JP2009038580A - Unit and method for processing image - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To perform correction processing appropriately to the copy of an image, where characters, graphs, photographs, and the like are mixed to an original. <P>SOLUTION: The image is read by a scanner (1). A character region is discriminated from a non-character region by image region separation processing (2). The read image is divided into block units (3). Extraction processing is executed only to a block, where the result of image region separation is the non-character region (4). Image correction is executed based on the extracted block (5). <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing method for extracting a specific portion and performing image processing based on the specific portion.

  The performance of personal computers over the last few years has made it easier and faster to handle even large files. More and more people are handling photographic-like natural images, which are generally considered to have a large capacity. In addition, input devices represented by digital cameras and scanners have become widespread, and various images have been digitized.

  There are various types of photographic images, from high-quality images taken by professionals to images with poor quality. The image with poor quality referred to here is an image that is overexposed or underexposed, an image in which an appropriate white balance cannot be performed, and a color cast with a tint on the entire image is generated. In general, the possible causes of bad images are due to inadequate light intensity during shooting, shooting conditions such as shooting under fluorescent light, and images generated during digitization such as noise and characteristics of digital cameras. Deterioration, etc. These poor quality images can be digitally processed and captured in a personal computer or the like, and then corrected to improve the image quality.

  Various proposals have been made for image correction. In general, in these correction processes, a correction amount determination unit that calculates a correction amount for performing correction, and correction is executed based on the obtained correction amount. It is divided into correction execution units.

  Among them, the correction amount determination unit can be roughly classified into two types according to the processing contents. A method of generating accumulated data of an image and determining a correction amount based on the data, and extracting a feature amount of a specific portion in the image and obtaining a correction amount from the specific portion.

  As a correction method using the former accumulated data, there are JP-A No. 2000-1362 and JP-A No. 2000-13616. In this process, color cast and level correction are performed on an image for which white balance setting is insufficient or exposure is not optimal. As the accumulation process for obtaining the correction amount, the luminance value for each pixel is accumulated to create a histogram, and based on this, the necessity of correction is determined and the correction amount is determined. Correction is executed by executing a luminance conversion process for correcting the generated luminance histogram as shown in FIG. 1A as shown in FIG. Appropriate gray balance is realized by calculating an average hue of luminance values corresponding to the HL and SD points in FIG. 1A, obtaining conversion coefficients so that they become achromatic colors, and applying them. .

  Further, contrast correction and saturation correction that make the image more suitable are also possible. From the acquired luminance histogram distribution, a luminance conversion amount such as an S-shaped curve is determined and contrast correction is performed, or a correction coefficient amount is calculated from the average saturation of the image, and the color difference component of the image is multiplied by the correction coefficient. Thus, each correction is performed.

  As a process for extracting the latter specific part, a detection process that is mainly a main part of an image such as human skin is generally used. Japanese Patent No. 3203946 is a correction of a video signal such as a television, but detects a skin color average luminance level from a color difference signal and a luminance signal, and adds a control signal to a gamma correction circuit in relation to the luminance level of all images. It is. This makes it possible to appropriately brighten a face that has become dark due to backlight or the like.

  Thus, it can be said that the probability of successful detection of a specific portion, that is, the detection rate is very important in image correction for extracting the feature amount of a specific portion in an image. If the detection rate is low, not only correction or processing is not applied, but an incorrect coefficient or location is set, which may deteriorate the image.

  By realizing such image correction and the like, high image quality is realized in various device devices. Here, paying attention to the device aspect, digital cameras, input devices represented by scanners, output devices such as printers, monitors, and the like, have made dramatic developments. On the other hand, in recent years, multifunction peripherals in which a printer function and a scanner function are integrated have been spreading. In the multi function device, in addition to a single function print function and a scanner function, a so-called copier function for immediately outputting an image read by a scanner with a printer is realized.

