JP2020088734A - Image processing apparatus, image processing method and program - Google Patents

Abstract

To correct the determination result of an image attribute with high accuracy.SOLUTION: An image processing apparatus includes: a character determination unit which determines whether or not a pixel included in an input image is a character pixel; a color determination unit which determines whether or not the pixel included in the input image is a chromatic pixel or an achromatic pixel; an extraction unit which extracts a plurality of character regions including a character composed of the character pixel; and an execution determination unit which determines whether or not to execute correction processing which corrects a character pixel, which is the chromatic pixel and included in a first character region among the plurality of character regions, to the achromatic pixel, based on region information which indicates whether a character pixel included in a second character region, which is included in the plurality of character regions, is the chromatic pixel or the achromatic pixel.SELECTED DRAWING: Figure 3

Description

The present invention relates to an image processing device, an image processing method, and a program.

Normally, by adaptively determining for each pixel (pixel block) of an image read from a document, etc., whether it is a black character, a color character, or a pattern, and performing image processing and compression processing suitable for each. There is known a multi-function peripheral (MFP) that generates a highly compressed PDF that can be stored in a higher compression than a PDF (Portable Document Format).

Further, there has been proposed a technique for detecting an erroneous determination and correcting it to a correct determination result even when an erroneous determination occurs due to color misregistration caused by scanner reading or the like.

However, in the related art, an erroneous determination due to a color shift or the like cannot be correctly detected, and an erroneous determination result may not be corrected. As a result, appropriate processing (image processing, compression processing, etc.) depending on the image attribute may not be performed, and the image quality may be deteriorated.

The present invention has been made in view of the above, and an object thereof is to make it possible to correct the determination result of the attribute of an image with higher accuracy.

In order to solve the above-described problems and achieve the object, the present invention provides a character determination unit that determines whether or not a pixel included in an input image is a character pixel, and a pixel included in the input image is a chromatic pixel. Included in the first character region of the plurality of character regions, a color determination unit that determines whether the pixel is an achromatic pixel or an achromatic pixel, an extraction unit that extracts a plurality of character regions including a character composed of character pixels, Whether or not to perform correction processing for correcting a character pixel that is a chromatic pixel to an achromatic pixel is determined by determining whether a character pixel included in a second character area included in a plurality of character areas is a chromatic pixel or an achromatic pixel. And an execution determination unit that determines based on the area information indicating whether or not

According to the present invention, there is an effect that the determination result of the image attribute can be corrected with higher accuracy.

FIG. 1 is a block diagram showing an example of the functional configuration of the image processing apparatus of this embodiment. FIG. 2 is a block diagram showing an example of the functional configuration of the image area separation unit. FIG. 3 is a block diagram showing an example of the functional configuration of the image correction unit. FIG. 4 is a flowchart showing an example of a black character conversion process in this embodiment. FIG. 5 is a diagram for explaining a specific example of the determination process for determining whether to perform the black character conversion process. FIG. 6 is a diagram for explaining a specific example of the determination process for determining whether to perform the black character conversion process. FIG. 7 is a diagram showing an example of image data, a character determination result, and a color determination result for a character area. FIG. 8 is a diagram for explaining a specific example of the character area after the black characterization processing is performed. FIG. 9 is a diagram for explaining a specific example of the input image after the black character conversion process is performed. FIG. 10 is a block diagram showing a hardware configuration example of the image processing apparatus.

An embodiment of an image processing device, an image processing method, and a program according to the present invention will be described in detail below with reference to the accompanying drawings.

An example in which the image processing apparatus of the present invention is applied to a digital color image processing apparatus having a scanner function and a printer function will be described below, but the applicable apparatus is not limited to this. Any device may be used as long as it is an image processing device that processes a color image. For example, the image processing apparatus of the present invention can be used as an image processing apparatus such as a multifunction peripheral, a copying machine, a printer, a scanner apparatus, and a facsimile apparatus having at least two functions of a copy function, a printer function, a scanner function, and a facsimile function. Can also be applied.

