type of image data. And a medium on which an image processing program is recorded.

[0002]

2. Description of the Related Art Conventionally, software for performing various effect processes on image data of natural images such as photographs and image data of non-natural images of draw type has been known. In such software, the image data is displayed on a display or the like, and an operator performs desired processing to form image data having a good appearance.

Here, among various kinds of effect processing, while there is one that converts a natural image into a more beautiful one,
There are some things that don't need to be modified like draw images.

[0004]

In the image processing apparatus composed of the above-mentioned conventional software, the operator must discriminate the kind of the image on the display and select various effect processing. There was a problem that I could not do it.

The present invention has been made in view of the above problems, and records an image processing apparatus, an image processing method, and an image processing program capable of automatically determining the type of image data and performing appropriate processing. The purpose is to provide the specified medium.

[0006]

In order to achieve the above object, the invention according to claim 1 decomposes an image into pixels in a dot matrix form, inputs image data representing information of each pixel, and outputs each pixel. The color number detecting means for detecting the number of used colors by regarding the information corresponding to the luminance as a color, and the image determination means for determining the type of the image based on the detected number of used colors are provided. .

The number of colors used varies depending on the type of image. For example, in the case of a natural image such as a photograph, even if the object to be photographed has the same blue color, a plurality of colors are used due to the shading, and considerable colors are used. On the other hand, when drawing data or a business graph, the number of colors is naturally limited because it is originally drawn by the operator. Therefore, the image type can be determined from the number of colors used. On the other hand, as a method of detecting the number of colors used in image data, first, there is a method of determining the actual color of each pixel in a matrix and totaling and detecting it in a histogram.

However, an accurate value is not always necessary, and a so-called full color can have a color number of 16.7 million colors, so that detecting the accurate color number itself can be troublesome.

Based on such a premise, in the invention according to claim 1 configured as described above, when the image is decomposed into dot matrix pixels and the image data representing the information of each pixel is input, The number detecting means regards the information corresponding to the luminance of each pixel as a color to detect the number of used colors, and the image determination means determines the type of the image based on the detected number of used colors.

The brightness corresponds to each color, and although a plurality of colors correspond to one brightness value, it does not happen that the brightness value is large and the number of colors is small.
It is unlikely in reality that it is composed of only colors with coincident brightness values. Therefore, it can be said that the brightness value may be used for determination if there is a rough tendency that the number of colors used is large or small. Of course, when the luminance values are replaced in this way, the value equivalent to the number of colors used is more accurate than the number of colors used, but it is called the number of colors used for the purpose of determining the type of image. To

Here, the invention according to claim 2 is
In the image processing apparatus according to claim 1, when the image data is represented by a plurality of component values corresponding to luminance, the color number detection means is configured to obtain the luminance by weighted integration of the same component values. is there.

Even if there is a merit of using brightness, color conversion must be performed if there is no brightness component in the parameter of the image data, and normally, a large amount of processing is required for color conversion. However, since some errors are allowed at the time of using the luminance, when the image data is represented by a plurality of component values corresponding to the luminance, a great deal of processing is required by weighted integration of the same component values. Luminance is required without need.

There are other methods for simplifying the detection of the number of colors used. For example, in a three-dimensional color space, it is considered that each group has one grid in each axis direction, and one group has one color. As a result, it is not necessary to collect data with a huge number of colors when each axis has 256 gradations.

The number of colors used in the entire image data does not necessarily have to be totaled for all pixels. For example, the invention according to claim 3 is claim 1 or claim 2.
In the image processing apparatus described in any one of the above 1, the color number detection means is configured to detect the number of colors of the pixels sampled from the image data.

Of course, although an error occurs due to thinning, it is not always necessary to know the exact number of colors used, as described above. Therefore, if the number of colors of pixels sampled from image data is detected, the number of target pixels can be detected. And the amount of processing is also reduced.

Further, the invention according to claim 4 is the image processing apparatus according to any one of claims 1 to 3, wherein the image determination means determines that the image is a natural image when the number of colors used is large. It is configured to do so.

Since a natural image is given as an image having a large number of used colors, the image determining means determines that the image is a natural image if the number of used colors is large.

When the image is a natural image, there is a contrast correction process as an appropriate image process. The invention according to claim 5 is the image processing apparatus according to claim 4, wherein when the image data is a natural image. The image processing means is configured to perform image processing for expanding the brightness distribution and not to expand the brightness distribution for a non-natural image.

For example, in a photograph, an image may have a narrow contrast depending on the photographing condition. For this reason, image processing may be performed. According to the invention of claim 5, it is determined that the image is a natural image when the number of colors of the image data detected by the color number detection unit is large.
In this case, the image processing means performs image processing for expanding the brightness distribution. Of course, the range of the distribution to be enlarged can be changed as appropriate, and it is not necessary to intentionally perform the enlargement processing if the image data has a sufficiently wide luminance distribution and a wide contrast. Further, in the case of a non-natural image such as a business graph, the width of the contrast is not required and the brightness distribution is not expanded.

Further, the invention according to claim 6 is the image processing apparatus according to claim 4 or claim 5, wherein when the image data is a natural image, image processing for enhancing saturation is performed. In addition, when the image is a non-natural image, the saturation is not emphasized.

Similarly, in a photograph, the color may become cloudy depending on the conditions of light rays at the time of photographing. Image processing may be performed for this purpose.
According to the invention, when the number of colors of the image data detected by the number-of-colors detecting unit is large, it is determined that the image is a natural image, and in this case, the image processing unit performs the image processing for enhancing the saturation. Of course, in the case of a non-natural image such as a business graph, there is no need to change the hue to make it vivid, and the saturation emphasis is not performed.

Further, the invention according to claim 7 is the image processing apparatus according to any one of claims 4 to 6, wherein when the image data is a natural image, image processing for edge enhancement is performed and When the image is a natural image, the image processing means is provided to prevent edge enhancement.

Also in this case, if a photograph is taken as an example, the image may have a blurred edge with a blunt edge depending on the shooting conditions. For this reason, image processing may be performed. According to the invention, when the number of colors of the image data detected by the number-of-colors detecting unit is large, it is determined that the image is a natural image, and in this case, the image processing unit performs image processing for edge enhancement. Of course, the degree of edge enhancement can be changed as appropriate. Various types of specific methods of edge enhancement processing can be adopted. For example, for each pixel forming the image data, a low frequency component is obtained based on the peripheral pixel distribution and the low frequency component is reduced. Therefore, the edge degree of each pixel may be corrected as a result.

