JP6056309B2 - Image processing apparatus, image processing method, and program - Google Patents

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program for performing processing for extracting a pattern from an image.

  In the captured image obtained by capturing the displayed screen, an intermediate color between the pattern and the background color is generated in the vicinity of the boundary between the pattern and the background by anti-aliasing for making a pattern such as a character appear smoothly.

  In a scanned image obtained by scanning an image, an intermediate color due to blur occurs at the boundary between the pattern and the background (paper portion).

  For example, when a character of a specified color is extracted from a captured image or a scanned image, pixels in an intermediate color portion due to anti-aliasing or blur may be excessively dropped or incorporated excessively from the character area. As a result, the extracted character image becomes a drowned or crushed image.

  FIG. 1 is a diagram illustrating an example of a character image in which an intermediate color is generated. As shown in FIG. 1, the intermediate color portion a1 occurs due to, for example, anti-aliasing or blur. The black portion shown in FIG. 1 is the original character color portion a2, the white portion is the background portion a3, and the gray portion is the intermediate color portion a1.

  FIG. 2 is a diagram in which only the character color part a2 shown in FIG. 1 is extracted. As shown in FIG. 2, since the intermediate color portion a1 is erased, a part of the character is erased and the original character is not understood.

  FIG. 3 is a diagram illustrating an example in which the intermediate color portion a1 illustrated in FIG. 1 is appropriately distributed. As shown in FIG. 3, the shape of the original character can be generated by appropriately assigning the intermediate color portion a1 to the character or the background. In other words, it is important to appropriately assign pixels that have become intermediate colors due to anti-aliasing or blur to the pattern or the background.

  For example, the following technique is used as a method for assigning intermediate colors. In this method, first, a plurality of colors with a high appearance frequency of an input color image are extracted as main colors, and other intermediate pixels are assigned to the main colors in the following procedure.

  First, the target intermediate pixel is projected on all the line segments connecting any two main colors in the color space of the target intermediate color pixel, and the distance between the two main colors and the projection point is calculated. Further, the foreground color and background color group to which the target pixel belongs is determined in consideration of the shortest distance on the image or the distance from the line segment among the pixels belonging to the main color at both ends of each line segment. . The intermediate color is assigned to one of the determined sets of colors (see, for example, Patent Document 1).

  Further, there is a technique for projecting an intermediate color point on a two-dimensional plane and distributing only the main color whose distance is within a threshold on the plane when distributing the intermediate color to the main color (see, for example, Patent Document 2).

JP 2003-16444 A WO2006 / 030891

  However, Patent Document 1 uses a combination of all the main colors extracted from the image, so that there is a problem that the processing time increases significantly as the main colors increase. Further, in Patent Document 1, even when no intermediate color is generated between main colors, the above-described line segment processing is performed and wasteful processing is performed.

  Further, in Patent Document 2, combinations of main colors can be narrowed down by not targeting combinations whose distance on the plane between the main colors is greater than or equal to the threshold. However, this method may include a main color to be targeted beyond a threshold value, and is not necessarily an appropriate narrowing-down method.

  For example, if the characters in the image contain characters that are partly thinner than others (for example, characters in the Mincho or Times font) and the resolution is low, The core may be an intermediate color (see FIG. 1). In this case, when narrowing down according to Patent Document 2, the true main color may be excluded from the determination target due to the narrowing down, and there is a problem that the determination of the color of the target pixel is erroneous.

  Therefore, in the prior art, it has been impossible to improve the processing speed while appropriately obtaining a combination of main colors to be assigned to intermediate colors.

  Therefore, an object of the disclosed technique is to provide an image processing apparatus, an image processing method, and a program capable of improving the processing speed while appropriately obtaining a combination of main colors to be assigned to intermediate colors.

An image processing apparatus according to an aspect of the disclosure includes a main color extraction unit that extracts a main color including a foreground color and a background color of the image based on a result of associating color information of each pixel of the image with a region of a color space. , Among the main colors extracted by the main color extraction unit, a combination of two different main colors is obtained to calculate a line segment between the two main colors, and the calculated line segment between the main colors remove the line segments that are not neutral occurs in the color space, and the line segment calculation unit that acquires a segment the intermediate color is generated between the two main colors, for each intermediate color in the image, Determining two principal colors having a minimum distance between the intermediate color and the line segment in the color space, determining which of the two main colors the intermediate color belongs to; and each intermediate color in the image Is generated by replacing the principal color determined by the determination unit with And a generation unit.