As described above, the attribute of the image may be erroneously determined due to the color shift caused by the scanner reading or the like. In particular, fine black characters included in a print document, a copy document, and the like often have noticeable misregistration due to a plotter that generates the document. In addition, depending on the scanning method, color misregistration is likely to occur even during scanning, and erroneous determination tends to occur as a whole.

The image processing apparatus of this embodiment corrects the attribute of an image that has been erroneously determined to a correct determination result. As a result, the color reproducibility of characters can be improved and the deterioration of image quality can be suppressed. Further, when correcting the determination result, the determination results of not only the determination target region but also other regions (regions near this region, etc.) are referred to. This makes it possible to perform the correction with higher accuracy.

FIG. 1 is a block diagram showing an example of the functional configuration of the image processing apparatus of this embodiment. As shown in FIG. 1, the image processing apparatus 100 includes a scanner 1, an image processing unit 2, an HDD (hard disk drive) 3, a plotter 4, and a compression processing unit 5.

The scanner 1 reads image data from a document and sends the read image data to the image processing unit 2.

The image processing unit 2 performs image processing on the image data read by the scanner 1. The image processing unit 2 includes a gamma correction unit 21, an image area separation unit 22, a data interface unit 23, a color processing/UCR (Under Color Removal) unit 24, and a printer correction unit 25.

The gamma correction unit 21 performs a one-dimensional conversion (gamma correction) on the data read by the scanner 1 (for example, an 8-bit signal for each color of R, G, and B after analog-digital conversion) so as to adjust the gradation balance for each color. Process). A density linear signal (RGB signal: a signal value indicating white is 0) which is a converted signal is sent to the image area separation unit 22 and the data interface unit 23.

The image area separation unit 22 separates the input image data (input image) into a plurality of areas corresponding to a plurality of attributes. For example, the image area separation unit 22 determines, for each pixel of the image data, a character determination result (comprehensive determination result) X1 indicating “character” or “non-character”, and “chromatic” and “achromatic”. The color determination result X2 indicating which of the two is output. Details of the image area separation unit 22 will be described later.

The character determination result being “character” means that the pixel is a pixel forming a character, for example. Since it is determined independently of the determination of color, both chromatic characters and achromatic characters are determined as "characters". The chromatic character indicates a character mainly represented by chromatic color (for example, a color character). The achromatic character indicates a character mainly represented by an achromatic color (for example, a black character). The character determination result being “non-character” means that the pixel is, for example, a pixel forming a character other than a character such as a photograph. Below, a chromatic character and an achromatic character may be called a color character and a black character, respectively.

The unit for outputting the determination result may be one pixel or a pixel block including a plurality of pixels. The following mainly describes an example in which the determination result is output on a pixel-by-pixel basis.

The data interface unit 23 is an interface for temporarily storing the determination results X1 and X2 output from the image area separation unit 22 and the image data (density linear signal) output from the gamma correction unit 21 in the HDD 3. Further, the data interface unit 23 outputs the image data after gamma correction and the determination results X1 and X2 from the image area separation unit 22 to the color processing/UCR unit 24.

The color processing/UCR unit 24 selects and executes color processing and UCR processing based on the determination results X1 and X2 for each pixel. For example, the color processing/UCR unit 24 converts each 8-bit RGB signal into an image signal (each 8 bits of C, M, Y, Bk) which is a control signal of the plotter 4 based on a predetermined conversion formula, and outputs the image signal. ..

The printer correction unit 25 performs gamma correction processing and dither processing (pseudo halftone processing) that reflects the gradation characteristics of the plotter 4 on the C, M, Y, and Bk image signals, and outputs them to the plotter 4.

The plotter 4 is a transfer printing unit that transfers the image data output from the image processing unit 2.

