JP5245949B2 - Image processing apparatus and image reading apparatus - Google Patents

Description

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

  For example, for an image read by an image reading apparatus, there is a so-called image area separation technique in which an image area is divided according to attributes such as lines, surface areas, characters, and natural images included in the image. Japanese Patent Application Laid-Open No. H10-228561 discloses an image area separation technique for determining whether an image image, a font image, or a graphic image. Patent Document 2 discloses a technique for adaptively creating an outline according to an attribute recognized for an image.

JP-A-8-9148 JP 2007-129557 A

An object of the present invention is to express a plurality of representation formats of image data corresponding to each image area included in an image from the colors of pixels drawn adjacent to each other in the image area or the arrangement pattern of pixels constituting the image. It is to provide a technique for determining which of the two to express.

In order to solve the above-described problem, an image processing apparatus according to claim 1 of the present application includes an acquisition unit that acquires image data in which a color of each pixel constituting an image is described, and an image acquired by the acquisition unit. Separating means for dividing the image represented by the data into one or a plurality of image areas by labeling processing, and for each of the one or a plurality of image areas divided by the dividing means , an element to be rendered in the image area Image data describing the rendering process with numerical values or mathematical expressions, image data corresponding to the image area subjected to reversible compression processing, or image data corresponding to the image area subjected to irreversible compression processing comprising the and generating means for generating any of the image data, said generating means is adjacent in the image region separated by said separator means An image obtained by performing irreversible compression processing on image data representing the image area in the first case where the density or lightness of the prime color changes more gradually than the predetermined change amount between the adjacent pixels. In a second case where data is generated and the color combination of the pixels included in the image area matches a predetermined color combination in a case other than the first case, the image area Image data describing the process of drawing an element by numerical values or mathematical formulas is generated, and when neither the first case nor the second case is performed, a reversible compression process is performed on the image data representing the image area. It is characterized by generating generated image data .

An image processing apparatus according to claim 2 of the present application includes an acquisition unit that acquires image data in which the color of each pixel constituting an image is described, and an image represented by the image data acquired by the acquisition unit. Separation means for dividing into one or a plurality of image areas by a labeling process, and processing for drawing an element to be drawn in the image area for each of the one or a plurality of image areas divided by the separation means Image data described by mathematical expressions, image data corresponding to the image area subjected to reversible compression processing, or image data corresponding to the image area subjected to irreversible compression processing Generating means for generating any of the above, and the generating means constitutes a character image among the pixels included in the image data acquired by the acquiring means. When an image region including pixels whose degree of common with a predetermined pixel arrangement pattern exceeds a threshold is extracted, and the image region partitioned by the partitioning unit overlaps the extracted image region, Image data in which a process of drawing the element in the image area delimited by the delimiting means is described by numerical values or mathematical expressions is generated.

An image reading apparatus according to claim 3 of the present application reads an image formed on a recording medium, generates image data representing the image, and an image represented by the image data generated by the reading unit. Is divided into one or a plurality of image areas by a labeling process, and for each of the one or a plurality of image areas divided by the separation means, a process of drawing an element to be drawn in the image area Image data described by numerical values or mathematical expressions, image data obtained by performing reversible compression processing on image data corresponding to the image region, or image data obtained by performing irreversible compression processing on image data corresponding to the image region comprises a generating means for generating one of out, said generating means adjacent the image area delimited by the delimiting means pixel In the first case where the color density or lightness changes more slowly than the predetermined change amount between the adjacent pixels, image data obtained by performing irreversible compression processing on the image data representing the image area In a second case where the combination of the colors of the pixels included in the image area matches a predetermined color combination, the element is added to the image area. An image obtained by generating image data describing a drawing process by a numerical value or a mathematical expression, and applying reversible compression processing to the image data representing the image area when neither of the first case and the second case is generated It is characterized by generating data.