The copying machine itself has a long history, starting with monochrome copying, and recently color copying has become common. From the viewpoint of image processing, various high image quality and high processing speed have been achieved. One of the typical processes is image quality improvement by image area separation. When considering the situation where copying is used, it is important to output text documents such as characters and graphs. Image processing using image area separation has been performed in various forms for the purpose of outputting clearer and higher quality characters and graphs. As image area separation, methods such as those disclosed in Japanese Patent Application Laid-Open Nos. 03-057083 and 09-204525 have been proposed. Examples include filter switching in JP-A-257329 and MTF correction in JP-A No. 2002-94798. With these processes, the character part is sharper and easier to read, and other areas other than the character are not greatly affected.
JP 03-070883 A JP 09-204525 A Japanese Patent Laid-Open No. 10-257329 JP 2002-94798 A JP 2000-1362 A JP 2000-13616 A Special Registration No. 3203946

  As described above, when considering the spread of single-function printers and scanners that can input and output photos with higher image quality and multifunction devices that combine them, the frequency of use of photographs in multifunction devices increases. Is clear. In addition, it is clear that the demand for high image quality will increase, and processing such as image correction that has been performed by a single function will become indispensable.

  On the other hand, it is necessary to improve the image quality of text documents that are often used as copiers and mixed images of text and text documents that are often found on the Internet. In the case of processing that detects specific parts described in the prior art and performs correction based on them, characters and graph areas other than those assumed so far are targeted. And a case where a face is erroneously detected occurs.

  The present invention has been made to solve the above-described problem. In an image processing apparatus that extracts a specific portion in an image and performs image processing based on the extraction, an image acquisition unit that acquires an image, and the image Means for separating the image area of the image obtained by the obtaining means; dividing means for dividing the image into certain blocks; and means for determining whether or not to perform extraction processing for each block according to the result of the image area separation. Extraction means for executing extraction processing only for blocks determined to be executed by the determination means, and image correction coefficient determination means for determining image correction coefficients based on the specific portion extracted by the extraction means The correction is performed using the correction coefficient determined by the image correction coefficient determination means.

  As described above, according to the present invention, according to the present invention, the human skin is appropriately extracted from the photo portion of the image in which characters, graphs, and photographs are mixed, and correction processing is performed based on the extracted human skin. Thus, it is possible to realize an effective correction process with few failures.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[Embodiment 1]
FIG. 2 is a schematic perspective view of a multifunction peripheral (multifunction printer apparatus: hereinafter, MFP apparatus) 1 according to the embodiment of the present invention. The MFP apparatus 1 has a function as a normal PC printer that receives data from a host computer (PC) and prints it, and a function as a scanner. It has a copy function for printing an image with a printer, a function for directly reading and printing image data stored in a storage medium such as a memory card, or a function for receiving and printing image data from a digital camera.

  In FIG. 2, the MFP apparatus 1 includes a reading device 34 such as a flat bed scanner, a printing device 31 such as an ink jet printer, and an operation panel 35 including a display panel 39 and various key switches. In addition, a USB port (not shown) for communicating with the PC is provided on the rear surface of the MFP apparatus 1, and communication with the PC is performed. In addition to the above configuration, a card slot 42 for reading data from various memory cards, a camera port 43 for data communication with a digital camera, and an auto document feeder (hereinafter referred to as ADF) 31 for automatically setting a document on a document table Thus, the MFP apparatus 1 is configured.

  In FIG. 3, the CPU 11 controls various functions provided in the image processing apparatus, and executes an image processing program stored in the ROM 16 in accordance with a predetermined operation of the operation unit 15.

  The reading unit 14 having a CCD corresponds to the reading device 34 in FIG. 2, reads a document image, and outputs analog luminance data of red (R), green (G), and blue (B) colors. Note that the reading unit 14 may include a contact image sensor (CIS) instead of the CCD. Further, if the ADF 31 as shown in FIG. 2 is provided, the order sheets can be read continuously, which is more convenient.

  The card interface 22 also corresponds to the card slot 42 of FIG. 2, and for example, image data shot with a digital still camera (Digital Still Camera, hereinafter referred to as DSC) and recorded on a memory card or the like is transferred in accordance with a predetermined operation of the operation unit 15. Read. Note that the color space of the image data read via the card interface 22 is converted from the DSC color space (for example, YCbCr) into the standard RGB color space (for example, NTSC-RGB or sRGB) by the image processing unit 12. The The image correction described in the prior art may be processed within this standard color space. The read image data is subjected to various processes necessary for the application such as resolution conversion to the effective number of pixels as necessary.

  The camera interface 23 also corresponds to the camera port 43 of FIG. 2 and is used for reading image data by directly connecting to the DSC.

