JP2004185183A - Image correction device, character recognition method, and image correction program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image correction device and image correction program capable of realizing an improvement in recognition ratio on the basis of the distribution state of RGB data of a digital image. <P>SOLUTION: When digital image data for one frame are inputted from an image input part 17 (step P1), the inputted image data are transferred to a RAM, and developed in a bit map image (step P2). When the development to the RAM 14 is ended, values of R, G and B of a processing object are compared with the values of R, G and B of circumferential data according to an image correction processing program to determine whether the processing object is an object (background) of extinction processing or a character (foreground), and the object of extinction processing is corrected by light homogenization. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a technique for correcting an image captured by an imaging device such as a digital camera.
[0002]
[Prior art]
Digital image data obtained by photographing a plane such as a document with an electronic imaging device such as a digital camera is different from digital image data obtained by a flat head scanner. Due to the characteristics of the lens, a dark shadow 72 as shown in FIG. 73 occurs. This is because the amount of light that has passed through the periphery of the lens decreases, and it is known that when the object to be photographed is a character, the dimming effect makes recognition difficult. When such a dimming effect is considered only by the characteristics of the lens, correction can be made by adjusting the light amount on a concentric circle along the shape of the lens.
[0003]
For example, an electronic camera (Patent Literature 1) configured to correct peripheral dimming of image data based on lens information related to peripheral dimming of a photographing lens, acquires characteristics of a photographing lens, and sets the characteristics according to the characteristics of an image An image processing apparatus (Patent Literature 2) configured to perform peripheral dimming of an image by using the reduced light amount, and to reduce the dimming amount of the peripheral image for all pixels based on the distance from the center of the photographing lens Image processing in which the density of the peripheral image is weighted more than the density of the central image, and the intensity of the correction for the dimming is set based on the density balance of the entire image. An apparatus (Patent Literature 3) has a method in which information corresponding to the intensity of the peripheral dimming is stored in a photographic film at the time of photographing, and the information is read at the time of the peak to perform the peripheral dimming correction (Patent Literature 4).
[0004]
[Patent Document 1]
JP-A-2002-190979
[Patent Document 2]
JP 2000-41183 A
[Patent Document 3]
JP-A-11-355511
[Patent Document 4]
JP-A-10-13667
[0005]
[Problems to be solved by the invention]
However, in the conventional peripheral dimming countermeasures as disclosed in Patent Documents 1 to 4, since the amount of light is increased or decreased with emphasis on lens characteristics, unevenness may occur, and external There is a problem that a change in the light amount distribution due to the light cannot be absorbed.
[0006]
SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-described conventional problem of vignetting, and an image correcting apparatus and an image correcting apparatus capable of improving the recognition rate based on the distribution of RGB data of a digital image. The purpose is to provide a fix. In particular, it is an object of the present invention to provide an image correction device and an image correction program suitable for being applied to a character recognition device that recognizes a photographed image as characters.
[0007]
[Means for Solving the Problems]
In order to solve the above-mentioned problems, an image correction apparatus according to a first aspect of the present invention includes an image data capturing unit that captures digital image data into a memory, and R, G, and B among all pixels of the digital image data captured into the memory. A maximum value acquisition unit that acquires the maximum value of the pixel data, a most frequent color data acquisition unit that acquires the color data that appears with the highest frequency among the color data of the pixels in the predetermined region in the image, and a processing target within the predetermined region. Determining means for determining whether or not the color data of the pixel is substantially equal to the color data obtained by the most frequent data obtaining means; and determining the color data of the pixel to be processed by the most frequent data obtaining means. When the values are substantially equal to each other, the difference between the maximum value of R, G, and B and the maximum value of R, G, and B of the color data of the pixel to be processed is calculated as the R, G, and B of each pixel in the predetermined area. Same amount to each And adding adding means One, characterized by comprising a.