  According to the disclosed technology, it is possible to improve the processing speed while appropriately obtaining a combination of main colors to be assigned to intermediate colors.

The figure which shows an example of the character image which the intermediate color generate | occur | produced. The figure which extracted only the character color part shown in FIG. The figure which shows the example which distributed the intermediate color part shown in FIG. 1 appropriately. FIG. 2 is a block diagram illustrating an example of hardware of the image processing apparatus according to the first embodiment. FIG. 3 is a block diagram illustrating an example of functions of the image processing apparatus according to the first embodiment. The figure which shows an example of an input image. The figure which shows an example of the color space after voting. The figure for demonstrating line segment deletion. The figure which shows an example of line segment information. The figure explaining determination of the group of main colors. The figure for demonstrating the shortest distance on an image. 5 is a flowchart illustrating an example of image processing in the first embodiment. FIG. 9 is a block diagram illustrating an example of functions of an image processing apparatus according to a second embodiment. 10 is a flowchart illustrating an example of image processing according to the second embodiment.

  Hereinafter, embodiments of an image processing apparatus, an image processing method, and a program will be described with reference to the accompanying drawings.

[Example 1]
<Hardware>
FIG. 4 is a block diagram illustrating an example of hardware of the image processing apparatus 10 according to the first embodiment. In the example illustrated in FIG. 4, the image processing apparatus 10 is connected to a reading unit 20 and a display unit 30.

  The reading unit 20 is, for example, a scanner device, and scans an image on a paper surface and reads pixel values one by one with respect to x and y coordinates arranged two-dimensionally. When the pixel value to be read is a color image, the pixel value is represented by a set of three colors of R (red), G (green), and B (blue).

  When the image to be read is a gray image, the pixel value often represents a brightness value. The color pixel values of the three colors RGB can be converted into lightness values using, for example, a lightness value = 0.299 × R + 0.587 × G + 0.114 × B. The reading unit 20 transmits the read image to the image processing apparatus 10.

  The display unit 30 is, for example, an LCD (Liquid Crystal Display) or the like, and displays a screen requested to be displayed by the image processing apparatus 10. In addition, the screen displayed on the display unit 30 may be captured by the image processing apparatus 10.

  The image processing apparatus 10 inputs, for example, a scanned image read by the reading unit 20 or a captured image of a screen displayed on the display unit 30. The image processing apparatus 10 generates an image in which an intermediate color due to anti-aliasing or blur appearing in a pattern including characters and graphics is appropriately assigned to the main color with respect to the input image. The main color is a color that appears more than a predetermined value in the image, for example, a pattern color or a background color. The intermediate color is, for example, a color other than the main color. The image processing apparatus 10 extracts a pattern (for example, a character) based on an image in which intermediate colors are assigned to main colors.

  The image processing apparatus 10 includes, for example, a control unit 101, a main storage unit 102, an auxiliary storage unit 103, a communication unit 104, and a drive device 105 as hardware. Each unit is connected via a bus so that data can be transmitted / received to / from each other.

  The control unit 101 is a CPU (Central Processing Unit) that performs control of each device, calculation of data, and processing in a computer. The control unit 101 is an arithmetic device that executes a program stored in the main storage unit 102 or the auxiliary storage unit 103. The control unit 101 receives data from the input device or the storage device, calculates, processes the output device, the storage device, and the like. Output to the device.

  The main storage unit 102 is, for example, a ROM (Read Only Memory) or a RAM (Random Access Memory). The main storage unit 102 is a storage device that stores or temporarily stores programs and data such as an OS and application software that are basic software executed by the control unit 101.

  The auxiliary storage unit 103 is, for example, an HDD (Hard Disk Drive) or the like, and is a storage device that stores data related to application software. The auxiliary storage unit 103 stores, for example, an image acquired from the reading unit 20 or an image obtained by capturing a screen displayed on the display unit 30.

