JP2013153273A - Image processing device, image reading device, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make it possible to select a more suitable compression processing technique in accordance with the contents of image data.SOLUTION: A compression condition determination part 130 includes: a color number calculation part 131 for calculating the number of colors constituting preprocessed image data; an object separation part 132 for performing object separation on the preprocessed image data; a gradation region extraction part 133 for extracting a gradation region in a target page on the basis of a result of the object separation; a uniform color region extraction part 134 for extracting a uniform color region in the target page on the basis of a result of the object separation by the object separation part 132; and a type determination part 135 for determining, on the basis of a result of the color number calculation by the color number calculation part 131, a result of the gradation region extraction by the gradation region extraction part 133, and a result of the uniform color region extraction by the uniform color region extraction part 134, whether the image data in the target page is a type, in which a first compression technique is to be applied, or a type, in which a second compression technique is to be applied.

Description

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

Image data obtained by reading a document is subjected to compression processing and converted into image data having a smaller capacity.
As a prior art described in the publication, a plurality of color information constituting image information is extracted, converted to a specific color to which the extracted color information belongs, and the image information converted into a specific color is converted for each specific color There is an image processing apparatus that compresses image information separated for each specific color, compresses the image information for each specific color, and outputs the compressed image information for each specific color (PTL 1). reference).

JP 2010-232954 A

Here, reducing (decreasing) the number of colors included in the image data is certainly one of the useful techniques for reducing the volume of the image data after compression than before compression. . However, even when the number of colors constituting the image data is small, the volume of the image data after compression may be less likely to be smaller than that before compression.
An object of the present invention is to make it possible to select a more appropriate compression processing method in accordance with the contents of image data.

  According to a first aspect of the present invention, there is provided calculation means for calculating the number of colors constituting image data, gradation area extraction means for extracting gradation areas expressed by gradations in the image data, and the calculation means. When the calculated number of colors is equal to or less than a predetermined threshold value and the gradation area extracted by the gradation area extraction means does not exist, the image data is determined as the first type, The gradation area extracted by the gradation area extraction means when the number of colors calculated by the calculation means exceeds the threshold or the number of colors calculated by the calculation means is equal to or less than the threshold. When the image data is present, the image processing apparatus includes a determination unit that determines the image data as the second type.

According to a second aspect of the present invention, color reduction means for reducing the number of colors in the image data determined to be the first type, and compression processing is applied to the first type of image data reduced by the color reduction means. The image processing apparatus according to claim 1, further comprising: a first compression processing unit; and a second compression processing unit that performs a compression process on the image data determined to be the second type.
The invention according to claim 3 further includes a uniform color area extracting means for extracting a uniform color area expressed in a uniform color in the image data, wherein the determining means is configured such that the number of the colors calculated by the calculating means is The gradation area extracted by the gradation area extraction means does not exist, and the size of the uniform color area extracted by the uniform color area extraction means is predetermined. 3. The image processing apparatus according to claim 1, wherein the image data is determined to be the first type when smaller than the specified reference size. 4.

  According to a fourth aspect of the present invention, there is provided a reading unit that reads an image of a document, a calculation unit that calculates the number of colors constituting the image data read by the reading unit, and a floor expressed in gradation in the image data. A gradation area extracting means for extracting a tone area; and the number of colors calculated by the calculating means is equal to or less than a predetermined threshold and the gradation area extracted by the gradation area extracting means does not exist. In this case, the image data is determined to be the first type, and the number of colors calculated by the calculation unit exceeds the threshold, or the number of colors calculated by the calculation unit is less than or equal to the threshold. The image reading apparatus includes a determination unit that determines the image data as the second type when the gradation region extracted by the gradation region extraction unit exists.

  In the invention according to claim 5, the reading unit sequentially reads a plurality of pages of document to output a plurality of image data corresponding to the plurality of pages, and the determination unit outputs the plurality of image data to the plurality of image data. 5. The image reading apparatus according to claim 4, wherein the determination is performed for each page.

  According to a sixth aspect of the present invention, there is provided a computer with a function of calculating the number of colors constituting image data, a function of extracting a gradation region expressed by gradation in the image data, and the calculated color of the color When the number is equal to or less than a predetermined threshold and the extracted gradation area does not exist, the image data is determined as the first type, and the calculated number of colors exceeds the threshold, or A program that realizes a function of determining the image data as the second type when the calculated number of the colors is equal to or less than the threshold value and the extracted gradation area exists.

According to the first aspect of the present invention, it is possible to select a more appropriate compression processing method in accordance with the content of the image data, as compared with the case where the present configuration is not provided.
According to the second aspect of the present invention, it is possible to compress both the first type image data and the second type image data to a smaller capacity as compared with the case where the present configuration is not provided. it can.
According to the third aspect of the present invention, it is possible to select a more appropriate compression processing method in accordance with the content of the image data as compared with the case where the configuration is not provided.
According to the fourth aspect of the present invention, it is possible to select a more appropriate compression processing method according to the content of the image data as compared with the case where the present configuration is not provided.
According to the invention described in claim 5, it is possible to select a more appropriate compression processing method for each of a plurality of image data constituting one file, for example, as compared with the case where the present configuration is not provided. can do.
According to the sixth aspect of the present invention, it is possible to select a more appropriate compression processing method according to the content of the image data as compared with the case where the present configuration is not provided.

