JP2012008914A - Image processing device and image processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing device and an image processing program capable of obtaining a binary image in which missing of information expressed by color differences in an image to be processed is reduced.SOLUTION: A limited color image generation unit 11 generates a limited color image by limiting colors used in an image to be processed to plural main colors. A binary image generation unit 12 binarizes the image to be processed to generate a binary image. A color boundary extraction unit 13 extracts a color boundary between adjacent main colors which are different in the limited color image generated by the limited color image generation unit 11, both of the adjacent main colors being converted into either one value in the binary image generated by the binary image generation unit 12. A determination unit 14 determines which side of the color boundary is to be corrected based on the main colors constituting the color boundary extracted by the color boundary extraction unit 13 and features about the regions of the main colors, and a correction unit 15 corrects values of the binary image on the determined side.

Description

  The present invention relates to an image processing apparatus and an image processing program.

  Conventionally, for example, when a color image is output by a monochrome printer or when the data amount is reduced and stored, the color image is converted into a binary image. When a color image is simply converted to a binary image by brightness, for example, when a color character exists in a background color with a different hue, the character and background are both converted to one of the binary values. The distinction is lost.

  For example, in Patent Document 1, luminance correction is performed for a specific area such as a character and a peripheral area such as a background based on the luminance information of a color image to obtain a monochrome image. In this case, when a certain color is used for the character and the background, if one color is output, either one is not reflected in the binary image. In addition, it is obtained by expanding from the boundary of the character area as a specific area, and in order to correct the luminance of the specific area or the peripheral area, a collapse occurs when it has a complicated image line.

  For example, in Patent Document 2, when a density difference is included in a predetermined range when making a single color, a boundary line is generated to separate the regions. For example, also in Patent Document 3, a binary image is obtained by synthesizing a binarized image and an image of a boundary line by exclusive OR.

JP 2006-121684 A JP 2008-005065 A Japanese Patent Laid-Open No. 11-205617

  An object of the present invention is to provide an image processing apparatus and an image processing program capable of obtaining a binary image in which loss of information expressed by a color difference in a processing target image is reduced. .

  According to the first aspect of the present invention, limited color image generation means for generating a limited color image in which colors used in the image to be processed are limited to a plurality of main colors, and binarization by binarizing the image. A binary image generating unit that generates a value image and a color boundary in which different primary colors are adjacent to each other in the limited color image but are converted to one of the adjacent primary colors in the binary image are extracted. Color boundary extraction means; determination means for determining which side of the color boundary is to be corrected based on features relating to the primary color and the area of the primary color that constitutes the color boundary; and the color boundary of the binary image An image processing apparatus comprising correction means for correcting a value determined by the determination means.

  According to the second aspect of the present invention, a limited color image generating unit that generates a limited color image in which colors used in a processing target image are limited to a plurality of main colors, and the limited color image is converted into the main color. Or a binary image generating means for generating a binary image by binarizing according to an adjacent relationship between the primary color region or the primary color and another primary color, and different primary colors are adjacent to each other in the limited color image. In the binary image, the color boundary extraction means for extracting a color boundary that has been converted to one of the values of the adjacent main color, and the color from the characteristics relating to the main color constituting the color boundary and the area of the main color An image processing apparatus comprising: a determination unit that determines which side of the boundary is to be corrected; and a correction unit that corrects a value determined by the determination unit of the color boundary in the binary image. It is.

  In the invention according to claim 3 of the present application, the color boundary extraction means in the invention according to claim 1 or 2 of the present application extracts the color boundary for each combination of the main colors from the entire limited color image. In the image processing apparatus, the determination unit determines which of the main color combinations to be corrected for each of the main color combinations.

  According to a fourth aspect of the present invention, in the invention according to any one of the first to third aspects of the present invention, the deciding means according to any one of the first to third aspects of the present invention determines which of the color boundaries according to the region of the primary color constituting the color boundary. It is an image processing apparatus that determines whether to correct the side of the image.

  An invention according to claim 5 of the present application is an image processing program for causing a computer to execute the function of the image processing apparatus according to any one of claims 1 to 4.