An image reading apparatus according to claim 4 of the present application reads an image formed on a recording medium, generates image data representing the image, and an image represented by the image data generated by the reading unit. Is divided into one or a plurality of image areas by a labeling process, and for each of the one or a plurality of image areas divided by the separation means, a process of drawing an element to be drawn in the image area Image data described by numerical values or mathematical expressions, image data obtained by performing reversible compression processing on image data corresponding to the image region, or image data obtained by performing irreversible compression processing on image data corresponding to the image region comprises a generating means for generating one of out, said generating means, among the pixels included in the image data acquired by the acquisition unit Extracting an image area including pixels whose degree of commonness with a predetermined pixel pattern constituting the character image exceeds a threshold value, and the image area partitioned by the partitioning means is the extracted image area In the case of overlapping, image data in which the process of drawing the element in the image area delimited by the delimiting means is described by numerical values or mathematical expressions is generated.

According to the image processing device according to claim 1 of the present application, one of a plurality of expression formats is set as an expression format corresponding to the image in accordance with the colors of pixels drawn adjacent to each other in the image region. You can choose.
According to the image processing apparatus according to claim 2 of the present application, it is possible to determine whether or not the process of drawing the image should be described by numerical values or mathematical expressions based on the arrangement pattern of the pixels constituting the image .
According to the image reading device according to claim 3 of the present application, any one of a plurality of expression formats is set as an expression format corresponding to the image in accordance with the colors of pixels drawn adjacent to each other in the image area. You can choose.
According to the image reading apparatus described in claim 4 of the present application, based on the arrangement pattern of the pixels constituting the image, it can be determined whether or not the process of drawing the image should be described by numerical values or mathematical expressions.

It is a block diagram for demonstrating the whole structure of an image processing apparatus. It is a block diagram which shows the functional structure of the information processing part which concerns on 1st Embodiment. It is a block diagram which shows the functional structure of the information processing part which concerns on 2nd Embodiment. It is a block diagram which shows the functional structure of the information processing part which concerns on 3rd Embodiment. It is a figure which shows the example of the image read by the scanner of an image processing apparatus.

1. Definitions In the following embodiments, an “image region” is a region where an image is drawn in an image.
The “raster system” is a system in which an image is divided into units called pixels arranged in a grid, and color information (tone and gradation) represented by each pixel is described for each pixel.
A “raster image” is an image expressed in a raster format.
“Resolution” is a value indicating the number of pixels arranged per unit length in a raster image. Here, the unit length is, for example, inches, and the resolution unit is “dpi” indicating the number of pixels per inch.
“Vector information” is information in which each element such as a line, a surface area, and a character to be drawn is defined in an abstract space, and a process of drawing each element is described by a numerical value or a mathematical expression. For example, a Bezier curve parameter is used for the description of the vector information.
The “vector method” is a method for drawing an element defined by vector information for each element. Specifically, the vector method means the coordinates of the start and end points of the line, color, thickness, how to bend, the color of the surface surrounded by the line, character code and character attributes (size and font), etc. This is a method expressed by a mathematical formula.
A “vector image” is an image expressed by a vector method.
“Rasterization” refers to converting a vector image into a raster image. If the size and resolution of the image are determined, rasterization can be performed by determining the color information of each pixel according to the drawing information included in the vector image.
“Vectorization” refers to converting a raster image into a vector image.
The “connected component” refers to a binary image corresponding to an image in which pixels having the same value are connected to each other to form one lump.
The “drawing color” is a color in which a drawing target is drawn in the image. For example, the color Cf of the character string “technical problem” in the drawing target Z3 in FIG. 5 and the color Cb filling the inside of the ellipse surrounding the character string are the “drawing color” drawing the drawing target Z3. Is.
The “non-drawing color” is a color that is not a drawing color and corresponds to the color of the recording medium in the recording medium on which the image is formed. For example, the color Cx surrounding the drawing target Z3 in FIG. 5 is a color that is not a drawing color, that is, a “non-drawing color”.
A “photographic image” refers to a raster image obtained by photographing natural objects mainly by an optical technique, and a raster image equivalent thereto, which is difficult to vectorize.
The “compression process” is a process of converting data that represents a target in a state where the amount of data is reduced.
“Reversible compression processing” refers to compression processing capable of restoring data before compression processing based only on data after compression processing.
The “irreversible compression process” refers to a compression process in which data before the compression process cannot be restored based only on the data after the compression process.