On the other hand, the image-processed image data may be used in various ways other than being displayed on a display, for example, a printing process or the like. In such a case, it is necessary to convert to a color space of printing ink different from the color space of the original image data, and the invention according to claim 8 corresponds to the one involving such color conversion. The image processing device according to any one of claims 4 to 7, wherein conversion is performed while including a table in which gradation color data in the conversion destination color space is associated with grid points in the conversion source color space. Pre-gradation in which the original gradation color data is converted into the gradation color data corresponding to the grid points of the table, and then the corresponding gradation color data is read by referring to the table and color conversion is performed. The conversion means and the storage area having a high-speed readable storage area capable of performing color conversion into corresponding gradation color data by interpolating calculation between grid points of the table and storing information of this color conversion Color conversion by interpolation if not stored in And a cache-use interpolation color conversion means for performing color conversion using the pre-gradation conversion means when the image data is a natural image, and the interpolation color conversion means when the image data is not a natural image. The color conversion is performed using the conversion means.

When performing color conversion between different color spaces, a table is prepared in which grid points in the color space of the conversion source are associated with gradation data in the color space of the conversion destination. This can be changed by referring to the table and sequentially reading the corresponding data of predetermined grid points, but if the grid points corresponding to all the gradation values of the conversion source gradation data are provided, the table becomes too large. Therefore, the pre-gradation conversion unit reduces the size of the table by converting the conversion source gradation data into gradation data corresponding to the grid points of the table.
It should be noted that although the gradation data other than the grid points of the table can be changed by the interpolation calculation, when the number of colors is large, the gradation conversion executed by error diffusion or the like has a characteristic that the calculation amount is surely reduced.

However, it is premised that the error diffusion process must be performed on the previous pixel, and in the case of a non-natural image, since the number of colors is small, the result of one conversion can be used many times. Therefore, in such a case, cache-based interpolation color conversion means that repeats the process of storing the color conversion result in a storage area that can be read at high speed while also using the interpolation calculation and reading from the storage area when necessary Can be said to be faster.

As described above, the method of providing a plurality of correspondences and changing the correspondences according to the pixels does not need to be limited to a substantial device, and it can be easily understood that it also functions as that method. it can. Therefore, the invention according to claim 9 is an image processing method for decomposing an image into pixels in a dot matrix shape and performing predetermined image processing on image data representing information of each pixel. The number of used colors is detected by inputting information corresponding to the luminance of each pixel as a color, and the type of image is determined based on the detected number of used colors.

That is, there is no difference that the method is not limited to a substantial device and is effective as a method thereof.

By the way, such an image processing apparatus may exist alone or may be used in a state of being incorporated in a certain device. The idea of the invention is not limited to this, and various embodiments are possible. Is included. Therefore, it may be software or hardware,
It can be changed as appropriate.

When the software of the image processing apparatus is embodied as an example of embodying the idea of the invention, it must be said that it naturally exists on a recording medium recording such software and is used. As an example thereof, the invention according to claim 10 records an image processing program which decomposes an image into pixels in a dot matrix and inputs image data representing information of each pixel by a computer to perform predetermined image processing. In the medium, the step of inputting the image data and detecting the number of colors used by regarding the information corresponding to the luminance of each pixel as a color, and the type of the image based on the number of colors used are detected. And a determination step.

Needless to say, the recording medium may be a magnetic recording medium or a magneto-optical recording medium, and any recording medium to be developed in the future can be considered in exactly the same manner. In addition, the duplication stage of the primary duplication product, the secondary duplication product, and the like is absolutely the same. In addition, in the case of software, the method of supplying the software is not provided as the recording medium described above, but the present invention is used even if the software is provided using a communication line.

Further, even when a part is software and a part is realized by hardware, there is no difference in the idea of the invention, and it is necessary to store a part on a recording medium. It may be in such a form that it is read as appropriate. Furthermore, it goes without saying that the present invention is also applicable to an image processing apparatus incorporated in a color facsimile machine, a color copying machine, a color scanner, a digital camera, a digital video, or the like.

[0033]

As described above, according to the present invention, the type of image data can be automatically determined from the viewpoint of the number of colors used, and the number of reproducible colors can be obtained by replacing the number of colors used with luminance. It is possible to provide an image processing apparatus capable of easily totaling even when the number is large.

According to the second aspect of the present invention, the brightness can be calculated very easily by weighting and integrating the component values corresponding to the brightness.

Further, according to the invention of claim 3,
Since the target pixels for detecting the number of colors are thinned out and selected,
The throughput can be reduced.

Further, according to the invention of claim 4,
The natural image can be easily determined based on the number of colors used.

Further, according to the invention of claim 5,
When it is determined that the image type is a natural image, the contrast enlargement processing is automatically performed to obtain the image data having the optimum contrast.

Further, according to the invention of claim 6,
When it is determined that the image type is a natural image, the saturation emphasis processing is automatically performed, and it is possible to obtain colorful image data.

Further, according to the invention of claim 7,
When it is determined that the image type is a natural image, edge enhancement processing is automatically performed, and image data with no round edges can be obtained.

Further, according to the invention of claim 8,
In the case of natural images with many colors used, color conversion can be performed with a minimum amount of calculation using a method such as error diffusion.
When the number of colors used is small, the conversion result can be repeatedly used by using the cache, so that the minimum processing amount can be obtained by the color conversion method according to each image type.

Further, according to the invention of claim 9,
It is possible to provide an image processing method capable of automatically and easily determining the type of image data from the viewpoint of the number of colors used replaced by luminance, and according to the invention of claim 10, the image processing method is also provided. A medium in which an image processing program capable of automatically and easily determining the type of data is recorded can be provided.

[0042]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing a specific hardware configuration example of an image processing apparatus according to an embodiment of the present invention.

In the figure, a scanner 11 and a digital still camera 12 are provided as various image input devices 10, and a computer main body 21 and a hard disk 22 are provided as image processing devices 20 that play a central role in image processing including image determination. The printer 31 and the display 3 are provided as the image output device 30 for displaying the image-processed image.
Equipped with 2.