The compression processing unit 5 receives the determination results X1 and X2 from the image area separation unit 22 temporarily stored in the HDD 3 and the image data after the gamma correction unit 21, and creates data for high compression PDF. The compression processing unit 5 includes an ACS (Auto Color Selection) processing unit 51, an image correction unit 52, and an image compression unit 53.

The ACS processing unit 51 determines whether the input image to the compression processing unit 5 is a color image or a grayscale image. The ACS processing unit 51 outputs the determination result of whether the image is a color image or a gray scale to the image correction unit 52.

The image correction unit 52 corrects the attribute determination result (character determination result X1, color determination result X2) of the input image. For example, when the image correction unit 52 receives a determination result indicating that the image is a color image from the ACS processing unit 51, the image correction unit 52 corrects the determination result of the attribute of the input image. Details of the image correction unit 52 will be described later.

The image compression unit 53 executes image compression processing suitable for the image attribute based on the determination result output from the image correction unit 52. The compression process applied to each attribute can be designated by the user from compression processes prepared in advance such as JPEG (Joint Photographic Experts Group).

Next, the functional configuration of the image area separation unit 22 will be described. FIG. 2 is a block diagram showing an example of the functional configuration of the image area separation unit 22. As described above, the input image (RGB data) read by the scanner 1 is corrected by the gamma correction unit 21 and input to the image area separation unit 22.

As shown in FIG. 2, the image area separation unit 22 includes a character determination unit 221 and a color determination unit 222.

The character determination unit 221 determines whether the pixel of interest of the image data is a character pixel or a non-character pixel (that is, a pattern), and outputs the determination result X1.

The character determination unit 221 includes an edge detection circuit 2211, a white background detection circuit 2212, a halftone dot detection circuit 2213, and a comprehensive determination circuit 2214.

The edge detection circuit 2211 performs edge determination (determination based on the continuity of white pixels and black pixels) on the density linear signal (G) after gamma correction to detect the edge of the line drawing candidate, and the result ( Hereinafter, the “edge detection result”) is output to the comprehensive determination circuit 2214. The edge detection circuit 2211 uses line continuity and patterns of black pixels and white pixels obtained by ternarization of the input image signal, for example, to separate a line drawing such as a character from a halftone dot, thereby selecting a line drawing candidate. Detect edges that make up. The output of the edge detection circuit 2211 is 1 bit per pixel, and the detected edge area pixel is activated.

The white background detection circuit 2212 determines whether the density linear signal (G) after gamma correction is a white background or a non-white background, and outputs the result to the comprehensive determination circuit 2214. The white background detection circuit 2212, for example, binarizes the input image signal with a predetermined threshold value to divide the input image signal into white pixels and black pixels. judge. At this time, the white background detection circuit 2212 controls the sizes of the reference regions on the left, right, top, and bottom to determine that the character edge portion having a desired line width or less is a white background, and the character edge portion exceeding the desired line width is a non-white background. It can be determined as a white background. The output of the white background detection circuit 2212 makes the white background active.

The halftone dot detection circuit 2213 determines a halftone dot for each pixel of the density linear signal (G) after gamma correction (determines by a repeating pattern of peak/valley peak pixels in the image), and comprehensively determines the result. It is output to the circuit 2214. The output of the halftone dot detection circuit 2213 activates the halftone dot area.

When the target pixel is active in the edge detection circuit 2211, active in the white background detection circuit 2212, and inactive in the halftone dot detection circuit 2213, the comprehensive determination circuit 2214 determines the determination result X1 that the target pixel is a character pixel. Output.

The color determination unit 222 includes a color determination circuit 2221. The color determination circuit 2221 determines whether the pixel of interest is a chromatic color (chromatic pixel) or an achromatic color (achromatic pixel) for the density linear signal (R, G, B) after gamma correction. The color determination circuit 2221 determines, for example, a pixel corresponding to Max(|RG|, |GB|, |BR|)>th (th is a predetermined threshold value) as a chromatic pixel, The determination result X2 indicating that the pixel is a color pixel is output.

