JP2002158874A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor in which a character can be distinguished surely from a background pixel based on a color signal. SOLUTION: A color signal delivered from a photoelectric converting section 1 is stored in a color image memory 2 and then used for calculating the chroma of each pixel at a chroma calculating section. At an area classifying section 4, each pixel is classified into a character area, an intermediate area and a background area based on the chroma. A character area deciding section 10 retrieves pixels in the peripheral character area centering a pixel in the intermediate area and calculates the difference between a pixel in the intermediate area and the color signal of a pixel in the character area. If the difference of the color signal is not larger than a preset threshold value, classification of a pixel in the intermediate area is corrected to the character area.

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 for binarizing a color image for character recognition and the like.

[0002]

2. Description of the Related Art Conventionally, a character recognition apparatus for reading a color image and performing character recognition uses a color image of R (red), G
(Green) and B (blue), which are read out after being separated into three colors, and R, G, and
The black pixels constituting the character are extracted based on the B color signal.

In such a character recognition device, when the luminance values of the R, G, and B color signals obtained from the color sensor are all smaller than a predetermined threshold value, it is determined that the pixel is black and a pixel constituting a character is determined. Was to be extracted.

[0004]

However, the conventional character recognition device has the following problems. That is,
Pixels in which the luminance of the R, G, and B color signals are all smaller than the threshold value are determined as character pixels. For this reason, for example, when a dark or dull color is used for the character entry frame (or background color), the character entry frame (or background color) may be detected as a character pixel and cause noise.
On the other hand, if the threshold is determined according to the luminance of the character entry frame,
There is a problem that the read characters are blurred.

For example, when a character entry frame printed in brown is read by a color sensor, the luminance of the B color signal becomes the smallest, and the threshold value is determined based on this luminance. By using such a threshold, the character entry frame is not detected. However, by using such a small threshold that the text box is not detected,
It has been difficult to reliably detect the actually written character portion as a character pixel, and there has been a problem that the read character may be blurred.

An object of the present invention is to solve the problems of the prior art and to provide an image processing apparatus capable of reliably determining a character and a background pixel based on a color signal.

[0007]

According to a first aspect of the present invention, there is provided an image processing apparatus comprising: a color signal of a red component, a green component, and a blue component of a pixel forming an image; Pixel information calculating means for calculating the saturation or lightness of each pixel based on the pixel information, and based on the saturation or lightness calculated by the pixel information calculating means, each of the pixels is a character area, an intermediate area or a background area. A pixel area classifying means for classifying the color area of the pixel in the character area or the background area within a predetermined range centered on the pixel; A pixel area correction unit that corrects a pixel area classified as the intermediate area into a character area or a background area as compared with the signal.

According to a second aspect of the present invention, the pixel area correcting means according to the first aspect of the present invention uses the pixel of the intermediate area as a pixel of interest and a window of m × n pixels (where m and n are plural) around the pixel of interest. Is set, and when the pixel of the character area exists in the window, the color signal of the pixel of the character area and the color signal of the target pixel are compared,
When the difference is equal to or smaller than the threshold value, the process of correcting the region of the pixel of interest into a character region is sequentially repeated until there is no more pixel in the intermediate region to be corrected.

According to a third aspect of the present invention, the pixel area correcting means according to the first aspect of the invention is arranged such that a pixel in an intermediate area adjacent to a pixel in a character area is a pixel of interest and is continuous on radiation in eight directions around the pixel of interest. A pixel in the intermediate region is searched, and color signals of the searched pixel in the intermediate region and the pixel of interest and a pixel in a character region adjacent to the pixel of interest are compared. The processing of correcting the pixel region of the intermediate region thus obtained into a character region is sequentially performed.

According to a fourth aspect of the present invention, the pixel area correcting means according to the first aspect of the present invention comprises:
A window of n (where m and n are plural) pixels is set, and when a pixel of a character region exists in the window, the color signal of the pixel of the character region and the color signal of the target pixel are compared. In the following, the processing of correcting the area of the pixel of interest into a character area and calculating the line width of the corrected character area is sequentially performed until the calculated line width satisfies a preset condition. ing.

According to the present invention, since the image processing apparatus is configured as described above, the following operation is performed.

The pixel information calculation means calculates the saturation or brightness of each pixel based on the color signals of the red, green and blue components of the pixels constituting the image. The pixel area classifying means classifies each pixel into a character area, an intermediate area, or a background area based on the calculated saturation or brightness. For the pixels classified into the intermediate region, the color signal of the pixel is compared with the color signal of the pixel in the character region or the background region existing within a predetermined range centered on the pixel by the pixel region correction unit. . Furthermore,
The pixel area classified as the intermediate area is corrected to a character area or a background area based on the comparison result of the pixel area correction unit.