[0008]
Further, the image correction device of the second invention includes an image data acquisition unit for acquiring digital image data into a memory, a luminance acquisition unit for acquiring the luminance of a pixel, and A maximum value acquisition unit that acquires a maximum value of the acquired luminance; a maximum luminance data acquisition unit that acquires luminance data that appears most frequently among luminance data of pixels in a predetermined region in an image; A determination unit that determines whether or not the luminance data of the pixel to be processed is substantially equal to the luminance data acquired by the maximum luminance data acquisition unit, and a luminance data of the pixel to be processed is determined by the maximum luminance data acquisition unit. When the luminance data is substantially equal to the acquired luminance data, the difference between the maximum luminance value and the maximum luminance value of the color data of the processing target pixel is calculated for each pixel within the predetermined area. Characterized by comprising adding means for adding the same amount each luminance, the.
[0009]
According to a third aspect of the present invention, there is provided the image correcting apparatus according to the first or second aspect, further comprising a character recognizing means for performing character recognition using the corrected image data.
[0010]
According to a fourth aspect of the present invention, in the image correction device according to any one of the first, second, and third aspects, the predetermined area is rectangular.
[0011]
The character recognition method according to a fifth aspect of the present invention includes the steps of: loading digital image data into a memory; acquiring the maximum values of R, G, and B from all pixels of the digital image data loaded into the memory; Acquiring the color data that appears most frequently among the color data of the pixels in the predetermined area in the image; and obtaining the color data of the pixel to be processed in the predetermined area by the most frequent data acquisition means. Determining whether the color data of the pixel to be processed is substantially equal to the acquired color data, and determining the maximum value of R, G, B and the R of the color data of the pixel to be processed. , G, and B, and adding the same amount to each of R, G, and B of each pixel in the predetermined area, and performing character recognition based on the image data obtained by the steps. With a The features.
[0012]
An image correction program according to a sixth aspect of the present invention is a program executed by an image correction device that corrects peripheral dimming of an image, and includes a step of reading digital image data and a step of loading the read digital image data into a memory. And obtaining a maximum value that can be taken independently for each of R, G, and B from all the pixels of the digital image data taken into the memory. Acquiring the color data that appears most frequently, and determining whether the color data of the pixel to be processed in the rectangular area is substantially equivalent to the color data acquired by the most multicolor data acquisition means, If it is determined by the determination that the color data of the pixel to be processed is substantially equivalent to the color data acquired by the multi-color data acquisition unit, R, Calculating the difference between the maximum value of R, G, and B of the color data of the pixel to be processed and the maximum value of R, G, and B for each pixel in the rectangular area. Adding by the amount.
[0013]
BEST MODE FOR CARRYING OUT THE INVENTION
FIG. 1 is a block diagram showing an embodiment of a hardware configuration of an image correction apparatus according to the present invention. The image correction apparatus 1 includes a CPU 11 for controlling the operation of the entire apparatus, and a key for a user to input data or give an operation instruction. An input unit 12, a display unit 13 for displaying images and the like, and a program temporarily resident, used as a temporary storage for input digital image data (hereinafter simply referred to as image data) and as a work area at the time of image correction. A storage unit 15 such as a magnetic disk reader, a storage medium 16 built in or attached to the storage unit 15, an image input unit 17 for inputting image data, and a printing unit 18 such as an image printer. Have.
[0014]
As shown in the drawing, a character recognition processing unit 22 for performing character recognition from an image (character image) and a dictionary 23 used for character recognition processing are added to the image correction device 1 as shown in FIG. Can be configured. In this case, the character recognition device with the image correction function can perform character recognition on an image (character image) on which the peripheral dimming countermeasures based on the present invention are applied. Character recognition can be performed based on a character image that has been clarified by image correction processing such as light reduction measures by taking in a character image (image data), so that character recognition with a high recognition rate can be realized.
[0015]
An area for temporarily storing image data transferred from the input buffer, a table area for temporarily storing a table (FIG. 6) for checking the most frequent colors in the rectangular range, an OS and image correction processing based on the present invention An area where a program such as a program resides, a constant storage area for holding constants, calculated values, acquired values, and the like are allocated.
[0016]
The storage unit 15 includes an image storage area for storing and storing the corrected image data, and a program resident area for storing a group of programs such as an OS and an image correction processing program for instructing execution of the operation as shown in FIG. Assigned.