  According to the invention described in claim 1 of the present application, it is possible to obtain a binary image in which a lack of information expressed by a color difference is reduced in an image to be processed compared to a case where the present configuration is not provided. There is an effect.

  According to the invention described in claim 2 of the present application, it is possible to obtain a binary image in which the lack of information expressed by the difference in color in the image to be processed is reduced as compared with the case where the present configuration is not provided. There is an effect.

  According to the third aspect of the present invention, unified binarization processing can be performed on the entire image.

  According to the invention described in claim 4 of the present application, it is possible to correct an appropriate side of the color boundary that is present in the image to be processed but is missing as compared with the case where the present configuration is not provided.

  According to the invention of claim 5 of the present application, the effect of the invention of any one of claims 1 to 4 can be obtained.

It is a block diagram which shows the 1st Embodiment of this invention. It is explanatory drawing of the specific example of the process in the 1st Embodiment of this invention. It is explanatory drawing of an example which correct | amends one side of the color boundary in a complicated figure. It is explanatory drawing of an example of a comprehensiveness. It is a block diagram which shows the 2nd Embodiment of this invention. It is explanatory drawing of the specific example of the process in the 2nd Embodiment of this invention. FIG. 15 is an explanatory diagram of an example of a computer program, a storage medium storing the computer program, and a computer when the functions described in the embodiments of the present invention are realized by the computer program.

  FIG. 1 is a block diagram showing a first embodiment of the present invention. In the figure, 11 is a limited color image generation unit, 12 is a binary image generation unit, 13 is a color boundary extraction unit, 14 is a determination unit, and 15 is a correction unit. The limited color image generation unit 11 generates a limited color image in which colors used in the processing target image are limited to a plurality of main colors. A known method may be used as a method for generating the limited color image. For example, the color used in the image to be processed is analyzed in the color space, and the main color is extracted by, for example, a color histogram or clustering. Replace it with k. Alternatively, for example, a limited color image may be generated by performing region division by contour tracking and extracting the main color in each region and converting the color of each region into the main color. Of course, other methods may be used.

  The binary image generation unit 12 binarizes the image to be processed and generates a binary image. A known method may be used as the binarization method. For example, the brightness of each pixel in the image to be processed may be binarized by comparing it with a predetermined threshold or a threshold determined including a plurality of pixels adjacent to the pixel.

  In the limited color image generated by the limited color image generation unit 11, the color boundary extraction unit 13 has different main colors adjacent to each other, but any of the adjacent main colors is a binary generated by the binary image generation unit 12. In the image, the color boundary that has been converted into one of the values is extracted. In such a limited color image, different colors are adjacent to each other in the limited color image, but there is no boundary in the binary image generated by the binary image generation unit 12, and the boundary is not included in the image to be processed. This is where the information expressed by the color difference is missing. The color boundary extracted by the color boundary extraction unit 13 is a processing target of the determination unit 14 and the correction unit 15. Each time the color boundary extraction unit 13 extracts the color boundary, the color boundary extraction unit 13 may pass the determination unit 14 to perform the processing of the determination unit 14 and the correction unit 15, or after extracting the color boundary from the entire processing target image. You may deliver to the determination part 14. In addition to extracting the color boundary by scanning the limited color image and the binary image, the color boundary may be extracted for each combination of main colors.

  The determining unit 14 determines which side of the color boundary is to be corrected based on the main color that constitutes the color boundary extracted by the color boundary extracting unit 13 and the characteristics of the main color region. Features relating to the main color include brightness, saturation, hue, and the like of the main color. In addition, as features relating to the main color area, the size (number of pixels, the size of the circumscribed rectangle), length, thickness, and comprehensive relationship (whether it is included in one side) where the main color is used Or the degree of inclusion, the degree of overlap, etc.) and the complexity. From these characteristics, for example, a determination degree may be calculated for each main color constituting the color boundary using a function F representing the determination degree, and one of them may be determined as a main color to be corrected. Alternatively, the logical determination may be made according to, for example, the priority order from the above-described features. The determination of which side of the color boundary is corrected may be performed at each color boundary, or may be performed for each set of main colors constituting the color boundary in the entire image.