The processing performed inside the computer main body 21 is shown in FIG. As shown in the figure, in the computer main body 21, an operating system 21a
Is running, and the printer driver 21b and the video driver 21c corresponding to the printer 31 and the display 32.
Is built in. On the other hand, the application 21d is controlled by the operating system 21a to execute processing, and executes predetermined image processing in cooperation with the printer driver 21b and the video driver 21c as necessary. The computer 21 executes each program stored in the internal ROM or the hard disk 22 while using the RAM or the like. Programs for such image processing are supplied via various recording media such as a CD-ROM, a floppy (registered trademark) disk, and an MO, and also via a public communication line such as a modem to an external network. It has also been implemented by connecting to and downloading software and data.

In the present embodiment, the image input device 10
The scanner 11 or the digital still camera 12 as the image output device outputs RGB (green, blue, red) gradation data as image data, and the printer 31 as the image output device 30 outputs CMY ( cyan,
Magenta, yellow) or CMY with black added
The binary data of K is required as an input, and the display 32 requires the gradation data of RGB as an input. Therefore, the specific role of the computer main body 21 as the image processing device 20 is to input RGB gradation data to create RGB gradation data that has undergone necessary emphasis processing, and for the display 32, use a video driver. 21c is displayed, and the printer 31 is converted into CMY binary data and printed by the printer driver 21b.

In the image processing of this embodiment, when the color number detecting means 21d1 of the application 21d detects the number of used colors for the image data input into the computer main body 21, the image determining means 21d2 determines the type of image. The image processing means 21d3 automatically performs appropriate image processing preset according to the type of image. Also,
The image data subjected to the image processing is displayed on the display 32 via the video driver 21c, and after confirmation, converted into print data by the printer driver 21b and printed by the printer 31.

In this embodiment, as the image processing means 21d3 set according to the type of image,
As shown in FIG. 3, contrast enlargement processing, saturation emphasis processing, and edge emphasis processing are prepared. In the printer driver 21b for converting image data into print data, as shown in FIG. A rasterizer 21b1 for rasterizing data, a color conversion unit 21b2 for color conversion by a combination of pre-gradation conversion or cache and interpolation calculation, and a gradation conversion unit 21b3 for binarizing the gradation data after color conversion are prepared. There is.

In the present embodiment, a computer system is incorporated between image input / output devices to perform image processing. However, such a computer system is not necessarily required and is used for image data. Any system that detects the number of colors and determines the type of image may be used. For example, as shown in FIG. 5, in a printer 31b that inputs and prints image data without using a computer system, a scanner 11b and a modem 13b are provided.
It is also possible to configure so that the number of colors used is automatically detected and the type of image is determined for image data input via the above.

FIG. 6 shows a flow chart corresponding to the image processing in the application. Step S1
02 and step S104, the luminance distribution is totaled to detect the number of colors used.

First, the brightness distribution detecting process will be described.

Before explaining how to represent the luminance, the pixels to be distributed will be described. As shown in step S102 of FIG. 6, thinning-out processing for thinning out target pixels is executed. As shown in FIG. 7, a bitmap image is formed as a two-dimensional dot matrix consisting of predetermined dots in the vertical direction and predetermined dots in the horizontal direction. It is necessary to check the brightness of. However, this distribution detection processing is intended to indirectly obtain the used color from the luminance and does not necessarily have to be accurate. Therefore, it is possible to perform thinning to the extent that it falls within a certain error range. According to the statistical error, the error with respect to the sample number N can be expressed as approximately 1 / (N ** (1/2)). However, ** represents the power. Therefore, in order to perform processing with an error of about 1%, N = 10000.

Here, the bitmap screen shown in FIG. 7 has the number of pixels of (width) × (height), and the sampling period ratio is ratio = min (width, height) / A + 1 (1). Where min (width, heig
ht) is the smaller of width and height, and A is a constant. Further, the sampling period ratio referred to here represents how many pixels are sampled, and the pixels marked with a circle in FIG.
The case where tio = 2 is shown. That is, one pixel is sampled every two pixels in the vertical direction and the horizontal direction, and sampling is performed every other pixel. The number of sampling pixels in one line when A = 200 is as shown in FIG.

As can be seen from the figure, when the width is 200 pixels or more, the number of samples is 100 pixels or more at the minimum, except for the case where the sampling period ratio = 1 which is not sampled. Therefore, when the number of pixels is 200 or more in the vertical and horizontal directions, (100 pixels) × (100 pixels) = (10000 pixels)
Is ensured and the error can be reduced to 1% or less.

Here, min (width, hei
ght) is used as a reference for the following reason.
For example, assuming that width >> height, as in the bitmap image shown in FIG. 10A, when the sampling period ratio is determined by the longer width, as shown in FIG. In addition, it may happen that pixels are extracted only in the upper and lower lines in the vertical direction. However, min (wi
If the sampling period ratio is determined based on the smaller one as dth, height), it is possible to perform thinning including the intermediate portion in the smaller vertical direction as shown in FIG. Become.

In this example, pixels in the vertical and horizontal directions are thinned out at an accurate sampling cycle. This is suitable for processing while sequentially thinning out pixels that are input. However, when all the pixels are input, the coordinates may be randomly specified in the vertical direction and the horizontal direction to select the pixels.
In this way, when the minimum required number of pixels such as 10000 pixels is determined, the process of randomly extracting until 10000 pixels is repeated 10000 pixels.
It suffices if the extraction is stopped when the number of pixels is reached.

If the pixel data of the pixels selected in this way has luminance as its component element, the distribution can be obtained using the luminance value. On the other hand, even in the case of image data whose luminance value is not a direct component value, it indirectly has a component value representing luminance. Therefore, the brightness value can be obtained by converting from the color space in which the brightness value is not the direct component value to the color space in which the brightness value is the direct component value.

Such color conversion between different color spaces is not uniquely determined by a conversion formula, but a correspondence relationship is obtained for color spaces having respective component values as coordinates and the correspondence is obtained. It is necessary to refer to the color conversion table that stores the relationship and perform sequential conversion. For the purpose of forming a table, the component values are represented as gradation values, and in the case of 256 gradations having a three-dimensional coordinate axis, about 16.7 million (2
It must have a color conversion table of 56 × 256 × 256) elements. As a result of considering efficient use of storage resources, instead of preparing correspondences for all coordinate values, we usually prepare correspondences for appropriate discrete grid points and use interpolation calculations together. I am trying to do it. Since this interpolation calculation is possible through some multiplications and additions, the amount of calculation processing becomes enormous.