  The image processing unit 12 performs image processing such as image analysis, calculation of conversion characteristics, conversion from luminance signals (RGB) to density signals (CMYK), image processing such as scaling, gamma conversion, and error diffusion, which will be described later. The data obtained thereby is stored in the RAM 17. When the correction data stored in the RAM 17 reaches a predetermined amount necessary for recording by the recording unit 13 corresponding to the printing apparatus 33 of FIG. 2, the recording operation by the recording unit 13 is executed.

  The nonvolatile RAM 18 is a battery-backed SRAM or the like, and stores data unique to the image processing apparatus. The operation unit 15 corresponds to the operation panel 35 of FIG. 2, selects image data stored in the storage medium, and starts a photo direct print start key, a key for printing an order sheet, and an order sheet. , A copy start key for monochrome copy or color copy, a mode key for specifying a mode such as copy resolution and image quality, a stop key for stopping copy operation, and a numeric keypad for inputting the number of copies It consists of a registration key. The CPU 11 detects the pressed state of these keys and controls each part according to the state.

  The display unit 19 corresponds to the display panel 39 of FIG. 2 and includes a dot matrix type liquid crystal display unit (LCD) and an LCD driver, and performs various displays based on the control of the CPU 11. The recording unit 13 corresponds to the printing apparatus 33 of FIG. 2 and is configured by an inkjet type inkjet head, a general-purpose IC, and the like, and reads out the recording data stored in the RAM 17 under the control of the CPU 11 and prints it out as a hard copy.

  The drive unit 21 includes a stepping motor for driving the paper supply / discharge roller, a gear for transmitting the driving force of the stepping motor, and a driver circuit for controlling the stepping motor in the operations of the reading unit 14 and the recording unit 13 described above. Etc.

  The sensor unit 20 includes a recording sheet width sensor, a recording sheet presence sensor, a document width sensor, a document presence sensor, a recording medium detection sensor, and the like. The CPU 11 detects the state of the original and the recording paper based on information obtained from these sensors.

  The PC interface 24 is an interface between the PC and the MFP apparatus 1, and the MFP apparatus performs operations such as printing and scanning from the PC via the PC interface 24.

  In the above configuration, at the time of copying, the image data read by the reading device 34 is processed in the MFP device and printed by the printing device 33. When a copy operation is instructed by the operation unit 15, the reading unit 14 reads a document placed on the document table. The read data is sent to the image processing unit 12, where processing such as background removal and black character processing, conversion from RGB signals to YMCK signals, error diffusion, and the like are executed. Thereafter, the converted data is sent to the recording unit 13 for printing.

  FIG. 4 shows a block diagram of image processing during copying. Hereinafter, each block will be described. In the present embodiment, as the image correction set by the panel, backlight correction that makes the in-document photograph portion more suitable is taken as an example.

(Input data converter)
The RGB value obtained from the reading unit of the scanner is converted into a defined standard color space, for example, sRGB. For the conversion, a conversion coefficient prepared in advance is used. As an example of the conversion method, a matrix operation represented by the following formula is given.

上記３×３のマトリクス演算で、所定の色空間上へと精度良く変換できない場合は、マトリクスを高次のものにするか、後述する四面体補間を利用する。

If the above 3 × 3 matrix calculation cannot be accurately converted into a predetermined color space, the matrix is made higher-order or tetrahedral interpolation described later is used.

(Image area separation processing unit)
As the image area separation process of this embodiment, a process mainly for separating an area such as a character or a graph and a non-character area including a photographic area other than that is performed. FIG. 5 shows a processing flow. In STEP 501, edge extraction is performed. For edge extraction, for example, an edge detection (Sobel) filter shown in FIG. 6 is used. By applying this to the entire image, only the edge portion can be extracted. In STEP 502, a closed loop portion surrounded by the edge portion obtained in STEP 501 is searched. In step 503, the detected dispersion value in the closed loop is obtained. This may be obtained for each RGB signal, or may be performed by converting to a luminance signal. In step 504, the obtained variance value is compared with a preset value. If it is determined that the variance is small, the area is determined to be a character portion or a graph portion.

  In addition to the above-mentioned automatic image area separation processing, if there is a liquid crystal monitor or an external display device that can display an image, the scanned image is displayed there, and the user designates the photo area and determines A method is also conceivable.