[0013]

(First Embodiment) FIG. 1 is a configuration diagram of an image processing apparatus showing a first embodiment of the present invention. This image processing apparatus separates a form into pixels and reads the pixels, and calculates the luminance of R, G, and B for each pixel by color signals r, g,
It has a photoelectric conversion unit 1 that outputs as b. The output side of the photoelectric conversion unit 1 is connected to a color image memory 2 for storing color signals r, g, b for one screen.

The color image memory 2 is connected to image information calculation means (for example, a saturation calculation unit) 3. The saturation calculator 3 calculates the saturation S by the following equation (1) based on the color signals r, g, and b stored in the color image memory 2. S = {(r−g) ² + (r−b) ² + (g−b) ² } / 2 (1) where r, g, and b are each within the range of 0 to 1. Is a luminance value normalized to. Thereby, the saturation S takes a value in the range of 0 to 1.

The saturation S calculated by the saturation calculation section 3 is provided to a pixel area classification means (for example, an area classification section) 4. The area classification unit 4 classifies the area of each pixel into any of a character area, an intermediate area, and a background area. The area information of each pixel classified by the area classification unit 4 and the color signals r,
g and b are provided to a pixel area correction unit (for example, a character area determination unit) 10.

The character area determination unit 10 determines a pixel classified as an intermediate area from the area information of each pixel supplied from the area classification unit 4 as a character area or a background area and binarizes the pixel. Is what you do. The character area determination unit 10 includes an image memory 11, an intermediate area detection unit 12, and an area correction unit 1.
3.

The image memory 11 stores the area information of each pixel constituting the image. The area information of each pixel classified by the area classification section 4 is written in the image memory 11 and the area information of the pixel is corrected by the correction information from the area correction section 13. , The area information is corrected.

The intermediate area detecting section 12 is provided in the image memory 1
1, a pixel in the intermediate region is searched and used as a pixel of interest. Based on the position of this pixel of interest, the color signals r, g, b of the pixel of interest and pixels in a certain range around the pixel of interest are obtained.
Is read. The pixel of interest read by the intermediate area detection unit 12 and the color signals r, g,
b is provided to the area correction unit 13.

The area correction section 13 determines whether or not the target pixel is corrected from the intermediate area to the character area, and rewrites the area information in the image memory 11 when correcting. Specifically, in the area correction unit 13, the color signals r, g, b of the pixel of interest and the color signals r, g, b of the pixels in the character area are compared for each component, and the difference between the components is set in advance. When the value is equal to or smaller than the threshold value, the pixel of interest is corrected to a character area.

The search of the pixels in the intermediate area in the image memory 11 by the intermediate area detecting section 12 is repeatedly performed in order from the beginning to the end of the image memory 11 until there is no more pixel of interest to be corrected. Then, the area information finally written in the image memory 11 is output as a binarized output signal OUT.

FIG. 2 is an explanatory diagram of the processing in the area classification unit 4 in FIG. FIG. 3 shows the character area determination unit 1 in FIG.
FIG. 7 is an explanatory diagram of a processing range at 0. FIG. 4 is a flowchart showing the operation of FIG. Hereinafter, the operation of FIG. 1 will be described with reference to FIGS.

First, the photoelectric conversion unit 1 in FIG. 1 is activated,
The form to be read is scanned (step S in FIG. 4).
1) The color signals r, g, b photoelectrically converted are output. The color signals r, g, b output from the photoelectric conversion unit 1
Is stored in the color image memory 2 (step S
2). The color signals r, g, and b of each pixel stored in the color image memory 2 are sequentially read out by the saturation calculator 3, and the saturation S is calculated according to the equation (1) (step S).
3).

The saturation S calculated by the saturation calculator 3 is given to the area classifier 4, and it is determined whether the pixel corresponds to a character area, an intermediate area, or a background area (step S4). . That is, as shown in FIG. 2, if the saturation S is between 0 and the threshold TH1, the character area, the thresholds TH1 and TH2
If it is between the threshold values TH2 and 1, it is determined to be a background area. The area information of the determination result is stored in the image memory 11 for each pixel (step S5).