That is, if a full-size color conversion table is used, the processing amount will be small, but the table size will be unrealistic, and if the table size is a realistic size, the calculation processing amount will be unrealistic. Often becomes.

In view of such a situation, in this embodiment, the conversion formula of the following formula for obtaining the luminance from the three primary colors of RGB is adopted, as is used in the case of television or the like. That is, the luminance yp at the point P is R
From the GB component values (Rp, Gp, Bp), yp = 0.30Rp + 0.59Gp + 0.11Bp (2) By doing so, it becomes possible to obtain the luminance value only by multiplying three times and adding twice.

In the present embodiment, as a result of targeting the RGB color space, such a conversion formula is adopted. However, since each component value shows the brightness of the color in the background, When each component value is viewed alone, it has the property of linearly corresponding to the brightness. Therefore, roughly speaking, it is not impossible to simplify it simply as yp = (Rp + Gp + Bp) / 3 (3) without considering each addition ratio.

When the luminances are totaled by the thinning-out process in this way, the distribution thereof is as shown by the solid line in FIG. Therefore, the number of colors used can be detected by counting the number of brightness values in which the number of pixels is not "0" in step S104. In addition, in step S102, the saturation distribution and the saturation distribution are totaled, which will be described later.

When the number of colors used is detected in this way, the number of colors used is compared with a predetermined threshold value in step S106. If the number of colors used is larger, it is determined that the image data is a natural image. To do. As the threshold value, for example, “5
It is sufficient to set the "0" color. As an example of image data other than a natural image, there is an example in which a business graph or a draw image is read by the scanner 11, or a computer graphic image is read by the scanner 11 or input from a network via a modem 13b. There are cases like this.

If it is a natural image, a flag as a natural image is set in step S108. The flag is set so that the determination result is transmitted to the printer driver 21b other than the image processing of the application 21d. In the present embodiment, only one threshold value is prepared for the time being and it is determined whether or not it is a natural image. However, it is possible to make a more detailed determination within the range of the number of colors used. Is also good. For example, even in the case of computer graphics, the number of colors may increase to some extent due to gradation and the like, and although the original number of colors is not so large, the number of colors is reduced when the scanner 11 reads the edge portion. May increase. Therefore, such a kind may be classified into a natural image and a non-natural image, and as will be described later, setting may be performed such that only edge enhancement processing is performed without performing image processing for natural images.

For natural images, the contrast is expanded in step S110, the saturation is emphasized in step S112, and the edge emphasis is executed in step S114.

In this embodiment, the luminance distribution is as shown in FIG.
As shown by the solid line, when the concentration is concentrated in part within the range of the original reproducible luminance distribution, it means a process of sufficiently expanding this within the reproducible range.

The range of reproducible luminance is "0" to "25".
5 ”, in the luminance conversion, the luminance Y of the conversion destination is calculated from the luminance y before the conversion and the maximum value ymax and the minimum value ymin of the luminance distribution range based on the following equation.

Y = ay + b (4) where a = 255 / (ymax-ymin) (5) b = -a.ymin or 255-a.ymax (6) Further, in the above conversion formula, Y <0. If so, Y = 0 and Y> 2
If 55, then Y = 255. Here, it can be said that a is an inclination and b is an offset. According to this conversion formula, the luminance distribution having a certain narrow width can be expanded to a reproducible range.

When the luminance distribution is expanded, as shown in FIG.
The flowchart shown in FIG.
Find both ends of the luminance distribution with. The brightness distribution in a natural image appears in a mountain shape. Of course, there are various positions and shapes. The width of the luminance distribution is determined depending on where to determine the both ends, but it is not possible to set the points where the skirt extends and the number of distributions becomes “0” as the both ends, and it is smaller on the side with the highest luminance in the distribution range. The portions that are inward from the side by a certain distribution ratio are defined as the ends of the distribution. In the present embodiment, this distribution ratio is set to 0.5%.
In this way, by cutting the upper and lower ends by a certain distribution ratio, it is possible to ignore white points and black points caused by noise and the like.

In the actual processing, 0.5 with respect to the number of pixels to be processed (the total number of pixels selected in the thinning processing)
% Is calculated, and the number of distributions is accumulated in order from the luminance value at the upper end and the luminance value at the lower end in the reproducible luminance distribution in order, and the luminance value with a value of 0.5% is obtained. The upper end side is ymax, and the lower end side is ymin.
Becomes

In the present embodiment, the upper end and the lower end are obtained through such a process for the luminance distribution, but it is also possible to obtain the both ends under statistical processing. For example, it is also possible to adopt a method in which the percentage of the average value of the brightness values is less than or equal to the end.

By the way, the possible range of the brightness y is "0".
Since it can only be "255", it is efficient to obtain the converted luminance Y in advance corresponding to all possible values of the luminance y, and this correspondence relationship is calculated in step S204. And store it as a table.

Thereafter, step S204 is performed for each pixel.
The brightness calculated is increased by referring to the table calculated in. By the way, up to this point, the correspondence relationship for converting the luminance has been obtained, and, for example, the correspondence relationship for the component values (Rp, Gp, Bp) on the RGB coordinate axes has not been obtained. However, the conversion equation of the equation (4) can also be applied in correspondence with the RGB component values (Rp, Gp, Bp). That is, the component values (R, G, B) before conversion
On the other hand, the converted component values (R ′, G ′, B ′) are R ′ = a · R + b (7) G ′ = a · G + b (8) B ′ = a · B + b (9) Can be asked as This is clear from the fact that both equations (4) and (3) show a linear correspondence relationship. In addition, the luminance y and Y have gradations of “0” to “25”.
5 ”corresponding to the RGB component values (R, G,
B) and (R ′, G ′, B ′) are also in the same range, and it can be said that the conversion table for the brightness y and Y described above can be used as it is.

Therefore, in step S206, the conversion table corresponding to the equations (7) to (9) is referred to for the image data (R, G, B) of all pixels, and the image data (R ', G',
B '). Then, in step S208, the converted pixels are sequentially moved as shown in FIG.
The process is repeated until it is judged as the last pixel in 10.