(Text processing part)
In the character processing section, it is performed to make the character higher quality. Generally, this is realized by enhancing the edge or increasing the density of the character portion. In order to perform edge enhancement, a sharpening filter represented by Laplacian may be applied. With regard to the density, processing may be performed so as to increase the density of the portion determined as the character by the image area separation.

(Image correction unit)
In the backlight correction processing performed in this image correction unit, correction is realized by detecting the skin color in the image and setting the appropriate brightness. Therefore, the processing is divided into human skin detection processing in the image as the first stage, determination of a correction coefficient based on the result as the second stage, and correction execution processing at the third stage.

  First, the human skin detection process in the first stage will be described. As processing, in addition to the result of the above-described image area separation, an image read by the scanner is used to extract a human skin portion using determination by color and determination by frequency.

  FIG. 7 shows a flowchart. In this process, the process is executed with 8 × 8 as one unit block.

  In STEP701, the image read by the scanner and stored in the RAM is divided into 8 × 8 pixel blocks, and a target block is set.

  In STEP 702, it is determined whether or not all the 64 pixels in the block are determined not to be character areas or graph areas in the image area separation processing section. If any pixel is recognized as a character part or a graph part, the process proceeds to STEP 708, where it is recognized as a block that is not human skin. If all the pixels are non-character areas that are not character parts or graph parts, the process proceeds to STEP 703 and data for color determination is generated. This is for the purpose of obtaining a representative value of the color of the target block, and the average of each RGB signal value may be taken, or pixels at the four corners of the block may be used as representative values.

  In STEP 704, it is determined whether or not the condition of the human skin is satisfied by comparing the color determination data obtained in STEP 703 with a preset value. As a value to be set, a setting in which the hue is in the range of the skin color and extremely high or low brightness or extremely low saturation is excluded is appropriate. If it is determined that the condition is not satisfied, the process proceeds to STEP 708, where it is recognized as a block that is not human skin.

  If the condition is satisfied, the process proceeds to STEP 705, where data for frequency determination is generated. Here, discrete cosine transform (DCT) is performed on the 8 × 8 block. The secondary DCT is represented by the following formula.

但し、

However,

である。今回のケースでは、N=8と設定される。

It is. In this case, N = 8 is set.

  In STEP 706, whether the AC component (AC coefficient) and F [k, l] (k> 0, l> 0) obtained in STEP 705 are satisfied with the conditions of the human skin by comparison with preset values. Determine whether or not. As a value to be set, it is appropriate to set so that there are few high frequency components and mainly low frequency components are detected. If it is determined that the condition is not satisfied, the process proceeds to STEP 708, where it is recognized as a block that is not human skin.

  If the condition is satisfied, the process proceeds to STEP 707 where the target block is recognized as human skin.

  After STEP 707 and STEP 708, the process proceeds to STEP 709, where it is determined whether or not all blocks have been completed. If not, the process returns to STEP 701. If completed, detection of human skin blocks is completed.

  Next, determination of a correction coefficient based on the result as a second stage will be described. Luminance is calculated from the human skin portion detected in the first stage and a correction coefficient is determined.

The RGB signal value and the Y (luminance) CbCr (color difference) signal value are converted by the following formula.
R = Y + 1.402 (Cr-128)
G = Y−0.34414 (Cb−128) −0.71414 (Cr−128)
B = Y + 1.772 (Cb-128)
Y = 0.900 x R + 0.587 x G + 0.114 x B
Cb = (− 0.299 × R−0.587 × G + 0.886 × B) × 0.564 + 128
Cr = (0.701 × R−0.587 × G−0.114 × B) × 0.713 + 128
In this embodiment, a brightness conversion table is created as a correction coefficient. This is, for example, a table storing correspondence indicating what value should be set for the luminance Y component. If the input is 8 bits, the entry is a table of 256. The output result may be 8 bits from 0 to 255, but in consideration of gradation loss, an output with more than 8 bits is desirable.