2. First Embodiment A configuration of an image processing apparatus 10 according to a first embodiment of the present invention will be described.
FIG. 1 is a block diagram for explaining the overall configuration of the image processing apparatus 10. As shown in FIG. 1, the image processing apparatus 10 includes an information processing unit 1, a scanner 2, and an image forming unit 3. The inner side surrounded by a two-dot chain line in FIG. The CPU 11 controls each unit of the information processing unit 1 by reading and executing a computer program (hereinafter simply referred to as a program) stored in the ROM 12. For example, the CPU 11 functions as an image area dividing unit and a vectorizing unit described later. The ROM 12 is a read-only nonvolatile storage device composed of a semiconductor element or the like. The ROM 12 stores various programs and BIOS (Basic Input / Output System). The RAM 13 is used as a work area when the CPU 11 executes a program. The RAM 13 has an area for storing data representing a vector image (hereinafter referred to as vector image data) and data representing a raster image (hereinafter referred to as raster image data). Note that these data representing an image may be subjected to data compression processing. A VRAM (Video RAM) 14 is a RAM that stores raster image data. The input unit 15 is an interface with an external input device such as a scanner or a computer, and receives image data under the control of the CPU 11. Here, the input unit 15 receives raster image data input from the scanner 2. The output unit 16 outputs the image data to an external device such as an image forming unit or a liquid crystal display medium under the control of the CPU 11. Here, the output unit 16 outputs the image data to the image forming unit 3. Each unit of the information processing unit 1 is connected via a bus 19.

  FIG. 2 is a block diagram showing a functional configuration of the information processing unit 1 according to the first embodiment of the present invention. Each unit surrounded by a two-dot chain line frame 11 in FIG. 2 is a function realized by the CPU 11 of the information processing unit 1. The acquisition unit 110 is a unit by which the CPU 11 acquires raster image data G0 from the scanner 2. Specifically, the CPU 11 causes the optical reading device included in the scanner 2 to read an image drawn on a recording medium such as paper, and the raster image data G0 corresponding to the image is input via the input unit 15 and the bus 19. Obtain it and store it in the RAM 13 or VRAM 14. The acquired raster image data G0 is supplied to the image area delimiting means 111.

  The image area dividing means 111 is a means for dividing the image represented by the supplied raster image data G0 into one or a plurality of image areas in which some image is drawn by a labeling process. Specifically, the CPU 11 compares the color of each pixel of the raster image data G0 stored in the RAM 13 or VRAM 14 with a threshold value, thereby converting the raster image data G0 into a binary image composed of two types of pixels. When converting to a binary image, the CPU 11 scans every other scanning line from the raster image data G0, for example, to lower the resolution or remove saturation information, thereby performing inspection. May be generated, and the color of each pixel of the generated image data may be compared with a threshold value. Then, the CPU 11 performs a labeling process on the generated binary image to extract the connected pixel group as a drawing pixel, and divides a rectangle circumscribing the drawing pixel as an image region. Each image region partitioned by the image region partitioning unit 111 is supplied to the first determination unit 112.

  The first determination unit 112 is a unit that determines, for each supplied image area, whether or not the image area is a photographic image based on the color density or brightness of the pixels in the image area. Specifically, the CPU 11 compares the amount of change in density or brightness with a predetermined amount of change for the colors of pixels drawn adjacent to each other in the supplied image area. If the color change amount of these pixels is more gradual than the predetermined change amount, the CPU 11 determines that this image region is a photographic image, and otherwise, this image region is determined as a photographic image. It is determined that it is not a photographic image and processing is performed.

  When the first determination unit 112 determines that the image area is a photographic image, the irreversible compression unit 114 generates image data obtained by performing irreversible compression processing on the raster image data G0 corresponding to the image area. It is means to do. As the irreversible compression process, a compression process combining encoding according to the appearance frequency of the color and data quantization is used. Thereby, for example, image data expressed in a format such as JPEG (Joint Photographic Experts Group) is generated. According to the irreversible compression processing, the data amount reduction effect is higher than that of the reversible compression processing, and therefore a data amount reduction effect for a photographic image having a large data amount is generally expected.