At least one of the character determination unit 221 and the color determination unit 222 may change the determination standard (determination method) according to the use of the data after the image area separation. For example, when the high compression PDF is created as described above, the character determination unit 221 and the color determination unit 222 can be mounted so as to use the determination standard specialized for the high compression PDF. At this time, when the processing result of the image area separation unit 22 is also used for a purpose other than the high compression PDF, the character determination unit 221 and the color determination are performed so that a determination criterion (different from the high compression PDF) suitable for the use is used. The section 222 may be mounted.

Next, the functional configuration of the image correction unit 52 will be described. FIG. 3 is a block diagram showing an example of the functional configuration of the image correction unit 52. As shown in FIG. 3, the image correction unit 52 includes an extraction unit 521 and a black character conversion processing unit 522.

An input image (RGB data), a character determination result X1 and a color determination result X2 are input to the extraction unit 521. The input image (RGB data) may be the image data itself output from the HDD 3 or the image data further corrected in the compression processing unit 5. The same applies to the character determination result X1 and the color determination result X2, which may be the determination result itself output from the image area separation unit 22 or the determination result corrected in the compression processing unit 5. ..

The extraction unit 521 extracts a character area including a character composed of character pixels. For example, the extraction unit 521 calculates a luminance signal from the input image (RGB data), and extracts the character region using the binarized image created from the luminance signal and the character determination result X1. The shape of the character area is, for example, a rectangle, but the shape is not limited to this. For example, the extraction unit 521 may extract a character area having a shape other than a rectangle. The extraction unit 521 adds information for identifying the character area to the extracted character area (numbering).

The black text conversion processing unit 522 includes an implementation determination unit 5221, an implementation unit 5222, and a storage unit 5223.

The implementation determination unit 5221 determines whether or not to perform a correction process of correcting a pixel that is a chromatic pixel included in the character region (first character region) and that is a character pixel into an achromatic pixel. In the following, an example will be described in which the correction process is a process of converting a chromatic pixel into a black pixel to convert a character into a black character (black character conversion process).

For example, the implementation determination unit 5221 determines, for each of the character regions extracted by the extraction unit 521, whether or not the character region is a region to be subjected to black character conversion processing, the input image (RGB data), the color determination result X2, and The determination is performed using the area information of another character area (second character area).

The area information is information indicating whether the character pixel included in the character area is a chromatic pixel or an achromatic pixel. For example, the area information is information indicating whether the character in the character area is a “color character” or a “black character”.

The implementation determination unit 5221 is an area that indicates whether the characters included in the character area are “colored characters” or “black characters” for all the character areas regardless of whether to perform the black character conversion process. Information is obtained, and the obtained area information is stored in, for example, the storage unit 5223. In this way, the area information of each character area is stored in the storage unit 5223.

The other character area is a character area that is a target of determination before the currently determined character area. For example, the implementation determination unit 5221 can read the region information of the character region whose position on the image is closest to the currently determined character region from the already determined character regions from the storage unit 5223 and use it for the determination.

The implementation unit 5222 performs the black character conversion process on the character area determined by the implementation determination unit 5221 to perform the black character conversion process. The color determination result X2 input to the image correction unit 52 is updated and output by the execution unit 5222 for the pixels subjected to the black character conversion process.

On the other hand, if the execution determination unit 5221 determines that the character area does not need to be blackened, the blackening processing is not performed. Therefore, the input color determination result X2 is not updated for the pixels in the character area, and is output in the same state as at the time of input.

The storage unit 5223 stores area information and the like of each character area. The storage unit 5223 stores the area information of the character area for all the character areas regardless of whether the black characterization processing is performed by the implementation unit 5222. The stored area information is input to the execution determination unit 5221 and is used to determine whether or not to perform the black character conversion process on another character area after the character area. Note that the storage unit 5223 can be configured by any commonly used storage medium such as a flash memory and a RAM (Random Access Memory).