  The correction unit 15 corrects the value determined by the determination unit 14 for the color boundary extracted by the color boundary extraction unit 13 in the binary image generated by the binary image generation unit 12. Since the color boundary extracted by the color boundary extraction unit 13 is one of binary values without a boundary in the binary image, the correction is determined by the color boundary determination unit 14. The value on the side may be changed to the other value of the binary value. As a result, the color boundary where the color difference exists in the binary image can be recognized, and the color information is reflected in the binary image. The number of pixels to be corrected may be determined in advance.

  FIG. 2 is an explanatory diagram of a specific example of processing according to the first embodiment of this invention. FIG. 2A shows a specific example of an image to be processed. In the image shown in FIG. 2A, a black character “A”, an orange character “B”, and an orange rectangle including a green character “C” exist in a gray background. Yes. For convenience of illustration, the difference in color is indicated by black for the other color and different shaded lines for the other colors.

  FIG. 2B shows a binary image binarized by the binary image generation unit 12 with the image shown in FIG. In this example, the binary values are indicated by white and black, and the black character “A” is set to one value (black) and the other portion is set to the other value (white). In this binary image, the orange character “B”, the rectangle, and the green character “C” are not reflected, and the color information is missing.

  On the other hand, the limited color image generation unit 11 generates a limited color image in which the colors in the processing target image shown in FIG. For example, when the image shown in FIG. 2A is read by an image reading device or the like, different colors exist at the boundary due to reading errors or the like, and there is a variation in color even in a solid portion. It may have occurred. If the limited color image is generated, the color boundary extracted by the next color boundary extraction unit 13 becomes clear. In the example shown in FIG. 2A, black, gray, orange, and green are extracted as main colors, and a color other than these colors is converted into one of the main colors to generate a limited color image. Here, the image in FIG. 2A is substituted.

  In the limited color image generated by the limited color image generation unit 11, the color boundary extraction unit 13 has different main colors adjacent to each other, but any of the adjacent main colors is a binary generated by the binary image generation unit 12. In the image, the color boundary that has been converted into one of the values is extracted. In this specific example, as can be seen by comparing FIG. 2A and FIG. 2B, the gray-orange boundary and the orange-green boundary existing in FIG. In the binary image shown in B), both are shown in white on both sides of the boundary. That is, at the boundary where gray and orange are adjacent, both the adjacent primary colors gray and orange are converted into one of the binary values (white) in the binary image. Further, even at the boundary where orange and green are adjacent, both the adjacent main colors orange and green are converted into one of the binary values (white) in the binary image. Therefore, the boundary between gray and orange and the boundary between orange and green are extracted as color boundaries to be corrected here. The extracted color boundary is indicated by a broken line in FIG.

  The determination unit 14 determines which side of the color boundary is to be corrected based on the characteristics related to the main color and the region of the main color that form the color boundary extracted by the color boundary extraction unit 13, and the correction unit 15 For the color boundary extracted by the color boundary extraction unit 13 in the binary image generated by the binary image generation unit 12, the value on the side determined by the determination unit 14 is corrected. First, it is determined which side of the orange / green color boundary is to be corrected. Here, it is assumed that the determination unit 14 determines that the green side is to be corrected, and the correction unit 15 corrects the green side. FIG. 2D shows the result of correcting the green side for the orange-green color boundary. Further, it is determined which side of the gray / orange color boundary is to be corrected. Here, it is assumed that the determination unit 14 determines that the orange side is to be corrected, and the correction unit 15 corrects the orange side. The result of correcting the orange side for the gray / orange color boundary is reflected in FIG. 2D and shown in FIG.

  The binary image shown in FIG. 2E is output as the processing result. In the binary image shown in FIG. 2B, the outlines of the orange character “B”, the rectangle, and the green character “C” that have disappeared appear, and the presence of color information is not lost.