  When the first determination unit 112 determines that the image area is not a photographic image, the second determination unit 113 matches the color combination of pixels drawn in the image area with a predetermined color combination. It is means for determining whether or not. The ROM 12 and the RAM 13 store an OS (Operating System) which is a basic program for the CPU 11 to control the information processing unit 1. The OS includes a color palette such as 16 colors or 256 colors and the like. A combination of colors to be called is predetermined. Thereby, this color palette is used in common by various programs read by the CPU 11 that executes the OS. The CPU 11 as the second determination unit 113 samples the color of the pixel drawn in the image area determined not to be a photographic image by the first determination unit 112, and compares this with the color combination in the color palette described above. . Then, when the two compared completely match, the CPU 11 determines that the color of the pixel drawn in the image area matches the predetermined color combination. Note that the CPU 11 determines in advance the color of the pixel drawn in the image area in the case where a part of the two compared matches, the difference between the two, or the sum of the differences does not exceed a predetermined value. It may be determined that the set combination of colors matches.

  When the second determination unit 113 determines that the color of the pixel drawn in the image area does not match a predetermined color combination, the reversible compression unit 115 has raster image data G0 corresponding to the image area. This is means for generating image data that has been subjected to reversible compression processing. Thereby, for example, image data expressed in a format such as PNG (Portable Network Graphics) is generated. The lossless compression process is less effective in reducing the amount of data compared to the lossy compression process, but if the image has a combination of pixel colors that matches a predetermined one, the data amount is a photographic image. Therefore, reversible compression processing is sufficient for such an image.

When the second determination unit 113 determines that the color of the pixel drawn in the image area matches a predetermined color combination, the vectorization unit 116 determines the raster image data G0 corresponding to the image area. It is a means for vectorizing and generating image data of a vector image. Thereby, the drawing target drawn in the image area is represented by a numerical value or a mathematical expression.
The case where the color of the pixel drawn in the image area matches the predetermined color combination indicates that there is a high possibility that the image area is drawn according to the color palette described above. As described above, this color palette is commonly used in various programs, and is often used particularly when drawing a drawing target by a vector method. That is, using this property, either the lossless compression unit 115 or the vectorization unit 116 is selected as a configuration for performing processing on the image region in accordance with the determination result of the second determination unit 113.

  As described above, processing by any one of the lossy compression unit 114, the lossless compression unit 115, and the vectorization unit 116 is performed according to the determination results of the first determination unit 112 and the second determination unit 113. The plurality of image data generated by performing any one of these processes are combined into one and stored in the RAM 13 or the like as composite image data G1. The raster image data G0 acquired by the acquisition unit 110 is determined for each image area because it is determined for each image area whether or not it should be drawn by a vector method based on the combination of drawing colors. The judgment process is faster than when there is no such information. Based on such determination, a format suitable for each drawing target is assigned, converted into image data in that format, and stored in the RAM 13 or the like as composite image data G1. Since the image data corresponding to each image area can be extracted from the stored composite image data G1, for example, enlargement / reduction, rotation / inversion, color change, etc. for each of these image data Reuse such as performing the above process is realized.

  5A to 5C are diagrams showing examples of images read by the scanner 2 of the image processing apparatus 10 described above. The drawing target Z1 in FIG. 5A is a photographic image or illustration in which the copying machine and its user are drawn, and the drawing target Z2 in FIG. 5B is a graph drawn using a color palette. is there. The drawing target Z1 is not assumed to be decomposed into parts constituting it and subjected to processing such as enlargement / reduction, rotation / reversal, and color change. It is assumed to be used. When the drawing target Z1 is a photographic image, the information processing unit 1 determines that the image is a photographic image based on the drawing color density or lightness change amount of the drawing target Z1 in accordance with the processing procedure described above. The image data is subjected to lossy compression processing. In addition, when the drawing target Z1 is not drawn using a pre-stored color palette, the information processing unit 1 is assumed to be decomposed into parts and reused according to the processing procedure described above. It is determined that the image is not an illustration, and lossless compression processing is performed on the image data. On the other hand, since the drawing target Z2 is a graph drawn using a color palette, the information processing unit 1 represents the drawing target Z2 as image data vectorized by the vectorization means 116 in accordance with the processing procedure described above. .