Next, the black character conversion processing by the image processing apparatus 100 according to the present embodiment configured as described above will be described. FIG. 4 is a flowchart showing an example of a black character conversion process in this embodiment.

The black character conversion process is started when the input image (RGB data), the character determination result X1, and the color determination result X2 are input to the image correction unit 52.

First, the extraction unit 521 extracts a character region using the binarized image created from the input image (RGB data) and the character determination result X1 (step S101). The extraction unit 521 performs numbering on the extracted character area (step S102). For example, the extraction unit 521 uses the upper left pixel of each character area as a reference pixel, and numbers each character area with a number according to the scan order of the reference pixel when raster scanning is performed. Note that the numbering method is not limited to this, and any method may be used as long as the information for identifying the character area can be added. The processing order of the character areas is not limited to the above example, and may be any order.

The implementation determination unit 5221 determines one character region as a determination target according to the numbering order, and determines whether to perform the black character conversion process on the character region (step S103). The details of this determination processing will be described later.

When it is determined that the black character conversion process is performed (step S103: Yes), the implementation unit 5222 performs the black character conversion process on the character area (step S104). The details of the black character conversion process will be described later.

After performing the black characterizing process, or when it is determined that the black characterizing process is not performed (step S103: No), the implementation determination unit 5221 calculates the region information of the character region (step S105). In this way, the region information is implemented regardless of the determination result of whether or not to perform the black character conversion process. For example, the implementation determination unit 5221 counts the color character pixels and the black character pixels in the character area. The execution determination unit 5221 compares both count results, and if the number of color character pixels is large, the result is “color character”, and if the number of black character pixels is large, “black character” is used as the area information of the character area. calculate. Since all the character pixels are black character pixels when the black character conversion processing is performed, the implementation determination unit 5221 calculates the area information that the character area is “black character” without counting the number of pixels. You may.

The execution determination unit 5221 stores the calculated area information in the storage unit 5223 (step S106). For example, the implementation determination unit 5221 generates area information in which information indicating whether the character area is “colored character” or “black character” and information identifying the character area (for example, a numbered number) are associated with each other. It is stored in the storage unit 5223.

The execution determination unit 5221 determines whether or not all the character areas have been referenced (step S107). When all the character areas are not referenced (step S107: No), the process returns to step S103 and the process is repeated for the next character area. If all the character areas have been referenced (step S107: Yes), the black character conversion process ends.

Next, a specific example of the determination process of determining whether or not to perform the black character conversion process of step S103 will be described. 5 and 6 are diagrams for explaining a specific example of the determination process for determining whether to perform the black character conversion process.

FIG. 5 is a diagram showing an example of the input image. “A” and “I” are examples of black letters. “A” and “A” are examples of color letters. “A” is an example of a character in which a color misregistration has occurred due to a misregistration caused by a plotter or an abnormality when reading a scanner.

When an input image as shown in FIG. 5 is input, the extraction unit 521 extracts character regions (step S101), and numbering is performed on each character region (step S102). In FIG. 6, for convenience of description, a rectangle indicating the extracted character area and a number (No. 1 to No. 5) given to each character area are shown.

In the following, No. 1 in FIG. An example in which the determination process (step S103) is performed by using the character region 5 as the character region to be processed will be described.