[0017]
The image correction processing program includes a subprogram 1 (FIG. 4) for acquiring the maximum value MaxColor and a subprogram 2 (FIG. 5) for acquiring the most frequent colors appearing in the rectangular range. It is installed at the time of initial setting of the image correction device 1 or at an arbitrary time and stored in the program storage area. Further, when the image correction apparatus 1 is started, it is read from the storage medium 16 and resides in the execution program residence area of the RAM 14.
[0018]
The image input unit 17 includes an image recording medium reading device such as a memory card reader or a CD-ROM reader that reads image data written on a memory card taken out of an imaging device such as a digital camera.
[0019]
Instead of or in addition to the image input unit 17, an external interface 19 for inputting image data by a cable connection or a short-range wireless connection such as infrared light with an imaging device such as the digital camera 100 as shown in the drawing, or a wired or A communication interface 20 for inputting image data transmitted from an imaging device such as the digital camera 200 via a wireless communication network may be provided.
[0020]
For example, the character recognition processing unit 22 performs character recognition by extracting a character image one by one from an image image, normalizing the character image, extracting a feature, and comparing the extracted feature with a feature of a character registered in the dictionary 23.
[0021]
The image correction processing of the present invention is configured by a program (image correction program) in the embodiment, and the CPU 11 executes the image correction processing according to the image correction program (FIGS. 3 to 5). May be provided.
[0022]
FIG. 2 is a flowchart showing the outline of the operation of the image correction apparatus of the present invention. When one frame of image data (digital data) is input from the image input unit 17 (or the external interface 19 or the communication interface 20). (Step P1), the CPU 11 transfers the input image data from the input buffer to the RAM 14 and develops (temporarily stores) it as a bitmap image. As an example of bitmap data, one pixel is represented by 24 bits, and each of the R, G, and B components is represented by 8 bits (step P2).
[0023]
When the development to the RAM 14 is completed, the CPU 11 compares the values of R, G, and B to be processed with the values of R, G, and B of the surrounding data by the operation shown in the flowchart of FIG. Then, it is determined whether the processing target is the target (background) or the character (foreground) of the dimming process, and the target of the dimming process is corrected by equalizing the amount of light (step P3).
If the image correction device 1 includes the character recognition processing section 22, the image correction device 1 further performs a character recognition process on the image corrected in step P3 (step P4).
[0024]
(Image correction processing operation)
FIG. 3 is a flowchart showing one embodiment of the image correction processing operation in step P3 shown in FIG.
In FIG. 3, the CPU 11 first operates in the manner shown in the flowchart of FIG. 4 according to the sub-program 1 to store all the data areas 入 力 (Xn, Ym) to (X + n, Y + m) of the input image developed in the RAM 14. ) Is searched for, and the maximum value MaxColor (R or G or B) that can be independently obtained is acquired and stored (temporarily stored) in the RAM 14, and the process proceeds to step S2 (step S1).
[0025]
Next, the origin (X = 0, Y = 0) of the image data is determined at the upper left corner of the image (step S2), and the rectangular area developed on the RAM 14 by the operation shown in the flowchart of FIG. The most multicolor AveColor (R, G, B) appearing in {(Xn, Ym) to (X + n, Y + m)} is acquired and stored (temporarily stored) in the RAM 14, and the process proceeds to step S4 ( Step S3). Note that the best mode is to take a rectangular range here, but it is not limited to a rectangle such as an ellipse.
[0026]
Next, the value of the color data (R, G, B) of the most frequent color in the rectangular range {(Xn, Ym) to (X + n, Y + m)} acquired in step S3 and the processing target The absolute value abs (AveColor− (X, Y)) of the difference between the value of the color data (R, G, B) of the pixel (coordinates (X, Y)) is compared with the threshold, and the absolute value of the difference is larger than the threshold. If it is smaller, it is determined to be the background color, and the process proceeds to step S5; otherwise, it is determined to be a foreground color such as a character (line segment) and the process proceeds to step S8 (step S4).