3. Second Embodiment Next, a second embodiment of the present invention will be described. The overall configuration of the image processing apparatus 10 according to the second embodiment of the present invention is the same as that of the first embodiment, and a description thereof will be omitted.
FIG. 3 is a block diagram showing a functional configuration of the information processing unit 1 according to the second embodiment of the present invention. In FIG. 3, the functional configuration common to the first embodiment is denoted by the same reference numerals as those in FIG. Each means surrounded by a two-dot chain line frame 11 in FIG. 3 is a function realized by the CPU 11 of the information processing unit 1. In the information processing unit 1 of the second embodiment, the second determination unit 113 is not provided, and a third determination unit 121 is provided instead of the second determination unit 113. In addition, character area extraction means 120 is provided.

  The character region extraction unit 120 is a character region in which a character may be drawn from the raster image data G0 acquired by the acquisition unit 110 in an area where the degree of commonness with a predetermined pixel arrangement pattern exceeds a threshold value. It is an example of the extraction means which extracts as. Specifically, the CPU 11 compares each pixel of the acquired raster image data G0 with the above array pattern. Here, as an example of a predetermined pixel arrangement pattern, “consisting of two color pixels having a contrast exceeding a threshold” or “one of the two colors in the vertical direction “Appear as straight lines with equal intervals”. By calculating the degree of coincidence with the reference with these arrangement patterns as a reference, the CPU 11 that is the character area extraction means 120 calculates the degree common to the arrangement pattern and extracts an area whose degree exceeds the threshold. To do.

  Note that the horizontal direction and vertical direction here are determined by the scanning direction when the image is read by the scanner 2, but depending on the reading state and the design of the original image, the arrangement of character strings described on paper or the like The direction and the scanning direction of the scanner 2 may not match. For example, the character region extraction unit 120 may determine that the direction of the straight lines appearing by a plurality of pixels of the one color described above does not coincide with the scanning direction of the scanner 2. However, the degree of commonality between the region and the array pattern may be increased.

  The third determination unit 121 is a unit that determines whether or not the image area partitioned by the image region partitioning unit 111 overlaps with the character region extracted by the character region extraction unit 120. The CPU 11 compares the image area delimited by the image area delimiting means 111 with the character area extracted by the character area extracting means 120, and determines whether or not they overlap each other. If they do not overlap, the CPU 11 reversibly compresses the raster image data G0 corresponding to the image area by the lossless compression means 115, and if they overlap, the raster image data corresponding to the image area. G0 is vectorized by the vectorizing means 116.

  As described above, according to the determination results of the first determination unit 112 and the third determination unit 121, the processing by any one of the lossy compression unit 114, the lossless compression unit 115, and the vectorization unit 116 is performed, and the generated plural Are combined and stored in the RAM 13 or the like as composite image data G1. For the raster image data G0 acquired by the acquisition unit 110, it is determined whether or not each image area overlaps with the character area, and the image area that is determined to overlap with the character area is to be drawn in the vector method. This is an area. Whether it is an image area to be drawn by the vector method or not is determined by whether or not it overlaps with the character area, so that the determination process can be completed more quickly than when such a configuration is not used. Become.

  For example, the drawing target Z3 shown in FIG. 5 is a character string “technical problem” drawn in the color Cf in an elliptical shape filled with Cb other than the color of the recording paper. Since this character string is extracted as a character region by the character region extraction unit 120, the extracted character region overlaps with the image region partitioned by the image region partitioning unit 111. For this reason, the information processing section 1 vectorizes the image area depicting the drawing target Z3 by the vectorizing means 116.

4). Third Embodiment Next, a third embodiment of the present invention will be described. The overall configuration of the image processing apparatus 10 according to the third embodiment of the present invention is the same as that of the first embodiment, and a description thereof will be omitted.
FIG. 4 is a block diagram showing a functional configuration of the information processing unit 1 according to the third embodiment of the present invention. In FIG. 4, the functional configuration common to the first embodiment and the second embodiment is denoted by the same reference numerals as those in FIG. 2 or FIG. Each means surrounded by a two-dot chain line frame 11 in FIG. 4 is a function realized by the CPU 11 of the information processing unit 1. The information processing unit 1 according to the third embodiment includes the second determination unit 113 according to the first embodiment, the character area extraction unit 120 according to the second embodiment, and the third determination unit 121. Fourth determination means 130 is provided.