  The communication unit 104 performs data communication with peripheral devices by wire or wireless. The communication unit 104 acquires an image including a pattern via a network, for example, and stores it in the auxiliary storage unit 103.

  The drive device 105 reads a predetermined program from the recording medium 106, for example, a flexible disk or a CD (Compact Disc), and installs it in the storage device.

  A predetermined program is stored in the recording medium 106, and the program stored in the recording medium 106 is installed in the image processing apparatus 10 via the drive device 105. The installed predetermined program can be executed by the image processing apparatus 10.

  In addition, although the image processing apparatus 10 has the reading unit 20 and the display unit 30 as separate configurations, it may be configured to include either one or both.

<Function>
FIG. 5 is a block diagram illustrating an example of functions of the image processing apparatus 10 according to the first embodiment. In the example illustrated in FIG. 5, the image processing apparatus 10 includes an image input unit 201, a main color extraction unit 202, a line segment calculation unit 203, a main color determination unit 204, an image generation unit 205, and a pattern extraction unit 206. Each unit illustrated in FIG. 5 functions, for example, when the control unit 101 loads and executes the extraction processing program stored in the auxiliary storage unit 103 in the main storage unit 102. Each unit illustrated in FIG. 5 can be realized by, for example, the control unit 101 and the main storage unit 102 as a work memory. Further, each unit illustrated in FIG. 5 may be realized by hardware, for example.

  The image input unit 201 inputs, for example, a captured image by screen capture or a scan image generated by scanning a document by the reading unit 20. Hereinafter, the captured image and the scanned image are collectively referred to as an image. The image input unit 201 stores the input image in the main storage unit 102.

  The main color extraction unit 202 extracts the main color including the foreground color and the background color of the image based on the result of associating the color information of each pixel of the image input by the image input unit 201 with the area of the color space. . The foreground color represents the original color belonging to the pattern, and the background color represents the color that becomes the background other than the pattern. The main color extraction unit 202 extracts a main color using the following known method, for example, and calculates the number of main colors.

  Based on the color information of each pixel of the input image, the main color extraction unit 202 votes for the area corresponding to the color information of the pixel in the color space, and the ratio of the number of votes to the total number of pixels is a predetermined threshold value. The central coordinates of the corresponding region of the color space which is the above and the maximum are used as the main color. The main color extraction unit 202 outputs the extracted main color to the line segment calculation unit 203.

  The main color extraction will be described using a specific example. FIG. 6 is a diagram illustrating an example of an input image. In the image shown in FIG. 6, the main colors are four colors c1, c2, c3, and c4. For example, the main color c4 is a color obtained by mixing the main color c1 and the main color c2, and is a color used in the pattern.

  FIG. 7 is a diagram illustrating an example of a color space after voting. The example shown in FIG. 7 is an example in which the image shown in FIG. 6 is voted on an area on the color space. As shown in FIG. 7, many votings are made in the areas of the main colors c1, c2, c3, and c4. The radius of the circle represents the number of votes. For example, if the radius shown in FIG. 7 is equal to or greater than a predetermined value, the main color extraction unit 202 extracts the center color of this circle as the main color.

  Returning to FIG. 5, the line segment calculation unit 203 has an intermediate color indicating a color other than the main color on the line between any two main colors in the color space among the main colors extracted by the main color extraction unit 202. The line segment to be calculated is calculated. For example, if there is no intermediate color on the line between the main colors, the line segment calculation unit 203 does not calculate the line segment formula and does not store the line segment information. This line segment is a line segment that does not require subsequent processing because no intermediate color is generated.

  The line segment calculation unit 203 calculates a line segment using, for example, the following method. The line segment calculation unit 203 calculates all combinations of two different main colors among all the main colors, and calculates an equation of a line segment (straight line) between the two main colors.

  After calculating the line segment equation, the line segment calculation unit 203 determines whether an intermediate color is generated in the color space between the main colors, and deletes the line segment if no intermediate color is generated. To do. Thereby, the line segment calculation unit 203 determines and records only the line segment in which the intermediate color is finally generated in the line segment connecting the main colors.