The implementation determination unit 5221 determines whether to perform the black character conversion process, for example, according to the following determination conditions (C1) to (C4). However, the judgment conditions are not limited to four, and may be increased or decreased.
(C1) Whether the size (size) of the character area is less than the size threshold (th_size) (C2) The number of color character pixels (cnt_color) in the character area is less than or equal to the threshold value (th_color) of the number of color characters Whether or not (C3) whether or not the number of black character pixels (cnt_black) in the character area is greater than or equal to the threshold value (th_black) of the number of black character pixels (C4) whether or not the neighboring character area is “black character”

Each condition will be described below. 7 is the same as No. 1 in FIG. It is a figure which shows the example of the image data RGB, the character determination result X1, and the color determination result X2 with respect to the character area of 5. A small rectangle corresponds to one pixel. A rectangular area including each pixel corresponds to a character area. For convenience of description, a portion where the shape of the character and the color of the character do not match is included between FIG. 6 and FIG. 7. Further, the character determination result X1 and the color determination result X2 are represented by binary values, but in FIG. 7, for convenience of description, they are represented by binary values due to the difference in hatching. The actual determination result is represented by, for example, a binary value of “0” or “1” as in the case of indicating whether it is white or black.

The size (size) of the character area (C1) indicates the number of pixels included in the character area. In the example of FIG. 7, the size is 60 pixels because it corresponds to the number of pixels in the character area. The implementation determination unit 5221 confirms whether or not the size (size) is less than the threshold value (th_size) as shown in the following expressions (1) and (2).
size<th_size (1)
size≧th_size (2)

If the size (size) is less than the threshold value (th_size) as in the formula (1), it is true, and if the size is equal to or larger than the threshold (th_size) as in the formula (2), it is false. The threshold value (th_size) may be a fixed value, or may be switched according to predetermined determination information (factor) such as the resolution of the input image (input resolution).

In (C2), the implementation determination unit 5221 uses the number of color character pixels (cnt_color) in the character area. The color character pixel is a pixel whose character determination result X1 indicates a character pixel and whose color determination result X2 indicates a chromatic pixel. In the example of FIG. 7, the number of color character pixels is 5 pixels. The implementation determination unit 5221 confirms whether or not the number of color character pixels (cnt_color) is equal to or less than a threshold value (th_color), as shown in the following expressions (3) and (4).
cnt_color≦th_color (3)
cnt_color>th_color (4)

True if the number (cnt_color) of color character pixels in the character area is equal to or smaller than the threshold value (th_color) as in Expression (3), and false if the value is larger than the threshold value (th_color) as in Expression (4). Becomes The threshold value (th_color) may be a fixed value, or may be switched according to predetermined determination information (factor) such as one or both of the input resolution and the character area.

In (C3), the implementation determination unit 5221 uses the number of black character pixels (cnt_black) in the character area. The black character pixels are pixels in which the character determination result X1 indicates a character pixel and the color determination result X2 indicates an achromatic pixel. In the example of FIG. 7, the number of black character pixels is 21 pixels. The execution determination unit 5221 confirms whether or not the number of black character pixels (cnt_black) is equal to or larger than a threshold value (th_black), as shown in the following expressions (5) and (6).
cnt_black≧th_black (5)
cnt_black<th_black (6)

It becomes true when the number of black character pixels (cnt_black) in the character area is equal to or larger than the threshold value (th_black) as in Expression (5), and false when the number is less than the threshold value (th_black) as in Expression (6). The threshold value (th_black) may be a fixed value, or may be switched according to predetermined determination information (factor) such as one or both of the input resolution and the character area.

In (C4), the implementation determination unit 5221 confirms whether the character area near the character area is a black character. The neighboring character area indicates, for example, a character area that is the closest to the character area among the character areas that have already been processed before the character area. For the character area group before the character area that has already been processed, in step S106, either "color character" or "black character" is stored in the storage unit 5223 as area information. The implementation determination unit 5221 confirms whether the area information of the character area near the character area is “black character”. If it is "black character", it is true, and if it is a color character, it is false.

The execution determination unit 5221 calculates the logical product of the determination results of each of the above four conditions, and when the calculation result is true, determines to perform the black character conversion process. When it is false, it is determined that the black character conversion process is not performed.

Next, a specific example of the black character conversion processing in step S104 will be described. 8 and 9 are diagrams for explaining specific examples of the character area and the input image after the black characterization processing is performed.