When all the area information of the pixels for one screen is stored in the image memory 11,
Is set as the search start position (step S6), and the intermediate area detection unit 12 is activated. The intermediate area detection unit 12 searches the area information of the pixels stored in the image memory 11 in order from the top, and detects a pixel determined to be an intermediate area as a target pixel (steps S7 and S7).
8). The intermediate region detection unit 12 determines the color signals r and g of a certain range of pixels (here, the target pixel and a total of nine pixels adjacent thereto) around the target pixel based on the detected position of the target pixel. , B from the color image memory 2 to the readout area correction unit 13.

In the area correction unit 13, as shown in FIG.
It is determined whether or not there is a pixel of the character area in a predetermined range around the pixel of interest (step S9). If so, the difference between the pixel of the character area and the color signals r, g, b of the pixel of interest is calculated. (Step S10). Further, the color signals r,
The difference between g and b is compared with a threshold (step S11). If the difference is smaller than the threshold, the area information of the pixel of interest is changed to a character area (step S12). The search for the target pixel and the area correction processing for the searched target pixel are sequentially performed up to the last pixel in the image memory 11. When the search is completed up to the last pixel, it is checked whether or not the area information of the pixel of interest has been changed during the screen search (step S13).

If there is a change in the pixel of interest, the search for the pixel of interest and its area correction process are repeated from the top of the image memory 11 (steps S6 to S13). If the pixel of interest has not been changed, the area information of the pixel of the intermediate area remaining in the image memory 11 is changed to the background area (step S14).

As a result, the area information of the pixels in the image memory 11 becomes binary of the character area and the background area, and the image memory 11 outputs the binarized output signal OUT.

As described above, the image processing apparatus according to the first embodiment includes an area classification unit 4 for classifying pixels into a character area, an intermediate area, or a background area based on saturation.
There is a character area determination unit 10 that compares the pixels in the intermediate area with the color signals of the pixels in the surrounding character area, and corrects the pixels into a character area based on the comparison result. As a result, even when the density of the pixels constituting the character gradually decreases, such as in the case of the character wiping, the character can be reliably detected by distinguishing the character pixel from the background pixel.

(Second Embodiment) FIG. 5 shows a second embodiment of the present invention.
5 is a flowchart showing the operation of the embodiment of the present invention, in which components common to those in FIG. 4 are denoted by common reference numerals.

The configuration of the image processing apparatus corresponding to the flowchart of FIG. 5 is substantially the same as that of FIG. 1, and an intermediate area having a slightly different function is used in place of the intermediate area detector 12 and the area corrector 13 in FIG. This is provided with a detection unit 12A and an area correction unit 13A.

That is, the intermediate area detecting section 12A scans the inside of the image memory 11 and detects a pixel in the intermediate area adjacent to a pixel in the character area as a pixel of interest. Further, the intermediate region detection unit 12A searches for pixels in the continuous intermediate region on the radiation in the eight directions (vertical, horizontal, and oblique) with the detected pixel of interest as the center, and detects the color signal of the detected pixel in the intermediate region. It has a function of reading r, g, and b from the color image memory 2 and providing the read data to the area correction unit 13A.

The area correcting section 13A is provided with the intermediate area detecting section 12
A, the color signals r, g,
b, and a function of determining whether or not to correct the area information of the pixels in the intermediate area into the character area according to the difference between the color signals r, g, and b of the pixels in the character area adjacent to the pixel of interest. I have. Other configurations are the same as those in FIG.

FIG. 6 is an explanatory diagram of the processing in step S9A in FIG. Hereinafter, the processing based on FIG. 5 will be described with reference to FIG.

An image for one screen of a form is read (step S1), the read color signals r, g, b are stored in the color image memory 2 (step S2), and the saturation S is calculated for each pixel. (Step S3), it is classified into any of the character, intermediate, and background regions (Step S4).
After all the area information for each pixel is stored in the image memory 11 (step S5), the head of the image memory 11 is set as a search start position (step S6).

Thereafter, the intermediate area detecting section 12A is activated, the area information of the pixels stored in the image memory 11 is searched in order from the top, and the pixels of the intermediate area adjacent to the pixels of the character area are set as the pixels of interest. It is detected (steps S7, S8). Further, by the intermediate area detection unit 12A,
A search is performed to determine whether or not there is a pixel in a continuous intermediate region on the radiation in the eight directions (vertical, horizontal, and oblique) with the detected target pixel as the center (step S9A). If there is a pixel in the intermediate area that is continuous with the target pixel, the color signals r, g, and b of the pixels in the intermediate area including the target pixel are stored in the color image memory 2.
And is supplied to the area correction unit 13A.