  The line segment calculation unit 203 deletes unnecessary line segments as follows, for example. The line segment calculation unit 203 sets Ka as the number of cubic regions through which a line segment connecting the main colors passes in the color space, and vote among the cube regions through which the line segment passes. The number of areas where the number is not 0 is defined as Kn. At this time, the line segment calculation unit 203 determines that an intermediate color has occurred between the main colors when Kn / Ka is equal to or greater than the threshold value Kth, registers this line segment, and deletes this line segment otherwise. To do.

  Hereinafter, line segment deletion will be described using a specific example. FIG. 8 is a diagram for explaining line segment deletion. In the example shown in FIG. 8, the three-dimensional color space is represented in two dimensions for easy understanding. Further, the color space shown in FIG. 8 is divided into equal-volume regions as shown by rectangles, and the numbers in the rectangles indicate the number of votes when voting the color of the pixel. The image shown in FIG. 6 is used.

  In the image shown in FIG. 6, there are four main colors c1, c2, c3, and c4, but only the main colors c1, c2, and c3 are used here for simplicity of explanation. A dark halftone dot rectangle shown in FIG. 8 represents a main color. A thin halftone dot rectangle shown in FIG. 8 represents a region through which a line segment passes.

When the line segment calculation unit 203 first obtains all the line segments between any two main colors, three line segments are obtained as shown in FIG. The line segment calculation unit 203 calculates Kn / Ka for each of the three line segments, and performs threshold determination using Kth. For example, Kth = 0.8.
Line segment L1 Kn1 / Ka1 = 5/6> Kth
Line segment L2 Kn2 / Ka1 = 4/4> Kth
Line L5 Kn5 / Ka5 = 1/3 <Kth
The line segment calculation unit 203 leaves the line segments L1 and L2, calculates the expression of the remaining line segments, and deletes the line segment L5. In addition, the line segment calculation unit 203 uses the number, label, main color of the end point, and parameters of the calculated formula (line segment) as the line segment information as information for identifying the line segment with respect to the remaining line segment. Store in the storage unit 102 or the like. Here, Kn may be the number of regions where the ratio of the number of votes to the total number of pixels is equal to or greater than a threshold value.

  FIG. 9 is a diagram illustrating an example of line segment information. In the example shown in FIG. 9, line segment information is obtained based on the color space shown in FIG. As shown in FIG. 9, a line segment is calculated by a line segment calculation unit 203 with a set of primary colors c1 and c2, a set of primary colors c2 and c3, a set of primary colors c2 and c4, and a set of primary colors c4 and c1. Has been. For the calculated line segment, as a line segment parameter, for example, a slope and an intercept that are parameters of a straight line equation are held.

  For example, if the foreground color and the background color can be distinguished from the main colors, the line segment calculation unit 203 performs line segment calculation for a line segment formed by a combination of the foreground color and the background color. You can also. For example, when the number of votes of the main color in the color space described above is, for example, 80% or more of the pixels of the entire image, the background color is likely to be a background color. You may consider this main color as a background color. Particularly in the case of a character image, the number of votes for the background color increases. In this case, the main color other than the background color is the foreground color. This determination method is effective when there is one background color.

  Returning to FIG. 5, for example, for each intermediate color in the image, the main color determination unit 204 obtains two main colors that minimize the distance between the intermediate color and the line segment. Decide which one to belong to.

  For example, the main color determination unit 204 obtains the color distance between each pixel of the image and each main color, and determines that the color of the pixel belongs to the main color when the color distance is equal to or smaller than the threshold. The primary color determination unit 204 sets pixels that do not belong to any of the primary colors as intermediate color pixels.

  When there are intermediate color pixels, the main color determination unit 204 determines a set of main colors including the foreground color and the background color for each intermediate color pixel.

  After the main color set of the intermediate color pixels is determined, the main color determination unit 204 determines which main color (including the foreground color and the background color) of the main color set belongs to the intermediate color pixel. Specifically, the main color determination unit 204 determines the set of main colors for the intermediate color pixels as follows.

  FIG. 10 is a diagram for explaining determination of a set of main colors. As shown in FIG. 10, the main color determination unit 204 obtains the length of the vertical line segment drawn from the intermediate color pixel pk to each line segment with respect to the intermediate color pixel pk, and the line segment with the shortest vertical line segment length is obtained. Ln is obtained.