[0027]
Next, the maximum value TopByte among the R, G, and B of the pixels (coordinates (X, Y)) is obtained (step S5), and the difference (R +, G +, B +) from MaxColor is calculated, and the process proceeds to step S7. (Step S6).
R, G, and B are corrected by adding the calculated difference values, R +, G +, and B +, to the R, G, and B values of each pixel to be processed, which is the background color, by the same amount. (Step S7).
[0028]
Next, it is determined whether or not the coordinate X exceeds the value of the width of the entire data area. If it does, the process proceeds to step S10, and if not, the process proceeds to step S9 (step S8). If the coordinate X does not exceed the value of the width of the entire data area, the process proceeds to step S3 in order to add the value of one dot width to the coordinate X and obtain the most frequent color appearing in the next rectangular range (step S9).
[0029]
When the coordinate X exceeds the value of the horizontal width of the entire data area, it is checked whether the coordinate Y exceeds the value of the vertical width of the entire data area. The image correction processing operation is terminated assuming that the processing has been completed, and if not exceeded, the process proceeds to step S11 (step S10). If the coordinate Y does not exceed the value of the vertical width of the entire data area, the process proceeds to step S3 to add the value of one dot width to the coordinate Y and obtain the most frequent color appearing in the next rectangular range (step S11). .
[0030]
When the image correcting apparatus 1 includes the character recognition processing unit 22, the character recognition processing unit 22 further cuts out the character image one by one from the corrected image image in steps S1 to S11 and normalizes the character image. Then, the feature of the character image after the normalization is extracted, compared with the feature of the character registered in the dictionary 23, character recognition is performed, and a recognition result is output (step S12).
[0031]
By the step S4 in the flowchart of FIG. 3, it can be determined whether or not the color data (R, G, B) of the pixel to be processed within the rectangular range is substantially equal to the most multicolor AveColor. When the color data of the target pixel is substantially equivalent to the maximum color data, the difference between the maximum value of R, G, B and the maximum value of R, G, B of the color data of the processing target pixel is determined within the rectangular range. Since the same amount can be added to each of R, G, and B of each pixel, the operation of the flowchart (FIG. 3) of the R, G, and B of the pixel to be processed (coordinates (X, Y)) can be performed. By comparing the value with the R, G, and B values of the most surrounding colors, it is possible to determine whether the data can be simply corrected as the background or the foreground data such as characters. Then, in step S7, the light amount of the image data is made uniform to eliminate peripheral dimming, so that the image can be sharpened.
[0032]
In addition, since the correction process is bypassed for the foreground data as shown in step S8 and thereafter, information such as characters is clearly displayed as shown in FIG. It will be easier to see.
[0033]
In addition, in step S12, a character image (image data) captured by an imaging device such as a digital camera can be captured and character recognition can be performed based on the character image that has been clarified by image correction processing such as dimming measures. Therefore, a high character recognition rate can be realized for characters photographed by a digital camera or the like.
[0034]
In step S2, the origin (X = 0, Y = 0) of the image data is set at the upper left corner of the image. However, the present invention is not limited to this. The origin may be the lower left corner, the upper right corner or the lower right corner may be the origin, or the center of the image may be the origin. However, when the position of the origin is not at the upper left corner, it is necessary to change the added value in steps S9 and S11 according to the position of the origin.
[0035]
(Operation by subprogram 1)
FIG. 4 is a flowchart showing an operation example of a subprogram for acquiring the maximum value.
First, the origin (X = 0, Y = 0) of the image data is set at the upper left corner of the image, the maximum value MaxColor (R, G, B) area of the RAM 14 is cleared to 0 (step S1-1), and the designated coordinates ( The values of R, G, and B of the pixel of (X, Y) are obtained, respectively. Here, R = Red (X, Y), G = Green (X, Y), and B = Blue (X, Y) (step S1-2).
[0036]
Next, the maximum value MaxRGB of the R, G, and B obtained in step S1-1 is obtained (step S1-3), and MaxRGB is compared with MaxColor. If MaxRGB <MaxColor, step S1- 6; otherwise, the process proceeds to step S1-5 (step S1-4). If MaxRGB <MaxColor is not satisfied, MaxRGB is substituted for MaxColor, and the process proceeds to step S1-6 (step S1-5).