For example, as shown in FIG.
Position (X5, Y1) adjacent to the pixel of the character area of Y1)
Is detected as a pixel of interest, and positions (X4, Y2), (X3, Y3),
A pixel in the intermediate area at (X2, Y4) and a pixel in the intermediate area at a position (X5, Y2) continuous below the pixel of interest are searched for as pixels to be corrected. Then, the color signals r, g, and b at these pixel positions are read from the color image memory 2 and provided to the area correction unit 13A.

In the area correction section 13A, the intermediate area detection section 1
The difference between the color signals r, g, b of the pixels in the intermediate area read from the color image memory 2 and the color signals r, g, b of the pixels in the character area by 2A is calculated (step S).
10A). The calculated difference between the color signals r, g, and b is compared with a preset threshold value (step S11). If the difference is smaller than the threshold value, the classification of the corresponding pixel of interest and the pixel of the intermediate region is performed in the character region. (Step S
12A).

After such a search for a pixel of interest and a pixel in an intermediate area continuous with the pixel of interest and an area correction process for those pixels are performed up to the last pixel of the image memory 11,
The area information of the pixels of the intermediate area remaining in the image memory 11 is changed to the background area (step S14).

As a result, the area information of the pixels in the image memory 11 becomes binary of the character area and the background area, and the image memory 11 outputs the binarized output signal OUT.

As described above, the image processing apparatus according to the second embodiment uses the area classification unit 4 for classifying pixels into any of a character area, an intermediate area, and a background area based on saturation.
And a pixel in the intermediate region adjacent to the pixel in the character region, and comparing the color signal of the pixel in the intermediate region on the radiation in eight directions with the color signal of the pixel in the character region. It has a character area determination unit 10 that corrects a character area based on the result. Thus, in addition to the same advantages as the first embodiment, correction of all pixels can be performed only by scanning the screen once, and the processing time can be reduced.

(Third Embodiment) FIG. 7 shows a third embodiment of the present invention.
FIG. 2 is a configuration diagram of an image processing apparatus according to the first embodiment, in which components common to those in FIG. 1 are denoted by common reference numerals.

This image processing apparatus is provided with a character area determining section 20 having a different function, instead of the character area determining section 10 in the image processing apparatus shown in FIG.

The character area determination section 20 determines and binarizes the pixels classified into the intermediate area by the area classification section 4 into one of a character area and a background area for each character. The character area determination unit 20 includes an image memory 21,
A character cutout unit 22, a panta memory 23, a line width calculation unit 24,
It comprises an intermediate area detection section 25 and an area correction section 26.

The image memory 21 stores area information of each pixel constituting an image. Character extraction section 22
Is to cut out pixel area information stored in the image memory 21 in units of one character. Pattern memory 2
Numeral 3 stores the area information of the pixel of one character extracted by the character extraction section 22 and corrects the area information by the correction information from the area correction section 26.

The line width calculation section 24 calculates the width of the line constituting the character based on the pixel area information of one character stored in the pattern memory 23, and the line width is within a predetermined range. It is to determine whether or not. Intermediate area detector 25
Finds a pixel in an intermediate area in the pattern memory 23 and sets it as a pixel of interest. Based on the position of this pixel of interest, the color image memory 2 outputs a pixel of interest and color signals r, g, b is read. The color signals r, g, and b of the pixel of interest and its surrounding pixels read by the intermediate region detection unit 25 are provided to the region correction unit 26.

The area correction section 26 determines whether or not the pixel of interest is corrected from the intermediate area to the character area, and rewrites the area information in the pattern memory 23 when the correction is performed. Specifically, in the area correction unit 26, the color signals r, g, and b of the pixel of interest and the color signals r, g, and b of the pixels in the character area are compared for each component, and the difference between the components is set in advance. When the threshold value is equal to or less than the threshold value, the target pixel is corrected to a character area.

FIG. 8 is a flowchart showing the operation of FIG. Hereinafter, the operation of FIG. 7 will be described with reference to FIG.

The photoelectric conversion unit 1 shown in FIG. 7 is activated, the form to be read is scanned and read, and the color signals r,
g and b are stored in the color image memory 2 (steps S1 and S2 in FIG. 4). The color signals r, g, and b of each pixel stored in the color image memory 2 are sequentially read out by the saturation calculation unit 3, the saturation S is calculated and given to the area classification unit 4, The area is classified into one of an area, an intermediate area, and a background area (steps S3 and S4). The classified area information is stored in the image memory 21 for each pixel (step S5).