Returning to the flowchart shown in FIG. 6, after the contrast is enlarged, the saturation is enhanced in step S112. This saturation enhancement processing is shown in FIG.

Also in this saturation enhancement processing, the saturation distribution in the image data is obtained in advance, and the saturation enhancement coefficient S is obtained from the distribution. In this case, similarly to the case of the luminance distribution, it is not necessary to collect the saturations for all the pixels, and the saturations are calculated for the pixels thinned out in step S102, and the saturations are calculated. If the image data has saturation as a component element, it is possible to obtain the distribution using the saturation value, and even in the case of image data where saturation is not a direct component element, Specifically, it has a component value representing the saturation. Therefore, the saturation value can be obtained by converting from the color space in which the saturation is not a direct component element to the color space in which the saturation value is a direct component value. For example, in the Luv space as the standard color system, the L axis represents luminance (brightness), and the U axis and V axis represent hue. Here, in the U-axis and the V-axis, the distance from the intersection of both axes represents the saturation, so that (U +
V) ** (1/2) is the saturation. However, the amount of calculation processing required for such conversion becomes enormous.

Therefore, in the present embodiment, the standard RGB gradation data is directly used as the image data and the saturation alternative value X is obtained as follows.

X = | G + B-2 × R | (10) Originally, the saturation is “0” when R = G = B,
The maximum value is obtained when mixing RGB single colors or a predetermined ratio of any two colors. From this property, it is possible to directly represent the saturation appropriately, but even with a simple formula (10), the saturation of the maximum value can be obtained for a single color of red and cyan that is a mixed color of green and blue. "0" when the components are uniform
Becomes In addition, the monochromatic colors of green and blue have reached about half of the maximum value.

In a situation where each component independently represents each color component, such as in the RGB color space, in a situation where the component values of the hue components are roughly equal, X '= | R + B-2 × G | (11) X ″ = | G + R−2 × B | (12), but the result is (10).
The one that followed the formula was the best.

When the saturation distribution of the pixels thinned out in step S102 is calculated based on the equation (10) from the RGB image data, the saturation is the minimum value "0" to the maximum value "511".
The distribution is in the range of, and the distribution is roughly as shown in FIG.

Based on the calculated saturation distribution, step S
At 302, a saturation enhancement index for this image is determined. Assuming that the aggregated saturation distribution is as shown in FIG. 15, in the present embodiment, the range occupied by the upper “16%” as the distribution number in the range of the effective pixel number is obtained. And the lowest saturation "A" within this range
Determines the saturation emphasis index S based on the following expression as representing the saturation of this image.

That is, if A <92, S = −A × (10/92) +50 (13) If 92 ≦ A <184, S = −A × (10/46) +60 (14) 184 ≦ A <230 If S = −A × (10/23) +100 (15) 230 ≦ A, then S = 0 (16). FIG. 16 shows the relationship between the saturation “A” and the saturation emphasis index S. As shown in the figure, the saturation emphasis index S is large when the saturation “A” is small in the range of the maximum value “50” to the minimum value “0”, and is small when the saturation “A” is large. Will gradually change.

In this embodiment, the saturation occupied by a certain proportion in the upper range of the aggregated saturation distribution is used. However, the present invention is not limited to this. For example, an average value is calculated or a median is calculated. It may be the basis for calculating the saturation emphasis index S. However, when a certain ratio in the upper part of the saturation distribution is taken, the effect of a sudden error is weakened, so that a good result can be obtained as a whole.

When the saturation emphasis index S is obtained, the saturation emphasis processing is performed on the image data of each pixel. When the saturation is emphasized based on the saturation emphasis index S, if the image data has a saturation parameter as described above, the parameter may be converted, but this time, R
The color space of GB is adopted. Therefore, the following is RG
A method of using the gradation data of B as it is to enhance the saturation will be described.

When each component is a component value of a hue component having an approximately equal relationship as in the RGB color space, R = G
= B, it is gray and has no saturation. Therefore, R
Assuming that the component having the minimum value in each component of GB merely reduces the saturation without affecting the hue of each pixel, the minimum value in each component is subtracted from all component values. It can be said that the saturation can be emphasized by expanding the difference value.

First, the saturation emphasis parameter Sratio advantageous for the calculation is obtained from the above-described saturation emphasis index S as Sratio = (S + 100) / 100 (17). In this case, when the saturation emphasis index S = 0, the saturation emphasis parameter Sratio = 1 and the saturation is not emphasized. Next, each component of RGB gradation data (R, G, B)
If the component value of blue (B) in is the minimum value,
The saturation enhancement parameter Sratio is used for conversion as follows.

R ′ = B + (R−B) × Sratio (18) G ′ = B + (G−B) × Sratio (19) B ′ = B (20) In this way, at least the RGB table is obtained. Color space and Luv
Color conversion with the space is not necessary, but in this case, emphasizing the saturation tends to improve the luminance and brighten the entire image. Therefore, the conversion is performed on the difference value obtained by subtracting the corresponding luminance value from each component value.

For the brightness, the conversion formula directly obtained from RGB as described above is used.

On the other hand, the saturation enhancement is R ′ = R + ΔR (21) G ′ = G + ΔG (22) B ′ = B + ΔB (23) The added / subtracted values ΔR, ΔG, and ΔB are obtained by the following equation based on the difference value with the brightness. That is, ΔR = (R−Y) × Sratio (24) ΔG = (G−Y) × Sratio (25) ΔB = (B−Y) × Sratio (26) It can be converted as' = R + (RY) * Sratio (27) G '= G + (GY) * Sratio (28) B' = B + (BY) * Sratio (29). It should be noted that the preservation of brightness is clear from the following equation.

Y ′ = Y + ΔY (30) ΔY = 0.30 ΔR + 0.59 ΔG + 0.11 ΔB = Sratio {(0.30R + 0.59G + 0.11B) -Y} = 0 (31) When the input is gray (R = G = B), the luminance Y
= R = G = B, the adjustment value ΔR = ΔG = ΔB = 0
Therefore, there is no achromatic color. Expression (27)
If the expression (29) is used, the brightness is preserved, and even if the saturation is emphasized, the brightness is not increased as a whole.

After the image data is converted in step S304, the converted pixel is moved as shown in FIG. 13 in step S306, and the process is repeated until the final pixel is determined in step S308.