[0037]
Next, it is checked whether or not the coordinate X is smaller than the value of the width of the entire data area. If not, the process proceeds to step S1-7. If not, the process proceeds to step S1-8 (step S1-6). . If the coordinate X does not exceed the horizontal width of the entire data area, the process proceeds to step S1-2 to add the value of one bit width to the coordinate X and acquire the most frequent color in the next rectangular range (step S1-7).
[0038]
If the coordinate X exceeds the value of the horizontal width of the entire data area, it is checked whether or not the coordinate Y exceeds the value of the vertical width of the entire data area. If the coordinate Y does not exceed the value, the process proceeds to step S1-9. If so, it is determined that the MaxColor acquisition operation has been completed for all image data areas, the operation by the subprogram ends, and the process returns to step S1 in the flowchart of FIG. 3 (step S1-8). If the coordinate Y does not exceed the value of the vertical width of the entire data area, a value of one bit width is added to the coordinate Y, and the process proceeds to step S1-2 (step S1-9).
[0039]
In the above step S1-1, the origin (X = 0, Y = 0) of the image data is set at the upper left corner of the image. However, the present invention is not limited to this. The origin may be the lower left corner, the upper right corner or the lower right corner may be the origin, or the center of the image may be the origin. However, when the position of the origin is other than the upper left corner, it is necessary to change the added value in steps S1-7 and S1-9 according to the position of the origin.
[0040]
(Operation by subprogram 2)
FIG. 5 is a flowchart showing an operation example of a subprogram for acquiring the most frequent colors appearing in a rectangular range. FIG. 6 is a diagram showing a configuration example of a table for examining the most frequently occurring color (most multicolor data) in an arbitrary area (rectangular range in the embodiment) centered on the processing target data. , 60-2,... Indicate table data constituting the table 60, reference numerals 61-1, 61-2,... Indicate the appearance frequency storage columns of the colors indicated by the respective table data, and the appearance frequency storage columns. .. Function as counters. .., R, G, and B in the table data 60-1, 60-2,. In FIG. 5, the table 60 (FIG. 6) is shown as Table []. The table 60 is generated in a table area of the RAM 14. In the configuration of FIG. 6, the table 60 requires an area of four times the size of the arbitrary area (appearance frequency + R, G, B) +1 (the number of data), but the table is not limited to the configuration of FIG.
[0041]
When the CPU 11 proceeds from step S2 to step S3 in the flowchart of FIG. 3, the CPU 11 clears the table data 60-1, 60-2,... Of the table 60 as shown in FIG. Step 3-1), R, G, and B values of the pixel at the designated coordinates (X, Y) are obtained. Here, R = Red (X, Y), G = Green (X, Y), and B = Blue (X, Y) (step S3-2).
[0042]
Next, among the table data 60-1, 60-2,... Of the table 60, the values in the R, G, and B storage columns of the table data in which the values have already been stored are compared with the threshold value. It is checked whether there is any data (step S3-3). If there is no data within the threshold, the process proceeds to step S3-5, and if there is, the process proceeds to step S3-6 (step S3-4).
[0043]
If there is no data within the threshold value, the R, G, and B values of the pixel at the designated coordinates (X, Y) obtained in step S3-2 are stored in the R, G, and B storage columns of the vacant table data in the table 60. Are stored (= stored), and the process proceeds to step S3-7 (step S3-5).
[0044]
If there is data within the threshold value, 1 is added to the counter of the data table of the existing color (appearance frequency storage column) to update, and the process proceeds to step S3-7 (step S3-6).
[0045]
Next, it is checked whether or not the data within the rectangular range has been checked for any data within the threshold. If the check has been completed, the process proceeds to step S3-8; otherwise, the process returns to step S3-2. (Step S3-7).
[0046]
Next, the appearance frequency columns 61-1, 61-2,... Of the table data 60-1, 60-2,. = R, G, B) is set in AveColor (R, G, B), and the process returns to step S3 in FIG. 3 (step S3-8).