When the area information of the pixels for one screen is stored in the image memory 21, the character extracting section 22 is activated and
Area information for characters is cut out and stored in the pattern memory 23 (step S21). Next, image memory 2
3 is set as the search start position (step S2).
3), the intermediate area detection unit 25 is activated. Further, the area information of the pixels stored in the pattern memory 23 is searched in order from the top by the intermediate area detection unit 25, and the pixel determined to be the intermediate area is detected as the target pixel (steps S24 and S25). The intermediate region detection unit 25 determines, based on the detected position of the pixel of interest, the color signals r and g of the pixels within a certain range around the pixel of interest (here, the pixel of interest and a total of nine pixels adjacent thereto). , B from the color image memory 2 to the readout area correction unit 26.

The area correction section 26 determines whether or not there is a pixel in the character area in a predetermined range around the pixel of interest (step S26). If so, the color signal between the pixel in the character area and the pixel of interest is determined. The difference between r, g, and b is calculated (step S27). Then, the difference between the color signals r, g, and b is compared with a threshold (step S28). If the difference is smaller than the threshold, the area information of the pixel of interest is changed to a character area (step S29). Searching for such a pixel of interest,
The region correction processing of the pixel of interest is sequentially performed up to the last pixel of the pattern memory 23.

When the search for the pixel of interest in the character memory 23 is completed (step S25), the line width detector 24 is activated, and the line width of the character area is determined based on the area information of the pixels in the character memory 23. Is calculated (step S3
0). It is determined whether or not the calculated line width is within a predetermined range (step S31). If the calculated line width is outside the predetermined range, the intermediate region detection unit 25 and the region correction unit 26 search for the pixel of interest again. Are repeated (steps S23 to S31).

If the line width falls within the predetermined range, the area information of the pixels of the intermediate area remaining in the pattern memory 23 is changed to the background area (step S32). As a result, the area information of the pixels in the pattern memory 23 becomes binary of the character area and the background area.
An output signal OUT for one character is output.

Further, the same processing is performed for the next one character, and when the processing for all the characters is completed (step S22), the operation of the image processing apparatus ends.

As described above, the image processing apparatus according to the third embodiment has the character area determination unit 20 that performs the same character area detection processing as in the first embodiment for each character. Thereby, even if the background color differs for each character, the character can be detected reliably.

The present invention is not limited to the above embodiment, and various modifications are possible. For example, there are the following modifications.

(A) The equation for calculating the saturation S in the saturation calculator 3 is not limited to the equation (1). For example, the following (2),
Equation (3) may be used. S = (| r−g | + | r−b | + | g−b |) / 2 (2) S = ｛(r−g) ² + (r−b) ² + (g−b) ) ² ｝ ^1/2 ... (3)

(B) Instead of the saturation calculation section 3, a brightness calculation section for calculating the brightness L by the following equation (4) may be provided. L = (r + g + b) / 3 (4)

(C) The character area determination unit 10 in FIG. 1 sets eight pixels around the target pixel as the processing range as shown in FIG. The processing range may be used.

(D) For example, steps S7 to S in FIG.
In 12, the pixel of the intermediate region adjacent to the pixel of the character region is set as the target pixel, and when the color signal difference between the target pixel and the pixel of the character region is equal to or smaller than the threshold value, the region of the target pixel is changed to the character region. Like that. Conversely, the pixel of the intermediate region adjacent to the pixel of the background region is set as the target pixel, and when the color signal difference between the target pixel and the pixel of the background region is equal to or smaller than the threshold value, the region of the target pixel is set as the background region. It may be changed to.

(E) The character area determination units 10 and 20 are configured to output the binarized correction results for the character area and the background area, but output the pixels of the character area with lightness (gray image). You may do it. As a result, for example, a character recognition device that performs character recognition using an output signal of the image processing device may set a threshold value to improve recognition accuracy.

(F) In the character area determination section 20 in FIG.
Although the region is corrected by cutting out pixels in units of characters, the region may be corrected by cutting out a certain range of pixels regardless of the boundaries of characters.

(G) FIGS. 1 and 7 show FIGS.
Although it is composed of individual processing units having each processing function, it is common practice to actually perform processing by a program using a computer.