  FIG. 3 is an explanatory diagram of an example of correcting one side of a color boundary in a complicated figure. As described above, the determination unit 14 determines which side of the main colors constituting the color boundary is to be corrected, and the color boundary is corrected for the determined side. For example, consider a case where there is a complicated figure as shown in FIG. Here, different colors are shown by changing diagonal lines, but it is assumed that any color is converted into one value in the binary image. Here, it is assumed that the binary values are white and black and converted to white.

  For example, when both sides of the color boundary existing in FIG. 3A are corrected, the result is as shown in FIG. The complicated part is crushed and disappears. On the other hand, when one of the color boundaries is corrected, the binary image shown in FIG. 3B is obtained, and the complicated portion is reflected in the binary image. By correcting one side of the color boundary, fine or small characters with complicated portions are reflected in the binary image.

As described above, which side of the color boundary is to be corrected is determined by the determination unit 14 from the characteristics regarding the main color constituting the color boundary and the characteristics regarding the area of the main color. Some specific examples will be described. For example, when the function F representing the above-described determination degree is used, as the function F,
F = α × thickness + β × size + γ × inclusion level−δ × saturation may be used. Here, the coefficients α, β, γ, and δ are positive numbers given in advance. The main color side having a small value of the function F may be determined as the side to be corrected at the color boundary and corrected. The thickness is a distance from a color boundary to be determined to another color boundary, and may be a line width if it is a character. The size is the size of the main color region including the color boundary, and may be obtained from the number of pixels, for example, or may be the size of a circumscribed rectangle of the region. FIG. 4 is an explanatory diagram of an example of the comprehensiveness. The comprehensiveness is an area ratio of a portion where a circumscribed rectangle of one main color area constituting the color boundary does not overlap with a circumscribed rectangle of the other main color area. In the example shown in FIG. 4, for ease of understanding, the two circumscribed rectangles are shifted to the side. Therefore, the area ratio of the non-overlapping portion is ½. In addition, since 2/3 of the circumscribed rectangle 2 overlaps the circumscribed rectangle 1, the area ratio of the non-overlapping portion is 1/3. Alternatively, the comprehensiveness may be determined based on whether or not it is included. The saturation may be the saturation of the main color.

  In this specific example of the function F, the value of the function F increases as the thickness is thicker and larger, does not overlap with the circumscribed rectangles of other main colors, and the saturation is lower. The higher the saturation is, the smaller the value. It is estimated that the smaller the value of the function F is, the more likely the foreground is between the background and the foreground, and the larger the value of the function F, the more likely it is the background. As shown in FIG. 3, in the complicated figure, the side estimated as the foreground is corrected, and the correction may be made by determining the side of the color region having a small function F as the side to be corrected.

  For example, in the example shown in FIG. 2, in the portion where the green character “C” is present in the orange rectangle, the green character “C” is narrower and smaller at the orange-green color boundary. Is included. Therefore, the value of the function F calculated from the green character “C” is smaller than the value of the function F calculated from the orange rectangle. Accordingly, it is determined that the green side is corrected at the orange / green color boundary, and the green side is corrected.

Since the thickness of characters and the like may change, the above function F is modified using the average thickness and variance of the thickness,
F = α1 × average thickness + α2 × thickness dispersion + β × size + γ × inclusion level−δ × saturation. Here, the coefficients α1, α2, β, γ, and δ are positive numbers given in advance. The main color side having a small value of the function F may be determined as the side to be corrected at the color boundary and corrected. Of course, it may be a function using other characteristics relating to the color of the main color and characteristics relating to the area of the main color, or what expression is used as a function for calculating the determination degree.