(1) When the line segment Ln is uniquely determined FIG. 10A shows an example in which the line segment Ln is uniquely determined. As shown in FIG. 10A, when the intermediate color pixel p1 has one closest line segment (line segment L2), the main color determination unit 204 sets the main colors c2 and c3 at both ends of the line segment L2. It is determined that the intermediate color belongs to one of them.

(2) When the line segment Ln is not uniquely determined FIG. 10B illustrates an example in which the line segment Ln is not uniquely determined. As shown in FIG. 10B, when three or more main colors are arranged in a straight line, the main color determination unit 204 is equal in distance to a plurality of line segments in the color space. Consider the distance on the image.

  In the case of the example shown in FIG. 10B, the shortest distances dks and dkt on the image between the pixels having the main colors cs and ct at both ends of the line segment having the same distance and p2 are calculated. The primary color determination unit 204 determines that, for example, the primary color group 204 exists on a line segment having both ends of the primary color set ci and cj that minimizes dks + dkt, and p2 belongs to either ci or cj.

  FIG. 11 is a diagram for explaining the shortest distance on the image. As shown in FIG. 11, the main color determination unit 204 calculates the shortest distances dk1, dk2, and dk4 between the intermediate color p2 and the main colors c1, c2, and c4. In the example shown in FIG. 11, the minimum of dks + dkt is a set of c1 and c2 (dk1 + dk2). Therefore, the primary color determination unit 204 determines a set of primary colors c1 and c2 for the intermediate color p2.

  Note that the main color determination unit 204 may determine which primary color the intermediate color belongs to using the distance on the actual image, the distance on the color space, or the like. The primary color determination unit 204 may determine, for example, a primary color that is closer in the color space from the intermediate color, or a primary color that is closer in the real space from the intermediate color.

  In addition, when using the distance in the real space, the main color determination unit 204 may use the shortest distance between the intermediate color and the main color, or use the distance between the intermediate color and the center of gravity of the connected main color. Good. The primary color determination unit 204, as described above, may determine the intermediate color as one of the primary colors by a predetermined determination method.

  Returning to FIG. 5, the image generation unit 205 generates an image in which each intermediate color or all pixels in the input image are replaced with the main color determined by the main color determination unit 204. Thereby, for example, an image as shown in FIG. 3 can be generated.

  The pattern extraction unit 206 extracts, for each color, a pattern belonging to each main color excluding the background color from the image generated by the image generation unit 205 as described above, in which all pixels of the image or each intermediate color is replaced with the main color. May be. The pattern extraction unit 206 may be a color image for the image to be extracted, or may create a binary image for each color.

  With the above configuration, the image processing apparatus 10 can improve the processing speed while appropriately obtaining a combination of main colors to be assigned to intermediate colors. Moreover, if it has the said structure, a precision is equivalent to a prior art and a processing speed improves by deleting a useless line segment. Furthermore, if it has the said structure, since it processes only when the distance in real space is also required, a processing load can be reduced.

<Operation>
Next, the operation of the image processing apparatus 10 in the first embodiment will be described. FIG. 12 is a flowchart illustrating an example of image processing according to the first embodiment. In step S101 illustrated in FIG. 12, the image input unit 201 inputs a capture image or a scan image.

  In step S102, the main color extraction unit 202 extracts a main color using a result associated with the area of the color space based on the color information of each pixel of the input image.

  In step S <b> 103, the line segment calculation unit 203 determines whether there is a pixel (an intermediate color pixel) having an intermediate color other than the main color in the image. If there is an intermediate color pixel (step S103-YES), the process proceeds to step S113, and if there is no intermediate color pixel (step S103-NO), the process proceeds to step S104.

  In step S104, the line segment calculation unit 203 first calculates a line segment connecting two main colors in the color space.

  In step S105, the line segment calculation unit 203 determines whether there is an unnecessary line segment in the calculated line segments. The unnecessary line segment is determined by, for example, how many intermediate colors are on the line segment. If there is an unnecessary line segment (step S105-YES), the process proceeds to step S106, and if there is no unnecessary line segment (step S105-NO), the process proceeds to step S107.