The determination method uses the luminance value of the block determined to be human skin. By calculating the luminance average Y _human skin of the human skin block, the brightness index of the human skin portion in the image can be acquired. The target brightness Y _TARGET whose value is set in advance, for example, Y _TARGET = Y _{human skin} x k (k = 1.1) to increase the brightness by 10%
A coefficient that brightens the human skin portion is obtained by generating a table such that In order to obtain a more appropriate coefficient, the increase rate to the target luminance is changed according to the luminance value of the human skin, or the target luminance is changed by considering the luminance value Y _{overall luminance} of the _entire image. Is also possible.
Y _TARGET = Y _{human skin} x k (Y _{overall brightness} )
A conversion table LUT _{Y (backlight)} as shown in FIG. 8 is created from the obtained target luminance. Examples of the creation method include a creation method that does not cause a sharp jump in gradation, such as a method of connecting with a straight line, a method of performing smoothing thereto, or a method of obtaining an approximate curve. Thus, Y _NEW for correcting the luminance is obtained.

Further, as the luminance increases, the saturation decreases, and it is necessary to correct it. This varies with the rate of increase in brightness,
S _(backlight) = f (Y _NEW -Y _ORG )
Is calculated by f (Y) is desirably a function that corrects the saturation as the difference in luminance increases.

In the final third stage, the correction execution process, the correction coefficients LUT _{Y (backlight)} and S _(backlight ) relating to the backlight correction obtained above are applied to the image. The original color-difference components Cb _ORG and Cr _ORG are applied as shown in the following equation, and Y _NEW , Cb _NEW , and Cr _NEW are obtained.

Y _NEW = LUT _{Y (backlight)} [Y _ORG ]
Cb _NEW = Cb _ORG × S _(backlight)
Cr _NEW = Cr _ORG × S _(backlight)
Through the above-described steps, the human skin portion is detected, and the backlight correction is applied based on the detected human skin portion.

(Scaling part)
The enlargement / reduction scaling factor is determined from the output size and scaling factor set by the panel. As the scaling method, there are several methods such as simple enlargement / reduction, bilinear method, and bicubic method. Which one to select is determined by the system environment and the required processing speed. The above-described scaling means will be omitted because they are not the essence of this proposal.

(Data converter for output)
The output data converter converts the input signals YCbCr to RGB data into printer device colors. For example, in the case of a printer loaded with six types of ink, the signals are converted into cyan (C), magenta (M), yellow (Y), black (K), light cyan (LC), and light magenta (LM) signals. . If the input is an RGB signal value, the conversion is (R, G, B) → (C, M, Y, K, LC, LM).

  There are several conversion methods, but here, a method using a look-up table (hereinafter referred to as LUT) and interpolation processing is taken as an example.

  The LUT prepared in advance describes C, M, Y, K, LC, and LM signal values corresponding to 4913 points obtained by dividing the RGB values as shown in FIG. 9 into 16 levels each. The C, M, Y, K, LC, and LM values corresponding to the values of the inputs R, G, and B are referred to. When the values of R, G, and B are between 16 divisions, they are obtained by interpolation processing.

  An example of the interpolation method is a tetrahedral interpolation method. The tetrahedral interpolation method is linear interpolation using four grid points with a unit of three-dimensional space as a tetrahedron. As the procedure, first, as shown in FIG. 10A, division into tetrahedrons is performed. Then, the tetrahedron to which the target point p belongs is determined. The four vertices of the tetrahedron are defined as p0, p1, p2, and p3, and the tetrahedron is further divided into smaller tetrahedrons as shown in FIG. Also, if the conversion values of the extension points are f (p0), f (p1), f (p2), and f (p3), respectively,

より求まる。ここで、w0、w1、w2、w3は、各頂点piと反対向位置の小四面体の体積比である。これにより、インク色Ｃ，Ｍ，Ｙ，Ｋ，ＬＣ，ＬＭへの変換が行われる。

More. Here, w0, w1, w2, and w3 are volume ratios of the small tetrahedrons at positions opposite to each vertex pi. Thereby, conversion to ink colors C, M, Y, K, LC, and LM is performed.

(Quantization part)
The data converted into the ink color is subjected to quantization processing. This converts multi-bit data into the number of bits that can be recorded by a recording apparatus. In the present embodiment, a case of a printer having a 1-bit binary value of recording (1) / non-recording (0) is considered. Here, the quantization method is an error diffusion method that is optimal for the quantization of photographic images. The input signal is 8 bits from 0 to 255.