When the determination unit 14 determines which side of the color boundary is to be corrected, in addition to the method using the determination degree calculated by the above-described function, the priority order is determined based on the color characteristics of the main color and the area characteristics. The logic may be determined according to the above. As an example,
S1. Determine the side of the main color with a low coverage as the side to be corrected S2. Determine the side of the main color with a small thickness as the side to be corrected S3. The main color side having a small area size is determined as the correction side. S4. Prioritizing that the side of the main color with high saturation is determined as the side to be corrected, if the difference between the feature values of the two main colors in order from S1 is within a predetermined threshold, correction is performed with the contents of that step. The side to be performed is determined, and if it is larger than the threshold value, it is determined that the process proceeds to the next. For example, in S1, if the difference in coverage between the two main color regions constituting the color boundary is within a predetermined threshold value, the side of the main color having a lower coverage is determined as the correction side. On the other hand, if the difference in inclusiveness is within a predetermined threshold, the process proceeds to S2, and the thickness is compared. In this way, the determination may be made in order. Even in S4, if the saturation difference is within a predetermined threshold value, one of the main colors may be determined as a side to be forcibly corrected. Of course, the ranking and each determination item shown here are only examples, and other determination items may be used, and the order is not limited to this example.

  The above-described determination may be performed for each color boundary, or may be performed collectively in the image. Even when it is performed for each color boundary, a determination made at a certain color boundary is stored together with a set of main colors constituting the color boundary, and the determination may be reflected at other color boundaries in the set of main colors. . Color boundary portions are corrected uniformly in the binary image.

  Further, when determining in a lump in an image, there may be a plurality of color boundaries in which two main colors are adjacent to each other. Therefore, the color boundary used for determining the correction side is specified. Alternatively, the characteristics at each color boundary may be processed statistically. For example, among the main color areas where there is a color boundary where two main colors are adjacent to each other, one main color area having the maximum thickness and the other main color area adjacent to the area are thick. It is only necessary to determine a correction side with respect to a region having a maximum length. Alternatively, using the variance of thickness, targeting the area of one main color with the smallest thickness variance and the area with the smallest thickness variance among the other major color areas adjacent to that area, What is necessary is just to determine the side to correct. In addition, the size of the area is used instead of the thickness, and the area of the one main color with the largest size and the area with the largest size among the areas of the other main color adjacent to the area are targeted. And the correction side may be determined. Of course, other features may be used. Once these representative regions are used to determine the side to be corrected, the determination is also used for other color boundaries adjacent to the two main colors. In addition, such correction side determination may be performed for each set of two main colors constituting the color region.

  When statistically processing the features at each color boundary, for each set of two adjacent main colors, the feature amounts at one or more color boundaries adjacent to the two main colors are totaled, and the total results are calculated. It suffices to determine which side is to be corrected. Alternatively, after determining which side of each color boundary is to be corrected, it is determined which side is to be corrected for the set of the two main colors depending on which side is determined to be corrected. May be.

  Such a determination of which side is corrected is performed for each set of two main colors constituting the color boundary, and for which color boundary adjacent to the two main color sets, which color boundary The determined side may be uniformly corrected by the correction unit 15.

  FIG. 5 is a block diagram showing a second embodiment of the present invention. Differences from the first embodiment of the present invention shown in FIG. 1 will be mainly described. In the second embodiment, the binary image generation unit 12 binarizes the limited color image generated by the limited color image generation unit 11.

  The binary image generation unit 12 includes main color colors (specifically, brightness, saturation, hue, etc.), main color areas (size, length, thickness, inclusion relationship, complexity, etc.), main color, etc. The limited color image generated by the limited color image generation unit 11 according to the adjacency relationship between the color and the other main color (the length of the adjacent portion of the main color and the other main color, the number of adjacent portions, etc.) Is binarized to generate a binary image.

For example, using a function G representing a degree of determination for determining whether to convert to one of binary values,
G = α × thickness + β × size + γ × inclusion level−δ × saturation degree is calculated. Here, the coefficients α, β, γ, and δ are positive numbers given in advance. If the calculated degree of determination is less than or equal to a predetermined value, it is converted to one of the binary values (for example, black), otherwise it is converted to the other binary value (for example, white). The thickness is a distance from a boundary adjacent to a certain primary color to another boundary, and may be a line width if it is a character. The size is the width of the region of the main color, and may be obtained from the number of pixels, for example, or may be the size of a circumscribed rectangle of the region. The comprehensiveness is an area ratio of a portion where a circumscribed rectangle of one main color region does not overlap with a circumscribed rectangle of the other adjacent main color region. The saturation may be the saturation of the main color. It is assumed that the lower the calculated degree of determination is, the more the foreground figure is, and the larger the background is, the higher the background. What is necessary is just to convert into the binary value according to each.