After the saturation emphasis is completed, the edge emphasis processing is executed in step S114 of the flowchart shown in FIG. This edge enhancement processing is shown in FIG.

In the edge enhancement processing, the number of pixels in the horizontal direction (width) in the input image is multiplied by the number of pixels in the vertical direction (height) to obtain the number of pixels in step S402, and the same number is detected in step S404. The edge emphasis degree is determined according to the number of pixels. Since the edge emphasis degree largely depends on the edge emphasis method, the edge emphasis method in the present embodiment will be described first. In this embodiment, the unsharp mask 40 shown in FIG. 18 is used. This unsharp mask 40 has "100" at the center.
Value of the pixel of interest Pi in the image data in a matrix
It is used to perform the weighting of j and to perform the weighting on the peripheral pixels as the weighting corresponding to the numerical value in the square of the same mask. If the unsharp mask 40 is used, the weighting is performed based on the equation (32).

[0094]

[Equation 1]

In the equation (32), “632” is the total value of the weighting coefficients, Mij is the weighting coefficient described in the square of the unsharp mask, and Pij is the image data of each pixel. Note that ij indicates the coordinate values in the vertical and horizontal rows.

When the image data after the edge enhancement is Qij, the edge enhancement calculation is performed based on the equation (33).

Qij = Pij + C × {Pij−P′ij} (33) The meaning of the expression (33) is as follows. P'i
Since j is obtained by lowering the weighting of the peripheral pixels with respect to the pixel of interest and adding them, it is so-called “blunt (unsharp)” image data. What is blunted in this way has the same meaning as what is called a low-pass filter. Therefore, "Pij-
“P′ij” has the same meaning as that obtained by subtracting the low-frequency component from all the original components and applying the high-pass filter. Then, the high-frequency component that has passed through the high-pass filter is multiplied by the edge emphasis coefficient C to obtain “Pi
In addition to j ”, the high frequency component is increased in proportion to the edge emphasis coefficient, and the edge is emphasized.

Also in this sense, the edge emphasis degree can be changed by the edge emphasis coefficient C. Therefore, if the number of pixels is large, the edge emphasis coefficient C is increased, and if the number of pixels is small, the edge emphasis coefficient C is decreased. Erat when the width and height of the image are width × height
Let io be represented by (34).

Eratio = min (width, height) / 640 + 1 (34) Then, the edge emphasis coefficient C of the obtained Eratio is determined as follows.

If Eratio <1, C = 1 if 1 ≦ Eratio <3 C = 2 If 3 ≦ Eratio, C = 3 That is, if the shorter pixel is less than 640 pixels, the edge enhancement coefficient C is “1”, 640 pixels. If the number is less than 1920 pixels, the edge enhancement coefficient C is "2", and if the number is 1920 pixels or more, the edge enhancement coefficient C is "3". In the present embodiment, the edge enhancement coefficient C is set in this way, but the edge enhancement coefficient may be proportionally changed because the size of the image changes depending on the dot density.

Since the edge emphasis degree varies depending on the size of the unsharp mask, a large size unsharp mask may be used if the number of pixels is large, and a small size unsharp mask may be used if the number of pixels is small. You can use a mask. Needless to say, both the edge emphasis coefficient C and the unsharp mask 40 may be changed, or the edge emphasis degree may be changed by only one of them. Further, as is clear from the figure, the unsharp mask 40 has the highest weighting in the central portion, and the weighting value gradually decreases toward the periphery. This degree of change is not necessarily fixed, but can be changed as appropriate.

By the way, in the “7 × 7” unsharp mask 40 shown in FIG. 18, the weight of the outermost square is “0” or “1”, and the multiplication of the weight is meaningless for “0”. However, the weighting of "1" has very little weight as compared with "632" which is the total sum of the squares. Therefore, in the present embodiment, “7 ×
Instead of the “7” unsharp mask 40, a “5 × 5” unsharp mask 41 shown in FIG. 19 is used. In the unsharp mask 41 shown in the figure, the outermost circumference of the "7 × 7" unsharp mask 40 is omitted, and the weighting is the same in the inner "5 × 5" mask portion. As a result, the specific processing amount is halved.

Further, in this embodiment, the amount of calculation is reduced as follows. When RGB gradation data is targeted, each component value corresponds to the luminance (brightness) of each color component. Therefore, originally, the calculation of the equation (33) must be individually performed for each RGB gradation data. However, if multiplication and addition are repeated by the number of squares of the unsharp mask 40, it can be said that the amount of calculation is large in such individual calculation for each component.

On the other hand, it can be said that the edge enhancement can be carried out by maintaining the hue and changing the luminance.
Therefore, it can be said that the amount of processing is reduced by calculating the brightness instead of calculating the RGB component values. If the conversion formula of the brightness Y is used, the formulas (32) and (33) can be rewritten as the formulas (35) and (36).

[0105]

[Equation 2]

Y ″ ij = Yij + C × {Yij−Y′ij} (36) Further, if Yij−Y′ij is replaced by the equation (37), delta = {Yij−Y′ij} × C. (37) The converted R'G'B 'can be calculated as in the expression (38).

R ′ = R + delta G ′ = G + delta B ′ = B + delta ... (38) In this way, the multiplication and addition are 1/3, so that the overall processing time can be reduced by about 50 to 70%. Becomes In addition, the conversion result has no enhancement of color noise and the image quality is improved.

The edge enhancement processing is performed by the unsharp mask 40 for each pixel in the matrix image data.
Image data (R'G'B ') after edge enhancement using
Corresponds to the process of calculating Steps S406 to S412 represent a loop process in which the edge enhancement process is repeated for each pixel. In step S410 in the loop process, the target pixel is sequentially moved in the horizontal direction and the vertical direction as shown in FIG. The process is repeated until it is determined as the last pixel.

However, the calculation of the equation (32) is performed by using the unsharp mask 40 adopted for the pixels around the target pixel.
The multiplication and the addition are required by the number of squares, and the processing amount becomes large. On the other hand, considering the situation where edge enhancement is required, this is the so-called edge portion of the image, so it is limited to the location where the image data greatly differs between adjacent pixels. From such a situation, it can be said that calculation is sufficient when the difference in image data between adjacent pixels is large.