The implementation unit 5222 performs the black character conversion process only on the character area determined to be the black character conversion process. In the black character conversion process, all the color character pixels in the character area are corrected (converted) into black character pixels. For example, when a character area as shown in FIG. 7 is to be subjected to the black character conversion processing, the color character pixel is corrected to the black character pixel by the black character conversion processing, and the result becomes as shown in FIG. FIG. 9 shows an example of an image after the black characterizing process is performed on the character area in FIG. As shown in FIG. The color misregistration of the character area 5 is corrected.

As described above, according to the present embodiment, the attribute (whether it is a black character, a color character, or the like) of another area such as an area near the area is referred to in addition to the area to be determined. The attribute of the area can be corrected. This makes it possible to perform the correction with higher accuracy. Further, since the attribute determination result can be corrected with high accuracy, more appropriate processing (image processing, compression processing, etc.) according to the attribute of the image can be executed, and deterioration of the image quality can be suppressed.

FIG. 10 is a block diagram showing a hardware configuration example of the image processing apparatus 100. The image processing apparatus 100 described in the above-described embodiment includes a controller 210, an operation panel 220, an FCU (Facsimile Control Unit) 230, a USB (Universal Serial Bus) device 240, and an MLB as illustrated in FIG. 10, for example. A (Media Link Board) 250, a scanner 1, and a plotter 4 are provided.

The operation panel 220 is a user interface that allows the user of the image processing apparatus 100 to input various settings and display various information presented to the user.

The FCU 230 is a control unit that controls the facsimile function of the image processing apparatus 100. The USB device 240 is a device connected to the image processing apparatus 100 by USB. The MLB 250 is a conversion board that converts the format of image data. The scanner 1 is an engine for reading a document, and the plotter 4 is an engine for printing. The image to be processed can be acquired by reading the document with the scanner 1.

The controller 210 is a control device that controls the operation of the image processing apparatus 100. As shown in FIG. 10, the controller 210 includes a CPU (Central Processing Unit) 211, a system memory 212, an HDD 3, a PHY (Physical Layer: a physical layer of a communication system circuit) 214, and an ASIC (Application Specific Integrated Circuit). 215 and. The operation panel 220 is connected to the ASIC 215 of the controller 210. Further, the FCU 230, the USB device 240, the MLB 250, the scanner 1 and the plotter 4 are connected to the ASIC 215 of the controller 210 via the data transfer bus 280.

In the image processing apparatus 100 described in the embodiment, some or all of the functional components of the image processing apparatus described above are mainly realized by the controller 210. That is, of the functional components described in the embodiment, the image processing unit 2 is realized by, for example, the ASIC 215 of the controller 210. Further, the compression processing unit 5 is realized, for example, by the CPU 211 of the controller 210 using the system memory 212 to execute a predetermined program (software).

The program is recorded in a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD as a file in a format that can be installed in the image processing apparatus 100 or an executable format. Provided. The program may be stored in a computer connected to a network such as the Internet and provided by being downloaded to the image processing apparatus 100 via the network. Further, the above program may be configured to be provided or distributed via a network such as the Internet. Further, the above program may be provided by being incorporated in the system memory 212 or the HDD 3 in the image processing apparatus 100 in advance.

Further, in the above-described embodiment, an example in which the image processing apparatus 100 is realized as a single apparatus is assumed, but the functional constituent elements of the image processing apparatus 100 are distributed and provided in a plurality of physically separated apparatuses. The operation of the image processing apparatus 100 may be realized by the cooperation of these plural apparatuses.