[0047]
FIG. 7 is an explanatory diagram of peripheral dimming that has occurred in a digital image, the result of correction processing, and the like. FIG. 7A is an explanatory diagram of the peripheral dimming according to the related art. Even when the background color is the same color, dark regions 72 and 73 (shaded portions) at the lower left and lower right are different from the background color. Appears in The reason why the light does not appear concentrically from the center is because external light at the time of photographing has an influence. FIG. 7B shows an example in which the brightness of a similar color is simply increased or replaced, and the character 71 disappears and becomes an unclear image as represented by a reference numeral 71 ′.
[0048]
FIG. 7C shows an image after the image correction processing of the present invention. The color data (R, G, B) around the pixel of the processing target (character 71) determines whether the processing target pixel is a background or a foreground. (Character), and in the case of the background, the light amount is made uniform based on the distribution state of the surrounding color data (R, G, B) to correct the dimming part. The character 71 does not disappear and becomes a clear image.
[0049]
(Modification)
In the description of the above embodiment, R, G, and B of a pixel to be processed (coordinates (X, Y)) are compared with R, G, and B of the largest number of surrounding pixels, and correction processing is simply performed as a background. Although it is determined whether the data is good data or foreground data such as characters, the luminance may be derived from R, G, and B, and the luminance may be used for comparison. In this case, a step of deriving the luminance from R, G, and B of all the pixels of the image data taken into the RAM 14 is provided at a stage preceding the step S1 of FIG. 3, and steps S1 and subsequent steps of the flowchart of FIG. In steps S1-1 and subsequent steps, steps S3-1 and subsequent steps in the flowchart of FIG. 5 and the description of those steps, R, G, and B may be replaced with luminance, and the color data may be replaced with luminance data. The method of deriving the luminance from R, G, and B can be performed using a known method (conversion formula).
In addition, Y data of video signal YUV data may be used without being limited to R, G, and B data.
As mentioned above, although one Example and a modification were described, the present invention is not limited to the above-mentioned Example and a modification, and it cannot be overemphasized that various modifications are possible.
[0050]
【The invention's effect】
As described above, according to the image correction apparatus of the first invention, the R, G, and B values of the pixel to be processed (coordinates (X, Y)) and the R, G, and By comparing the value of B, it is determined whether the data can be simply corrected as the background or the foreground data such as characters, and the amount of image data is made uniform to eliminate peripheral dimming and the like. As in the conventional case, no dark portion or the like appears in the periphery, and a line image such as a character becomes a clear image.
[0051]
Further, in the image correcting apparatus of the second invention, since the luminance is used instead of R, G, and B, the same effect as that of the first invention can be obtained.
[0052]
Further, in the image correcting apparatus according to the third aspect of the invention, character recognition is performed based on the corrected image data, so that the recognition system can be further improved.
[0053]
Further, in the image correcting apparatus according to the fourth aspect of the present invention, since the predetermined area to be processed is rectangular, there is an effect that a computer program can be easily assembled and the calculation can be performed quickly.
[0054]
Further, according to the character recognition method of the fifth invention, it is determined whether the data can be simply corrected as the background or the foreground data such as a character, and the light amount of the image data is made uniform to eliminate peripheral dimming and the like. Therefore, even after the correction, a dark portion or the like does not appear in the periphery as in the related art, and a line image such as a character becomes a clear image, and the character recognition rate can be further improved.
[0055]
According to the image correction program of the sixth invention, the same effects as those of the first invention can be obtained by the program. Therefore, if the image correction program is installed, a commercially available personal computer can be used as the image correction device. Therefore, the end user of the imaging device such as a digital camera can easily perform the light reduction correction of the image.
[Brief description of the drawings]
FIG. 1 is a block diagram showing one embodiment of a hardware configuration of an image correction device based on the present invention.
FIG. 2 is a flowchart showing an outline of the operation of the image correction device of the present invention.
FIG. 3 is a flowchart illustrating an embodiment of an image correction processing operation.
FIG. 4 is a flowchart showing an operation example of a subprogram for acquiring a maximum value.
FIG. 5 is a flowchart illustrating an operation example of a subprogram for acquiring the most frequent colors appearing in a rectangular range.