  Based on the determination result of the second determination unit 113 and the determination result of the third determination unit 121, the fourth determination unit 130 performs any processing of the lossless compression unit 115 and the vectorization unit 116 on the image region. It is a means to determine whether to perform. For example, the fourth determination unit 130 determines that the color of the pixel drawn in the image area matches the predetermined color combination by the second determination unit 113 and the third determination unit 121 determines that the image Only when it is determined that the area and the character area overlap, the raster image data G0 corresponding to the image area may be vectorized to generate image data of the vector image. The fourth determination unit 130 determines that the second determination unit 113 determines that the color of the pixel drawn in the image area matches a predetermined color combination, or the third determination unit 121 determines that the color combination is predetermined. When it is determined that the image area and the character area overlap, the image data of the vector image described above may be generated.

  With respect to the raster image data G0 acquired by the acquisition means 110, it is determined for each image area whether or not it should be drawn by the vector method based on both the color combination of drawn pixels and the inclusion relation of the character area. The Therefore, the accuracy of the determination is higher than when the above configuration is not used.

5. Modification The above is the description of the embodiment, but the contents of this embodiment can be modified as follows. Further, the following modifications may be combined.
(1) In the third embodiment and the fourth embodiment described above, the third determination unit 121 determines whether the image region partitioned by the image region partitioning unit 111 overlaps the character region extracted by the character region extraction unit 120. However, before this determination, the character region extracted by the character region extraction means 120 is further subjected to pattern matching processing to extract a region where the character is specified (hereinafter referred to as a character specifying region). The third determination unit 121 may determine whether or not the image area overlaps with the character specifying area. That is, after the character area extracting unit 120, a matching unit 122 that performs pattern matching based on font data and extracts a character specifying region may be provided (see FIGS. 3 and 4). Specifically, the CPU 11 converts each pixel of the character area extracted by the character area extracting unit 120 into bitmap font font data, which is a predetermined pixel arrangement pattern, or rasterized font data of an outline font. The font name, font size, and character code of the character described in the extracted character area are specified depending on whether the pixel pattern matches. Then, only the character specifying area in which the described character is specified may be supplied to the third determination unit 121.
It should be noted that the “match” of this pattern may have a width, and a case where pixels having a ratio exceeding the threshold value match may be regarded as “pattern match”.

(2) In the above-described embodiment, the information processing unit 1 is built in the image processing apparatus 10, but the information processing unit 1 may be realized by a personal computer.
2 is a function realized by the CPU 11 of the information processing unit 1, but these means may be realized by other than the CPU 11. For example, each of these means may be realized by a dedicated image processor.

(3) In the second embodiment and the fourth embodiment described above, when the second determination unit 113 determines that the image region is not a photographic image in the first determination unit 112, the pixels drawn in the image region It has been determined whether or not the color combination matches a predetermined color combination, but before the second determination unit 113, a color reduction unit 117 for reducing the drawing color of the image area is provided. (See FIGS. 2 and 4). That is, the CPU 11 may perform a process of reducing the drawing color of the image area before performing the process of the second determination unit 113. As an algorithm of the color reduction processing, for example, the algorithm shown in the following steps S401 to S407 can be cited.

Step S401: Based on the calculated histogram, a color with a low frequency is merged with a color close to that color and a frequency that is higher than the frequency of the color.
Step S402: If the component color is less than or equal to the target number of drawing colors, the process is terminated.
Step S403: A pair of maximum color differences is searched with the whole as one color group.
Step S404: The group of interest is divided into two with priority on color difference.
Step S405: If the number of groups is less than or equal to the target number of colors, the process ends.
Step S406: A group having the maximum color difference pair is searched from all the groups.
Step S407: Return to step S404.