FIG. 11 is a diagram showing an error distribution method in the error diffusion method. When the signal value of the target pixel is L (0 ≦ L ≦ 255), it is compared with the threshold value TH. Depending on its size,
L> TH ・ ・ ・ ・ ・ ・ 1 (Recording)
L ≦ TH ・ ・ ・ ・ ・ ・ 0 (not recorded)
It is determined. The error E (= L-TH) generated at that time is distributed to surrounding pixels according to the distribution coefficient shown in FIG. By performing this processing for all pixels and all ink color colors C, M, Y, K, LC, and LM, 1-bit image data colors C ′, M ′, Y ′, K ′, LC ′, Quantized to LM ′.

  Next, the flow of image processing in the above-described image processing block will be described with reference to FIG. In STEP 1201, the scanner data is read. In STEP 1202, input data conversion processing is performed to obtain signal values in the sRGB space, and then image region separation processing is executed in STEP 1203. In STEP 1204, the character portion is processed in response to the result. In step 1205, it is determined whether or not the user has set the backlight correction by the panel. If it is set, the backlight correction is executed in STEP 1206. If not set, the process proceeds to STEP 1207 as it is. In STEP 1207, it is determined whether the enlargement / reduction process is necessary. If necessary, the process proceeds to STEP 1208 and the scaling process is executed. If not necessary, the process proceeds to STEP 1209 as it is, and is converted into the ink color of the printer by the output data conversion unit. In STEP 1210, quantization processing is executed and converted into data that can be recorded by the printer.

  As described above, as described with specific examples, according to the first embodiment of the present invention, in a copy of a document including characters, graphs, and photographs, human skin is appropriately extracted from the photograph portion. By performing the correction process based on this, an effective correction process with few failures can be realized.

[Other Embodiments]
In the above-described embodiment, a multi-function device has been described as an example. However, a further object of the present invention is to provide a storage medium (or recording medium) that records a program code of software that realizes the functions of the above-described embodiment as a system. Alternatively, it goes without saying that this can also be achieved by supplying the data to the apparatus and reading and executing the program code stored in the storage medium by the computer (or CPU or MPU) of the system or apparatus. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention. Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an operating system (OS) running on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

It is a figure which shows an example of the brightness | luminance histogram of the image which is performing the color cast which exposure is not appropriate. 1 is an overview perspective view of a multifunction peripheral (MFP) according to an embodiment of the present invention. 3 is a block diagram showing a configuration of a main part related to control of the MFP apparatus according to the present embodiment. FIG. It is a figure which shows the image processing block which concerns on embodiment of this invention. It is a figure which shows the flow of the image area separation process which concerns on embodiment of this invention. It is a figure which shows the Sobel filter used for edge detection. It is a figure which shows the flow of the human skin detection process which concerns on embodiment of this invention. It is a figure which shows the luminance conversion table for backlight correction which concerns on embodiment of this invention. It is a figure which shows an example of the look-up table used for the color conversion process which concerns on this Embodiment. It is a figure which shows the tetrahedral interpolation process which concerns on this Embodiment. It is a figure showing the distribution method in the error diffusion method which concerns on this Embodiment. It is a figure which shows the flow of the image processing which concerns on embodiment of this invention.

Claims (4)

In an image processing apparatus that extracts a specific part in an image and performs image processing based on the extraction,
Image acquisition means for acquiring images;
Means for separating an image area from the image obtained by the image obtaining means;
Dividing means for dividing the image into certain blocks;
Means for determining whether to perform extraction processing for each block according to the result of the image area separation;
Extraction means for executing extraction processing only for blocks determined to be executed by the determining means;
An image correction coefficient determination means for determining an image correction coefficient based on the specific portion extracted by the extraction means;
An image processing apparatus comprising: an image correction unit that performs correction using the correction coefficient determined by the image correction coefficient determination unit.   The image processing apparatus according to claim 1, wherein the extraction unit is executed by determination based on color and determination based on frequency analysis. In an image processing method for extracting a specific portion in an image and performing image processing based on the extraction,
An image acquisition step of acquiring an image;
Separating the image area from the image obtained by the image obtaining step;
A dividing step of dividing the image into certain blocks;
Determining whether to perform extraction processing for each block according to the result of the image area separation; and
An extraction step for performing the extraction process only for the blocks determined to be executed by the determination step;
An image correction coefficient determination step for determining an image correction coefficient based on the specific portion extracted by the extraction step;
And an image correction step of performing correction using the correction coefficient determined in the image correction coefficient determination step.   The image processing method according to claim 3, wherein the extracting step is executed by determination by color and determination by frequency analysis.

Images