1 Scanner 2 Image Processing Unit 3 HDD
4 Plotter 5 Compression Processing Unit 21 Gamma Correction Unit 22 Image Area Separation Unit 23 Data Interface Unit 24 Color Processing/UCR Unit 25 Printer Correction Unit 51 ACS Processing Unit 52 Image Correction Unit 53 Image Compression Unit 100 Image Processing Device 210 Controller 211 CPU
212 system memory 215 ASIC
220 Operation panel 221 Character determination unit 222 Color determination unit 230 FCU
240 USB device 250 MLB
280 data transfer bus 521 extraction unit 522 black character conversion processing unit 2211 edge detection circuit 2212 white background detection circuit 2213 halftone dot detection circuit 2214 comprehensive determination circuit 2221 color determination circuit 5221 execution determination unit 5222 execution unit 5223 storage unit

JP 2001-309189 A

Claims (9)

A character determination unit that determines whether or not the pixels included in the input image are character pixels,
A color determination unit that determines whether the pixels included in the input image are chromatic pixels or achromatic pixels;
An extraction unit for extracting a plurality of character regions including a character composed of the character pixels,
A second character area included in the plurality of character areas determines whether to perform a correction process for correcting a character pixel that is a chromatic pixel included in the first character area of the plurality of character areas into an achromatic pixel. An execution determination unit that determines based on area information indicating whether the character pixel included in is a chromatic pixel or an achromatic pixel,
An image processing apparatus including. The area information indicates whether the character included in the character area is a chromatic character represented by a chromatic color or an achromatic character represented by an achromatic color,
Further comprising a storage unit that stores the area information for each of the character areas,
The execution determination unit determines whether to perform the correction process based on the area information of the second character area stored in the storage unit,
The image processing apparatus according to claim 1. The implementation determination unit determines the size of the first character region, the number of the character pixels determined to be the chromatic pixel among the character pixels included in the first character region, and the first character region. Whether to perform the correction process based on at least one of the number of the character pixels determined to be the achromatic pixel among the included character pixels and the area information of the second character area Judge,
The image processing apparatus according to claim 1. The implementation determination unit determines whether to perform the correction process based on a comparison result obtained by comparing the size of the first character region with a threshold value and the region information of the second character region. ,
The threshold value is changed according to predetermined determination information including the resolution of the input image,
The image processing apparatus according to claim 1. The execution determination unit compares the number of the character pixels determined to be the chromatic pixels among the character pixels included in the first character area with a threshold value, and the area of the second character area. Based on the information, it is determined whether to perform the correction process,
The threshold value is changed according to predetermined determination information including at least one of the resolution of the input image and the size of the first character area,
The image processing apparatus according to claim 1. The execution determination unit compares the number of the character pixels determined to be the achromatic pixels among the character pixels included in the first character area with a threshold value, and the area of the second character area. Based on the information, it is determined whether to perform the correction process,
The threshold value is changed according to predetermined determination information including at least one of the resolution of the input image and the size of the first character area,
The image processing apparatus according to claim 1. Further comprising an execution unit that performs the correction process on the first character area determined to perform the correction process,
The image processing apparatus according to claim 1. A character determination step of determining whether or not the pixels included in the input image are character pixels,
A color determination step of determining whether the pixels included in the input image are chromatic pixels or achromatic pixels;
An extraction step of extracting a plurality of character areas including a character composed of the character pixels;
A second character area included in the plurality of character areas determines whether to perform a correction process for correcting a character pixel that is a chromatic pixel included in the first character area of the plurality of character areas into an achromatic pixel. An execution determination step of determining based on area information indicating whether the character pixel included in is a chromatic pixel or an achromatic pixel,
An image processing method including. Computer,
A character determination unit that determines whether or not the pixels included in the input image are character pixels,
A color determination unit that determines whether the pixels included in the input image are chromatic pixels or achromatic pixels;
An extraction unit for extracting a plurality of character regions including a character composed of the character pixels,
A second character area included in the plurality of character areas determines whether to perform a correction process for correcting a character pixel that is a chromatic pixel included in the first character area of the plurality of character areas into an achromatic pixel. An execution determination unit that determines based on area information indicating whether the character pixel included in is a chromatic pixel or an achromatic pixel,
Program to function as.

Images