To embody this, step S406
Then, compare the image data between adjacent pixels,
Only when the difference is large, the calculation of the unsharp mask in step S408 is performed. By doing so, it is not necessary to perform the calculation of the unsharp mask on the image data portion which is not the edge portion, and the processing is drastically reduced.

Further, as shown in FIG. 20, originally there are eight pixels around the target pixel corresponding to the target pixel, so eight comparisons are required. However, for example, when comparing the pixel of interest in the center of the figure with the pixel of the grid of “5”, when the pixel of interest was the grid of the same “5” before that, the pixel of the grid of “1” was detected. It can be seen that the comparison is made once. Therefore, if it suffices to compare at least adjacent pixels only once, it is a combination of "1" and "5", "2" and "6", which are mutually opposite directions. Only one of "3" and "7" or "4" and "8" is sufficient, and comparison is made in the four directions of the combination.

As described above, for a natural image with a large number of colors used, the contrast is automatically expanded in the optimum range, and saturation enhancement and edge enhancement are automatically performed at the optimum enhancement level for the image. Done. Of course, if they are not natural images, these are skipped as unnecessary.

Up to now, the type of image data has been determined from the number of colors used in the image processing in the application 21d to perform the optimum image processing. However, the same applies to the determined type of image in the print processing as well. The optimal process is selected.

FIG. 21 shows a flowchart corresponding to the print processing. After the raster data is generated in step S502, the type of image data is determined based on the flag described above in step S504, and either step S506 or step S508 of the color conversion processing prepared for two types is executed. . After that, step S
Binarization is performed at 510, and print data is output at step S512.

What is executed in step S506 is a color conversion process in which the interpolation calculation process and the cache process are combined, and the procedure is shown in FIG. In the interpolation calculation shown in the figure, in addition to the eight-point interpolation calculation for substantially performing the calculation processing, the caching for color conversion is also performed without performing the substantial calculation processing.

FIG. 23 shows the principle of the eight-point interpolation calculation. Assuming a cube consisting of eight lattice points surrounding the coordinate P having RGB gradation data as a component value in the color space of the conversion source, the conversion value at the k-th vertex of the cube is Dk and the cube is Let V be the volume of
The conversion value Px at the inner point P of the cube can be interpolated by the following formula from the weighting by the ratio of the volumes Vk of the eight small rectangular parallelepipeds divided at the point P as shown.

[0117]

[Equation 3]

Therefore, eight grid points surrounding the coordinates are specified, and the calculation is executed for each of the CMY gradation data at each grid point.

By the way, referring to the flow chart shown in FIG. 22, the eight-point interpolation is not necessarily executed in the interpolation calculation processing routine, but the eight-point interpolation is referred to by referring to the cache table as shown in FIG. Caching is performed to omit the calculation. This cache table is a table of a fixed capacity for storing the CMY gradation data obtained when the 8-point interpolation calculation is executed using the conversion source RGB gradation data as the component value. Initially, this table is blank, but step S
C obtained immediately after executing the eight-point interpolation calculation in 606
The MY gradation data is additionally updated in step S608, and when the "cache + interpolation calculation" processing routine is executed in step S506 shown in FIG. 21, the conversion source data of the conversion source is first calculated in step S602. RGB
The cache table is searched using the gradation data of as the component value and a cache hit is found (it was found by the search)
In this case, the stored C in step S612.
The MY gradation data is referred to.

In the color conversion processing, the RGB gradation data is CMed for each pixel of the rasterized dot matrix.
In order to convert to Y gradation data, step S610
Repeat until the final pixel is reached.

Although such an interpolation calculation requires a large amount of calculation, the number of colors used is small when the image is not a natural image, so that the result of one calculation can be used many times. Therefore, when it is determined that the type of image data is not a natural image, this "cache + interpolation calculation" process is extremely effective.

Next, the pre-gradation conversion of step S508 which is the other color conversion processing will be described.

The flowchart of FIG. 25 and the diagram showing the error distribution of pixels in FIG. 26 are for explaining the outline of the pre-gradation conversion. The above-mentioned basic equation of eight-point interpolation requires multiplication eight times and addition seven times, so that it is a heavy resource and time burden whether it is implemented by hardware or software. Therefore, in order to perform color conversion more easily, Japanese Patent Laid-Open No. 7-30772 of the present applicant discloses a technique of gradation conversion instead of interpolation calculation.

The pre-gradation conversion disclosed in the publication is to convert the gradation data of a pixel so that it coincides with the grid coordinates by using a technique such as so-called error diffusion. The nearest grid coordinate is searched for (S702), and the error (dg) from the grid coordinate is calculated (S702).
704), the error (dg) is distributed to neighboring pixels (S).
706) only. Therefore, the burden of calculation can be extremely simplified as compared with the case of repeating multiplication and addition. The reason why the accuracy can be maintained without performing the interpolation calculation is described in detail in the publication, and will not be described in detail here. Since the gradation conversion for binarization is also performed after the color conversion, the gradation conversion performed first is called pre-gradation conversion.

Even in this pre-gradation conversion, since gradation conversion is performed for each pixel of the rasterized dot matrix, the process is repeated until the final pixel is reached in step S708. Then, in the subsequent step S710, the gradation converted RG
The color conversion table is referred to by the gradation data of B, but at this time, since it is always a grid point, there is no need to perform interpolation calculation, and the reading process is extremely easy.

When the number of colors to be used is extremely large like a natural image, the probability of hitting in the above-mentioned "cache + interpolation calculation" is low, so the number of interpolation calculations increases. However, in such pre-gradation conversion, although processing such as error diffusion must be executed for all pixels, one processing is simple, so
Overall throughput is low. Therefore, the number of colors used is large,
For image data determined to be a natural image, it is possible to reduce the entire processing amount by selecting the color conversion processing by such pre-gradation conversion.

In the present embodiment, the color conversion process of "cache + interpolation calculation" is adopted for the non-natural image having a small number of used colors, and the color conversion process by the pre-gradation conversion is made for the natural image having a large number of used colors. However, the present invention is not limited to such a combination, and other combinations can be adopted. That is, the most appropriate color conversion process may be freely set according to the type of image and automatically used.