  In step S106, the line segment calculation unit 203 deletes a line segment in which no intermediate color is generated on the line.

  In step S107, the primary color determination unit 204 calculates the line segment L closest to the intermediate color. For example, the main color determination unit 204 draws a perpendicular line from the intermediate color on the line segment, and determines using the length of the perpendicular line.

  In step S108, the main color determination unit 204 determines whether the line segment is uniquely determined. “Uniquely determined” means that the closest line segment L is one, and “not uniquely determined” means that there are a plurality of closest line segments L. If it is uniquely determined (step S108—YES), the process proceeds to step S110. If it is not uniquely determined (step S108—NO), the process proceeds to step S109.

  In step S109, the main color determination unit 204 determines one line segment L from the plurality of line segments in consideration of the distance on the image.

  In step S110, the main color determination unit 204 determines which of the main colors at both ends of the line segment L belongs to the intermediate color. The determination of which one belongs can be made by using a distance on a color space, a distance on an actual image, or the like.

  In step S111, the primary color determination unit 204 determines whether all intermediate color pixels have been processed. If all the intermediate color pixels have been processed (step S111—YES), the process proceeds to step S112. If all the intermediate color pixels have not been processed (step S111—NO), another intermediate color pixel is selected and the process returns to step S107.

  In step S <b> 112, the image generation unit 205 generates an image in which each pixel (or each intermediate color pixel) in the image is replaced with the main color determined by the main color determination unit 204. The image generation unit 205 can set the pixels that have become an intermediate color due to anti-aliasing or blurring to an appropriate main color while speeding up the processing.

  In step S113, the pattern extraction unit 206 extracts a pattern of all colors (for example, characters) from the generated image or extracts a pattern for each color. Which pattern is to be extracted may be set in advance by the user.

  As described above, according to the first embodiment, it is possible to improve the processing speed while appropriately obtaining a combination of main colors to be assigned to intermediate colors. For example, in the first embodiment, whether or not an intermediate color between main colors is generated is determined, and only when an intermediate color is generated between main colors, a line segment in the color space connecting the main colors and the intermediate color pixels are connected. By calculating the distance, the amount of processing can be reduced. In the first embodiment, the distance on the actual image may be considered only when the shortest line segment between the target intermediate color pixel and the line segment in the color space is not uniquely determined. In the first embodiment, when the processing amount is reduced, since the true main color for the intermediate color is not excluded from the determination target, the intermediate color can be appropriately assigned to the main color.

[Example 2]
Next, an image processing apparatus according to the second embodiment will be described. In the second embodiment, when a designated color is input, a pattern for the designated color is extracted.

<Hardware>
Since the hardware of the image processing apparatus in the second embodiment is the same as the hardware of the image processing apparatus 10 in the first embodiment, the following description will be made using the same reference numerals as those shown in FIG.

<Function>
FIG. 13 is a block diagram illustrating an example of functions of the image processing apparatus 40 according to the second embodiment. In the configuration of the image processing apparatus 40 shown in FIG. 13, the same components as those shown in FIG. Hereinafter, the designated color input unit 301, the image generation unit 302, and the pattern extraction unit 303, which are different from the first embodiment, will be mainly described. The designated color input unit 301, the image generation unit 302, and the pattern extraction unit 303 can be realized by, for example, the control unit 101 or the main storage unit 102 as a work memory.

  The designated color input unit 301 is inputted with a designated color by a user or the like. The designated color may be selected from the main colors extracted by the user, or may be set in advance before the extraction process. The designated color is output to the image generation unit 302 and / or the pattern extraction unit 303.

  When the specified color is acquired from the specified color input unit 301, the image generation unit 302 sets the main color of the same color as the specified color or the main color of the color most similar to the specified color as the foreground color, and an image of only this foreground color Is generated. If the designated color is not input from the designated color input unit 301, the image generation unit 302 performs the same processing as in the first embodiment.

  When the specified color is acquired from the specified color input unit 301, the pattern extraction unit 303 extracts a main color pattern of the same color as the specified color or a pattern of a main color of the color most similar to the specified color from the generated image. The extracted pattern image may be a color (multi-value) image or a binary image.