DESCRIPTION OF SYMBOLS 1 ... Information processing part, 10 ... Image processing apparatus, 11 ... CPU, 12 ... ROM, 13 ... RAM, 130 ... 4th determination means, 14 ... VRAM, 15 ... Input part, 16 ... Output part, 19 ... Bus, 2 DESCRIPTION OF SYMBOLS Scanner 3 ... Image formation part 110 ... Acquisition means 111 ... Image area | region division means 112 ... 1st determination means 113 ... 2nd determination means 114 ... Lossless compression means 115 ... Lossless compression means 116 ... Vectorization means, 117 ... color reduction means, 120 ... character area extraction means, 121 ... third determination means, 122 ... collation means, G0 ... raster image data, G1 ... composite image data.

Claims (4)

Obtaining means for obtaining image data in which the color of each pixel constituting the image is described;
Separating means for dividing the image represented by the image data acquired by the acquiring means into one or a plurality of image areas by labeling processing;
For each of one or more image areas delimited by the delimiter, image data describing processing for drawing an element to be rendered in the image area by numerical values or mathematical expressions, and image data corresponding to the image area Generating means for generating either reversible compression processing image data or image data corresponding to the image area subjected to irreversible compression processing ;
The generating means includes
In the first case, the color density or brightness of the adjacent pixels in the image area delimited by the delimiter means changes more slowly than the predetermined amount of change between the adjacent pixels. Generate image data that has been subjected to irreversible compression processing.
Processing for drawing the element in the image area in a second case where the combination of the colors of the pixels included in the image area matches a predetermined color combination, except in the case of the first case Generate image data that describes numerically or mathematically,
An image processing apparatus that generates image data obtained by performing reversible compression processing on image data representing the image area when neither of the first case and the second case . Obtaining means for obtaining image data in which the color of each pixel constituting the image is described;
Separating means for dividing the image represented by the image data acquired by the acquiring means into one or a plurality of image areas by labeling processing;
For each of one or more image areas delimited by the delimiter, image data describing processing for drawing an element to be rendered in the image area by numerical values or mathematical expressions, and image data corresponding to the image area Generating means for generating either reversible compression processing image data or image data corresponding to the image area subjected to irreversible compression processing ;
The generating means includes
Among the pixels included in the image data acquired by the acquisition means, an image region including pixels whose degree of commonness with a predetermined pixel array pattern constituting the character image exceeds a threshold value is extracted.
When the image area delimited by the delimiter overlaps with the extracted image area, image data that describes the process of drawing the element in the image area delimited by the delimiter by numerical value or mathematical expression is generated An image processing apparatus. Reading means for reading an image formed on a recording medium and generating image data representing the image;
Separating means for dividing an image represented by the image data generated by the reading means into one or a plurality of image areas by labeling processing;
For each of one or more image areas delimited by the delimiter, image data describing processing for drawing an element to be rendered in the image area by numerical values or mathematical expressions, and image data corresponding to the image area Generating means for generating either reversible compression processing image data or image data corresponding to the image area subjected to irreversible compression processing ;
The generating means includes
In the first case, the color density or brightness of the adjacent pixels in the image area delimited by the delimiter means changes more slowly than the predetermined amount of change between the adjacent pixels. Generate image data that has been subjected to irreversible compression processing.
Processing for drawing the element in the image area in a second case where the combination of the colors of the pixels included in the image area matches a predetermined color combination, except in the case of the first case Generate image data that describes numerically or mathematically,
An image reading apparatus that generates image data in which reversible compression processing is performed on image data representing the image area when neither the first case nor the second case is performed . Reading means for reading an image formed on a recording medium and generating image data representing the image;
Separating means for dividing an image represented by the image data generated by the reading means into one or a plurality of image areas by labeling processing;
For each of one or more image areas delimited by the delimiter, image data describing processing for drawing an element to be rendered in the image area by numerical values or mathematical expressions, and image data corresponding to the image area Generating means for generating either reversible compression processing image data or image data corresponding to the image area subjected to irreversible compression processing ;
The generating means includes
Among the pixels included in the image data acquired by the acquisition means, an image region including pixels whose degree of commonness with a predetermined pixel array pattern constituting the character image exceeds a threshold value is extracted.
When the image area delimited by the delimiter overlaps with the extracted image area, image data that describes the process of drawing the element in the image area delimited by the delimiter by numerical value or mathematical expression is generated An image reading apparatus.

Images