FIG. 6 is a diagram showing a configuration example of a table for checking the most frequent colors appearing in a rectangular range.
FIG. 7 is an explanatory diagram of peripheral dimming occurring in a digital image, a result of a correction process, and the like.
[Explanation of symbols]
11 CPU (image data acquisition means, maximum value acquisition means, luminance acquisition means, most-color data acquisition means, determination means, addition means, most-luminance data acquisition means)
14 RAM (memory)
17 Image input unit (image data capturing means)
19 External interface (image data capturing means)
20 Communication interface (image data capturing means)
60 tables (most color data acquisition means, most luminance data acquisition means)

Claims (6)

Image data capturing means for capturing digital image data into a memory;
Maximum value acquisition means for acquiring the maximum value of R, G, B from among all the pixels of the digital image data taken into the memory;
Among the color data of the pixels in the predetermined area in the image, the most frequent data acquisition means for acquiring the color data that appears most frequently,
Determining means for determining whether or not the color data of the pixel to be processed in the predetermined area is substantially equivalent to the color data obtained by the most multicolor data obtaining means;
When the color data of the pixel to be processed is substantially equivalent to the color data obtained by the multicolor data obtaining unit, the maximum value of the R, G, and B and the color of the pixel to be processed are determined by the determination unit. Adding means for adding the same amount of difference between the maximum value of R, G, and B to the R, G, and B of each pixel in the predetermined area;
An image correction device comprising: Image data capturing means for capturing digital image data into a memory;
Brightness acquisition means for acquiring the brightness of the pixel;
Maximum value acquisition means for acquiring the maximum value of the acquired luminance from among all the pixels of the digital image data taken into the memory,
Among the luminance data of the pixels in the predetermined area in the image, the most frequent luminance data acquisition means for acquiring the luminance data that appears most frequently,
Determining means for determining whether the luminance data of the processing target pixel in the predetermined area is substantially equivalent to the luminance data acquired by the maximum luminance data acquiring means,
When the luminance data of the pixel to be processed is substantially equivalent to the luminance data acquired by the maximum luminance data acquiring unit, the maximum value of the luminance and the luminance of the color data of the pixel to be processed are determined by the determination unit. Addition means for adding the same amount to the difference between the maximum value and the luminance of each pixel in the predetermined area,
An image correction device comprising: 3. The apparatus according to claim 1, further comprising a character recognizing unit, wherein character recognition is performed using the corrected image data. The apparatus according to claim 1, wherein the predetermined area is a rectangle. Capturing digital image data into a memory;
Obtaining the maximum value of R, G, B from among all the pixels of the digital image data taken into the memory;
Obtaining color data that appears most frequently among the color data of the pixels in the predetermined area in the image;
Determining whether the color data of the pixel to be processed in the predetermined area is substantially equivalent to the color data acquired by the multicolor data acquisition means,
When the color data of the pixel to be processed is substantially equivalent to the acquired color data, the maximum value of the R, G, B and the maximum value of R, G, B of the color data of the pixel to be processed are calculated. Adding the same difference to the R, G, and B of each pixel in the predetermined area by the same amount,
Performing character recognition based on the image data obtained in the step,
A character recognition method comprising: A program executed by an image correction device that corrects peripheral dimming of an image,
Reading digital image data, loading the read digital image data into a memory,
Acquiring a maximum value that can be taken independently of each of R, G, and B from among all the pixels of the digital image data taken into the memory;
Acquiring color data that appears most frequently among the color data of the pixels in the rectangular area in the image;
Determining whether or not the color data of the processing target pixel in the rectangular area is substantially equivalent to the color data acquired by the multicolor data acquisition unit;
When the color data of the pixel to be processed is determined to be substantially equivalent to the color data acquired by the multi-color data acquisition unit, the maximum value of the R, G, and B and the pixel of the pixel to be processed are determined. Calculating a difference between the maximum value of R, G, and B of the color data;
Adding the calculated difference to the R, G, and B of each pixel in the rectangular area by the same amount,
An image correction program characterized by comprising:

Images