  With the above configuration, the image processing apparatus 40 can input a designated color and extract a pattern for the designated color while maintaining the effects of the first embodiment.

<Operation>
Next, the operation of the image processing apparatus 40 in the second embodiment will be described. FIG. 14 is a flowchart illustrating an example of image processing according to the second embodiment. In step S201 shown in FIG. 14, the designated color input unit 301 accepts an input of the designated color. Note that step S201 may be performed after step S203.

  The processing in steps S202 to S212 is the same as the processing in steps S101 to S111 shown in FIG.

  In step S213, the image generation unit 302 generates an image including the pattern of the designated color when the designated color is acquired.

  In step S214, the pattern extraction unit 303 acquires the designated color and extracts the pattern of the designated color.

  As described above, according to the second embodiment, it is possible to input a designated color while extracting the pattern for the designated color while maintaining the effects of the first embodiment.

  In addition, each said Example functions suitably in the process which extracts a character from the capture image and scanning image containing a character. In addition, when the character in the image is a character in which some character lines are thinner than other character lines (for example, characters in the Mincho or Times font) and the resolution is low, The example works well.

  In addition, by recording a program for realizing the image processing described in each of the above-described embodiments on a recording medium, the image processing in each of the embodiments can be performed by a computer. For example, it is possible to record the program on a recording medium and cause the computer to read the recording medium on which the program is recorded, thereby realizing the above-described image processing.

  The image processing apparatus in each embodiment can be applied to any processing apparatus having a processor, a memory, and an interface for acquiring data, such as a computer (Personal Computer), a tablet terminal, and a smartphone. Further, the scanner device may be mounted so that the image processing can be executed.

  The recording medium is a recording medium that records information optically, electrically, or magnetically, such as a CD-ROM, flexible disk, magneto-optical disk, etc., and information is electrically recorded such as ROM, flash memory, etc. Various types of recording media such as a semiconductor memory can be used. This recording medium does not include a carrier wave.

  Although each embodiment has been described in detail above, it is not limited to a specific embodiment, and various modifications and changes can be made within the scope described in the claims. It is also possible to combine all or a plurality of the components of the above-described embodiments.

In addition, the following additional remarks are disclosed regarding the above Example.
(Appendix 1)
A main color extraction unit that extracts the main colors including the foreground color and the background color of the image based on the result of associating the color information of each pixel of the image with the area of the color space;
A line segment calculation unit that calculates a line segment in which an intermediate color indicating a color other than the main color exists on a line between any two main colors in the color space among the main colors extracted by the main color extraction unit; ,
For each intermediate color in the image, a determination is made to determine two primary colors that minimize the distance between the intermediate color and the line segment in the color space, and determine which of the two primary colors the intermediate color belongs to And
An image processing apparatus comprising: a generation unit configured to generate an image in which each intermediate color in the image is replaced with a main color determined by the determination unit.
(Appendix 2)
The line segment calculation unit
The image processing apparatus according to appendix 1, wherein all line segments between any two main colors in the color space are calculated, and line segments where the intermediate color does not exist on the line segments are deleted.
(Appendix 3)
The determination unit
When there are a plurality of sets of two main colors having the minimum distance, the plurality of main colors are determined based on the distance on the image between the intermediate color pixels and the main color pixels at both ends of the line segment. The image processing apparatus according to attachment 1 or 2, wherein one set is determined from the set of colors.
(Appendix 4)
An input section for inputting a specified color;
The image processing apparatus according to any one of supplementary notes 1 to 3, further comprising: a pattern extraction unit that extracts a pattern corresponding to the specified color from the image generated by the generation unit.
(Appendix 5)
Based on the result of associating the color information of each pixel of the image with the area of the color space, the main colors including the foreground color and background color of the image are extracted,
Among the extracted main colors, calculate a line segment in which an intermediate color indicating a color other than the main color exists on a line between any two main colors in the color space;
For each intermediate color in the image, find two primary colors that minimize the distance between the intermediate color and the line segment in the color space, determine which of the two primary colors the intermediate color belongs to,
An image processing method in which a computer executes processing for generating an image in which each intermediate color in the image is replaced with the determined main color.
(Appendix 6)
The process of calculating the line segment is as follows:
The image processing method according to appendix 5, wherein all line segments between any two main colors in the color space are calculated, and line segments that do not have the intermediate color on the line segments are deleted.
(Appendix 7)
Based on the result of associating the color information of each pixel of the image with the area of the color space, the main colors including the foreground color and background color of the image are extracted,
Among the extracted main colors, calculate a line segment in which an intermediate color indicating a color other than the main color exists on a line between any two main colors in the color space;
For each intermediate color in the image, find two primary colors that minimize the distance between the intermediate color and the line segment in the color space, determine which of the two primary colors the intermediate color belongs to,
A program that causes a computer to execute processing for generating an image in which each intermediate color in the image is replaced with the determined main color.
(Appendix 8)
The process of calculating the line segment is as follows:
The program according to appendix 7, wherein all line segments between any two main colors in the color space are calculated, and line segments that do not have the intermediate color on the line segments are deleted.