In this way, the number of colors used can be counted by totaling the luminance distributions for each pixel selected by the thinning process for the image data (step S102) (step S10).
4) As a result, if the number of colors used is large, it can be determined that the type of image data is a natural image, and based on such a determination result, a suitable contrast is applied to the natural image. Enlargement processing (step S110), saturation enhancement processing (step S112), edge enhancement processing (S1)
14) can be automatically selected, and in the printing process, if the image is a natural image, color conversion is performed by pre-gradation conversion (step S508). If the image is not a natural image, "cache + interpolation calculation" is performed. The color conversion is performed (step S506), and it is possible to automatically select a color conversion process with a small processing amount.

[Brief description of drawings]

FIG. 1 is a block diagram of a specific hardware configuration example of an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is a block diagram showing processing performed inside a computer.

FIG. 3 is a schematic block diagram showing a more detailed configuration of image processing means.

FIG. 4 is a schematic block diagram showing a more detailed configuration of a printer driver.

FIG. 5 is a schematic block diagram showing another application example of the image processing apparatus of the present invention.

FIG. 6 is a flowchart showing image processing of an application according to the present invention.

FIG. 7 is a diagram showing a conversion source image.

FIG. 8 is a diagram showing a sampling cycle.

FIG. 9 is a diagram showing the number of sampling pixels.

FIG. 10 is a diagram showing a relationship between a conversion source image and sampled pixels.

FIG. 11 is a diagram showing an aggregated luminance distribution and an enlarged luminance distribution.

FIG. 12 is a flowchart showing a contrast enlargement process prepared as image processing.

FIG. 13 is a diagram showing a moving direction of a target pixel.

FIG. 14 is a flowchart showing saturation enhancement processing prepared as image processing.

FIG. 15 is a schematic diagram of an aggregated state of saturation distribution.

16 is a diagram showing a relationship between saturation A and saturation emphasis index S. FIG.

FIG. 17 is a flowchart showing edge enhancement processing prepared as image processing.

FIG. 18 is a diagram showing an unsharp mask.

FIG. 19 is a diagram showing an improved version of the unsharp mask.

FIG. 20 is a diagram showing a comparison direction with adjacent pixels in image data.

FIG. 21 is a flowchart illustrating a procedure of print processing of a printer driver.

FIG. 22 is a flowchart of color conversion processing by cache + interpolation calculation.

FIG. 23 is a diagram showing the concept of eight-point interpolation calculation.

FIG. 24 is a diagram showing the contents of a cache table.

FIG. 25 is a flowchart of a pre-gradation conversion process.

FIG. 26 is a diagram showing a state of error diffusion of each pixel.

[Explanation of symbols]

10 ... Image input device 20 ... Image processing device 21a ... Operating system 21b ... printer driver 21b1 ... rasterizer 21b2 ... Color conversion unit 21b3 ... Gradation converter 21c ... Video driver 21d ... application 21d1 ... Color number detection means 21d2 ... Image judging means 21d3 ... Image processing means 30 ... Image output device

   ─────────────────────────────────────────────────── ─── Continued front page    F-term (reference) 5B057 AA11 BA02 CA01 CA08 CA12                       CA16 CB01 CB08 CB12 CB16                       CE11 CE17 CE18 DA12 DA17                       DB02 DB06 DB09 DC23 DC25                       DC36                 5C077 LL01 LL19 MP08 PP03 PP32                       PP34 PP37 PP51 PQ08 PQ12                 5C079 HB01 HB04 HB12 LA02 LA31                       LB01 MA11 NA03 NA05                 5L096 AA02 AA06 BA07 CA02 DA01                       FA37 FA54 GA28 GA41 JA11

Claims (10)

[Claims] 1. A color number detection in which an image is decomposed into pixels in a dot matrix form, image data representing information of each pixel is input, and information corresponding to the brightness of each pixel is regarded as a color to detect the number of colors used. An image processing apparatus comprising: a means; and an image determination means for determining an image type based on the detected number of used colors. 2. The image processing apparatus according to claim 1, wherein when the image data is represented by a plurality of component values corresponding to brightness, the color number detecting means calculates the weighted sum of the component values. An image processing apparatus characterized by obtaining brightness. 3. The image processing device according to claim 1 or 2, wherein the color number detection means is
An image processing device characterized by detecting the number of colors of pixels sampled from image data. 4. The image processing apparatus according to claim 1, wherein the image determination unit determines that the image is a natural image when the number of colors used is large. Processing equipment. 5. The image processing apparatus according to claim 4, wherein when the image data is a natural image, image processing is performed to expand the luminance distribution, and when the image data is a non-natural image, the brightness distribution is not enlarged. An image processing apparatus, comprising: 6. The image processing apparatus according to claim 4 or 5, wherein when the image data is a natural image, image processing for enhancing saturation is performed, and when the image data is a non-natural image. An image processing apparatus comprising an image processing means for preventing saturation from being emphasized. 7. The image processing apparatus according to any one of claims 4 to 6, wherein when the image data is a natural image, image processing for edge enhancement is performed, and when the image data is a non-natural image, edge enhancement is performed. An image processing apparatus comprising an image processing unit that prevents the image processing. 8. The image processing device according to any one of claims 4 to 7, wherein the grid points in the conversion source color space correspond to the gradation color data in the conversion destination color space. The gradation color data of the conversion source is converted into the gradation color data corresponding to the grid points of the table, and the corresponding gradation color data is read by referring to the table. Pre-gradation conversion means for performing color conversion and a storage area capable of performing color conversion into corresponding gradation color data by interpolating between the grid points of the above table and storing this color conversion information at high speed. When the image data is a natural image, the pre-gradation conversion means is used when the image data is a natural image. Color conversion, and the same image data An image processing apparatus, wherein color conversion is performed by using the interpolation color conversion means when the image is not a natural image. 9. An image processing method for decomposing an image into pixels in a dot matrix shape and performing predetermined image processing on image data representing information of each pixel, wherein the image data is input to each pixel. An image processing method, characterized in that information corresponding to brightness is regarded as a color, the number of colors used is detected, and the type of image is determined based on the detected number of colors used. 10. A medium in which an image processing program for decomposing an image into pixels in a dot matrix and inputting image data representing information of each pixel by a computer and performing predetermined image processing is recorded. The method includes the steps of inputting data and detecting the number of colors used by regarding the information corresponding to the luminance of each pixel as a color, and determining the type of image based on the number of colors used. A medium having an image processing program recorded therein.