[0063]

As described above in detail, according to the first and second aspects of the present invention, pixels are classified into any of a character area, an intermediate area, and a background area based on saturation or brightness. Means for comparing a color signal of a pixel classified as an intermediate region with a color signal of a pixel in a character region or a background region existing within a predetermined range centered on the pixel and correcting the color signal into a character region or a background region It has a pixel area correction means. This allows the pixels in the middle area to be properly
It is possible to re-classify the character area or the background area, and the pixels of the character and the background can be reliably determined.

According to the third aspect, the pixel area correction means searches for pixels in the intermediate area that is continuous on the radiation in eight directions around the pixel of interest, and replaces the searched pixels in the intermediate area with the character area or the character area. The correction is made to the background area. Thereby, a similar effect can be obtained in a shorter time than in the second invention.

According to the fourth aspect, the pixel region correcting means corrects the pixels in the intermediate region to a character region or a background region for each pixel present in a certain range (for example, one character), and corrects the corrected character region. Until the line width meets the set conditions,
The correction process is repeated. This allows
Even in a form in which a plurality of background colors and character colors are mixed, it is possible to reliably determine the pixels of the characters and the background.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an image processing apparatus according to a first embodiment of the present invention.

FIG. 2 is an explanatory diagram of processing in an area classification unit 4 in FIG.

FIG. 3 is an explanatory diagram of a processing range in a character area determination unit 10 in FIG. 1;

FIG. 4 is a flowchart showing the operation of FIG.

FIG. 5 is a flowchart showing the operation of the second embodiment of the present invention.

FIG. 6 is an explanatory diagram of a process of step S9A in FIG. 5;

FIG. 7 is a configuration diagram of an image processing apparatus according to a third embodiment of the present invention.

FIG. 8 is a flowchart showing the operation of FIG. 7;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Photoelectric conversion part 2 Color image memory 3 Saturation calculation part 4 Area classification part 10, 20 Character area judgment part 11, 21 Image memory 12, 25 Intermediate area detection part 13, 26 Area correction part 22 Character extraction part 23 Pattern Memory 24 Line width calculator

Continued on front page F-term (reference) 5B057 CA01 CA08 CA12 CA16 CB01 CB08 CB12 CB16 CC02 CE11 CE17 DA08 DB02 DB06 DB09 DC25 5C077 LL19 MP08 PP27 PP35 5C079 HB01 HB06 LA01 LA06 LA34 MA11 NA11 NA29

Claims (4)

[Claims] 1. A pixel information calculating means for calculating saturation or brightness of each pixel based on a color signal of a red component, a green component and a blue component of a pixel constituting an image, and the pixel information calculating means calculates the saturation or brightness of each pixel. A pixel region classification unit that classifies each pixel into a character region, an intermediate region, or a background region based on the saturation or brightness, and a color signal of the pixel classified into the intermediate region by the pixel region classification unit. A pixel area correction for correcting the area of the pixel classified as the intermediate area into a character area or a background area by comparing with a color signal of a pixel in a character area or a background area existing within a predetermined range around the pixel. And an image processing device. 2. The pixel area correcting means sets a window of m × n (where m and n are plural) pixels around the pixel of interest with the pixel of the intermediate area as a pixel of interest. When there is a pixel in the character area, the process of comparing the color signal of the pixel of the character area with the color signal of the pixel of interest and correcting the area of the pixel of interest to the character area when the difference is equal to or less than the threshold value is corrected. 2. The image processing apparatus according to claim 1, wherein the processing is repeatedly performed sequentially until there are no more pixels in the intermediate area. 3. The pixel area correction unit searches for a pixel in an intermediate area that is continuous on radiation in eight directions around the pixel of interest using a pixel in an intermediate area adjacent to a pixel in a character area as a pixel of interest, The color signals of the searched pixel of the intermediate region and the pixel of interest and the pixel of the character region adjacent to the pixel of interest are compared, and when the difference is equal to or less than the threshold value, the region of the pixel of interest and the pixel of the searched intermediate region is compared. 2. The image processing apparatus according to claim 1, wherein the processing of correcting the image data into a character area is sequentially performed. 4. The pixel area correcting means sets m × n (where m and n are plural) pixels centered on the pixel of interest with a pixel of the intermediate area as a pixel of interest for each pixel existing within a certain range. When a pixel of the character area is present in the window, the pixel of the character area is compared with the color signal of the pixel of interest. When the difference is equal to or less than the threshold, the area of the pixel of interest is 2. The image according to claim 1, wherein the processing for correcting the area and calculating the line width of the corrected character area is sequentially and repeatedly performed until the calculated line width satisfies a preset condition. Processing equipment.