Alternatively, a function H representing the degree of changing the binary value is used,
The degree is calculated from H = ε × length of adjacent portions. Here, the coefficient ε is a positive number given in advance. For adjacent main colors whose calculated degree values are larger than a predetermined value, the binary values may be different.

  The binary image generated in this way is passed to the color boundary extraction unit 13, and different primary colors are adjacent to each other in the limited color image generated by the limited color image generation unit 11. In the binary image, the color boundary converted to one of the values is extracted. Then, the determination unit 14 determines which side of the color boundary is to be corrected, and the determined unit corrects the determined side. The processing of the color boundary extraction unit 13, the determination unit 14, and the correction unit 15 is as described in the first embodiment.

  FIG. 6 is an explanatory diagram of a specific example of processing according to the second embodiment of the present invention. FIG. 6A shows a specific example of an image to be processed, which is shown in FIG. In the image shown in FIG. 6A, a black character “A”, an orange character “B”, and an orange rectangle including a green character “C” are present in a gray background. Yes. For convenience of illustration, the difference in color is indicated by black for the other color and different shaded lines for the other colors.

  The limited color image generation unit 11 generates a limited color image in which the colors in the image to be processed shown in FIG. 6A are limited to the main color, with the image shown in FIG. In this example, black, gray, orange, and green are extracted as main colors, and a limited color image is generated by converting these colors to any of the main colors. Here, the image in FIG. 6A is substituted.

  The binary image generation unit 12 binarizes the limited color image generated by the limited color image generation unit 11 according to the adjacent relationship of the main colors, and generates a binary image. The binary image binarized by the binary image generation unit 12 is shown in FIG. In this example, binary values are indicated by white and black, and the black character “A” and the orange character “B”, as well as one value (black) of the orange rectangle and the green character “C” therein. ), And the gray portion as the background is converted to the other value (white). In this binary image, the green letter “C” in the orange rectangle is not reflected, and the information expressed by the color difference in the image to be processed is missing.

  In the limited color image generated by the limited color image generation unit 11, the color boundary extraction unit 13 has different main colors adjacent to each other, but any of the adjacent main colors is a binary generated by the binary image generation unit 12. In the image, the color boundary that has been converted into one of the values is extracted. In this specific example, the boundary between orange and green that exists in FIG. 6A is either one of the binary images shown in FIG. ). Accordingly, the boundary between orange and green is extracted here as the color boundary to be corrected. The extracted color boundary is indicated by a broken line in FIG.

  The determination unit 14 determines which side of orange or green is to be corrected based on the characteristics regarding the orange and green regions for the color boundary adjacent to orange and green extracted by the color boundary extraction unit 13. Here, it is assumed that it is decided to correct the green side. The correction unit 15 corrects the value determined by the determination unit 14 for the color boundary extracted by the color boundary extraction unit 13 in the binary image generated by the binary image generation unit 12. Here, the green side of the binary image is corrected at the color boundary where orange and green are adjacent. The corrected result is shown in FIG.

  The binary image shown in FIG. 6D is output as the processing result. In the binary image shown in FIG. 6B, the outline of the green character “C” that has disappeared appears, and the information represented by the difference in color in the image to be processed is present without being lost. It becomes like this.

  FIG. 7 is an explanatory diagram of an example of a computer program, a storage medium storing the computer program, and a computer when the functions described in the embodiments of the present invention are realized by the computer program. In the figure, 21 is a program, 22 is a computer, 31 is a magneto-optical disk, 32 is an optical disk, 33 is a magnetic disk, 34 is a memory, 41 is a CPU, 42 is an internal memory, 43 is a reading unit, 44 is a hard disk, 45 is An interface 46 is a communication unit.