DESCRIPTION OF SYMBOLS 10, 40 Image processing apparatus 20 Reading part 30 Display part 10 Electronic pen 101 Control part 102 Main memory part 103 Auxiliary memory part 104 Communication part 105 Drive apparatus 201 Image input part 202 Main color calculation part 203 Line segment calculation part 204 Main color determination Sections 205 and 302 Image generation sections 206 and 303 Pattern extraction section 301 Designated color input section

Claims (6)

A main color extraction unit that extracts the main colors including the foreground color and the background color of the image based on the result of associating the color information of each pixel of the image with the area of the color space;
Of the main colors extracted by the main color extraction unit, a combination of two different main colors is obtained, a line segment between the two main colors is calculated, and the color between the main colors is calculated from the calculated line segment. a line segment calculation unit to delete a line segment intermediate color does not occur, to obtain the segment to which the intermediate color is generated between the two major color space,
For each intermediate color in the image, a determination is made to determine two primary colors that minimize the distance between the intermediate color and the line segment in the color space, and determine which of the two primary colors the intermediate color belongs to And
An image processing apparatus comprising: a generation unit configured to generate an image in which each intermediate color in the image is replaced with a main color determined by the determination unit. The determination unit
When there are a plurality of sets of two main colors having the minimum distance, the plurality of main colors are determined based on the distance on the image between the intermediate color pixels and the main color pixels at both ends of the line segment. The image processing apparatus according to claim 1, wherein one set is determined from the set of colors. An input section for inputting a specified color;
The pattern extraction part which extracts from the image produced | generated by the said production | generation part the pattern of the principal color of the same color of the said designated color, or the principal color of the color most similar to this designated color, These are provided. Image processing device. Based on the result of associating the color information of each pixel of the image with the area of the color space, the main colors including the foreground color and background color of the image are extracted,
Among the extracted main colors, a combination of two different main colors is obtained to calculate a line segment between the two main colors, and an intermediate color is generated in the color space between the calculated main line and each main color. delete was non line, obtains a line segment the intermediate color is generated between the two main colors,
For each intermediate color in the image, find two primary colors that minimize the distance between the intermediate color and the line segment in the color space, determine which of the two primary colors the intermediate color belongs to,
An image processing method in which a computer executes processing for generating an image in which each intermediate color in the image is replaced with the determined main color. Based on the result of associating the color information of each pixel of the image with the area of the color space, the main colors including the foreground color and background color of the image are extracted,
Among the extracted main colors, a combination of two different main colors is obtained to calculate a line segment between the two main colors, and an intermediate color is generated in the color space between the calculated main line and each main color. delete was non line, obtains a line segment the intermediate color is generated between the two main colors,
For each intermediate color in the image, find two primary colors that minimize the distance between the intermediate color and the line segment in the color space, determine which of the two primary colors the intermediate color belongs to,
A program that causes a computer to execute processing for generating an image in which each intermediate color in the image is replaced with the determined main color. The determination unit
When three or more main colors are arranged in a straight line in the color space, the two main colors having the shortest distance are obtained from the distances between the intermediate colors and the main colors on the image, and the intermediate colors are the two main colors. The image processing apparatus according to claim 1, wherein the image processing apparatus determines which one of them belongs.