  You may implement | achieve the function of each part demonstrated by each embodiment of the above-mentioned all or part by the program 21 which can be performed by computer. In that case, the program 21 and the data used by the program may be stored in a computer-readable storage medium. The storage medium is a signal of a corresponding signal that causes a change state of energy such as magnetism, light, electricity, etc. according to the description content of the program to the reading unit 43 provided in the hardware resource of the computer. In this format, the description content of the program is transmitted to the reading unit 43. For example, there are a magneto-optical disk 31, an optical disk 32 (including a CD and a DVD), a magnetic disk 33, a memory 34 (including an IC card, a memory card, a flash memory, and the like). Of course, these storage media are not limited to portable types.

  The program 21 is stored in these storage media, and the program 21 is read from the computer by, for example, mounting these storage media on the reading unit 43 or the interface 45 of the computer 22, and the internal memory 42 or the hard disk 44 (magnetic disk) And the program 21 is executed by the CPU 41, the functions described in the above-described embodiment of the present invention are realized in whole or in part. Alternatively, the program 21 is transferred to the computer 22 via the communication path, and the computer 22 receives the program 21 by the communication unit 46 and stores it in the internal memory 42 or the hard disk 44, and the CPU 21 executes the program 21. May be.

  In addition, the computer 22 may be connected to various devices via an interface 45. For example, display means for displaying information, reception means for receiving information from the user, and the like may be connected. Further, for example, an image reading device is connected via the interface 45, and the processing described in each embodiment of the present invention is performed by using an image read by the image reading device or an image obtained by processing the image as a processing target image. May be. The processed binary image may be stored in the hard disk 44, stored in a storage medium via the interface 45, or transferred to the outside through the communication unit 46. Further, an image forming apparatus as an output device may be connected via the interface 45, and a processed binary image may be formed.

  Of course, it may be partially configured by hardware, or all may be configured by hardware. Or you may comprise as a program which included all or one part of the function demonstrated by each embodiment of this invention with other structures. Of course, when applied to other purposes, it may be integrated with the program for that purpose.

  DESCRIPTION OF SYMBOLS 11 ... Limited color image generation part, 12 ... Binary image generation part, 13 ... Color boundary extraction part, 14 ... Determination part, 15 ... Correction part, 21 ... Program, 22 ... Computer, 31 ... Magneto-optical disk, 32 ... Optical disk 33 ... Magnetic disk, 34 ... Memory, 41 ... CPU, 42 ... Internal memory, 43 ... Reading unit, 44 ... Hard disk, 45 ... Interface, 46 ... Communication unit.

Claims (5)

  Limited color image generation means for generating a limited color image in which colors used in the image to be processed are limited to a plurality of main colors, and binary image generation means for binarizing the image to generate a binary image A color boundary extracting means for extracting a color boundary that is adjacent to a different primary color in the limited color image but is converted to one of the adjacent primary colors in the binary image; and A determining means for determining which side of the color boundary is to be corrected based on the features relating to the primary color and the area of the primary color; and a value on the side determined by the determining means for the color boundary in the binary image An image processing apparatus comprising correction means for correcting the above.   A limited color image generating unit configured to generate a limited color image in which colors used in an image to be processed are limited to a plurality of main colors; and the limited color image is the primary color, the primary color region, or the primary color. A binary image generating means for generating a binary image by binarizing according to the adjacent relationship between the main image and another main color, and different main colors are adjacent to each other in the limited color image. Color boundary extraction means for extracting a color boundary that has been converted into one of the values, and which side of the color boundary is to be corrected based on the main color that constitutes the color boundary and the characteristics relating to the area of the main color An image processing apparatus comprising: a determination unit that determines; and a correction unit that corrects a value determined by the determination unit of the color boundary in the binary image.   The color boundary extraction unit extracts the color boundary for each of the main color combinations from the entire limited color image, and the determination unit selects any of the main color combinations for each of the main color combinations. The image processing apparatus according to claim 1, wherein whether to correct the color side is determined.   The said determination means determines which side of the said color boundary is correct | amended according to the area | region of the said main color which comprises the said color boundary. Image processing apparatus.   An image processing program for causing a computer to execute the function of the image processing apparatus according to any one of claims 1 to 4.

Images