1 is a diagram showing a configuration of an image reading system in an embodiment of the present invention. FIG. 2 is a block diagram illustrating a hardware configuration of an image reading apparatus in the image reading system. It is a block diagram which shows the function structure of an image reading apparatus. It is a block diagram which shows the function structure of a compression condition determination part. It is a block diagram which shows the function structure of a color number calculation part. It is a figure for demonstrating the division | segmentation process of the color space in the color number calculation part provided in the compression condition determination part. It is a figure for demonstrating the method of the data separation by the color separation process part provided in the compression condition determination part. It is a flowchart for demonstrating the procedure of the process in a compression condition determination part. It is a flowchart for demonstrating the determination procedure of the compression processing method in a compression condition determination part. It is a figure which shows an example of the input image data read by the scanner.

Embodiments of the present invention will be described below in detail with reference to the accompanying drawings.
FIG. 1 is a diagram showing a configuration of an image reading system according to an embodiment of the present invention.
The image reading system includes an image reading device 10 and a terminal device 20 that are connected to each other via a network 30. Here, the image reading apparatus 10 has a function of reading an image formed on a set original. Further, the image reading apparatus 10 includes a document feeding device, and can read a document in a document bundle composed of a plurality of sheets (a plurality of pages) one by one in order. On the other hand, the terminal device 20 has a function of acquiring image data obtained by the image reading device 10 reading a document via the network 30.

FIG. 2 is a block diagram showing a hardware configuration of the image reading apparatus 10 in the image reading system shown in FIG.
An image reading apparatus 10 according to the present embodiment includes a CPU (Central Processing Unit) 11, a memory 12 including a ROM (Read Only Memory) and a RAM (Random Access Memory), an HDD (Hard Disk Drive), and an SSD (SSD). A communication device 14 that transmits and receives data (including image data) between the storage device 13 configured by Solid State Drive) and an external device such as the terminal device 10 via the network 30 and receives input from the user. In addition, a UI (User Interface) device 15 that outputs (displays) an instruction to the user and a scanner 16 as an example of a reading unit that reads an image of a document are provided. Further, the image reading apparatus 10 further includes a bus 18 that connects these components. The scanner 16 has a function of outputting full-color image data by reading, for example, RGB three-color images.

  In the image reading apparatus 10, the CPU 11 controls the operation of the image reading apparatus 10 including image processing by executing processing based on the control program read from the memory 12 or the storage device 13. The control program executed by the CPU 11 is stored in a memory medium such as a CD-ROM, for example, in addition to being stored in the memory 12 in advance, or provided to the CPU 11 or provided to the CPU 11 via the network 30. It is also possible to do.

FIG. 3 is a block diagram showing a functional configuration of the image reading apparatus 10 realized by executing the control program described above.
The image reading apparatus 10 according to the present embodiment includes the above-described scanner 16 and an image processing apparatus 100 that processes and outputs image data obtained by the scanner 16 reading a document. The image processing apparatus 100 also includes a preprocessing unit 110 that performs predetermined preprocessing on image data (input image data) input from the scanner 16, and image data that has been preprocessed by the preprocessing unit 110. A compression processing unit 120 that performs compression processing on (preprocessed image data). The input image data is input as a file including image data for one page or a plurality of pages.

  Here, for example, the pre-processing unit 110 has a function of performing gradation correction on the input image data, and a function of enlarging / reducing the input image data in accordance with the enlargement / reduction magnification designated via the UI device 15 or the like. A function for performing spatial filtering on the input image data, a function for converting the color space of the input image data, and the like are executed as necessary. In addition, the preprocessing unit 110 performs preprocessing for each page on input image data including one or a plurality of pages.

  On the other hand, the compression processing unit 120 includes a compression condition determination unit 130, a color separation processing unit 140, a first compression processing unit 150, a page composition unit 160, a second compression processing unit 170, and a file composition unit 180. It has.

  The compression condition determination unit 130 analyzes the input preprocessed image data and performs compression by the first compression method for each page or by a second compression method different from the first compression method. Decide whether to apply compression. Details of the first compression method and the second compression method will be described later. Hereinafter, in the compression condition determination unit 130, the image data of the page for which the application of the first compression method is determined is referred to as first image data, and the image data of the page for which the application of the second compression method is determined is the second image. Called data.

The color separation processing unit 140 performs a process of separating the first image data, for which the application of the first compression method has been determined by the compression condition determination unit 130, among the preprocessed image data, by color.
The first compression processing unit 150 as an example of the first compression processing unit performs compression processing using the first compression method for each color on the first image data separated by color by the color separation processing unit 140. .
The page composition unit 160 synthesizes the first image data for each color subjected to the compression processing by the first compression processing unit 150 in units of pages, thereby performing the first image data subjected to the first compression processing (compressed). First image data) is created.

  The second compression processing unit 170 as an example of the second compression processing unit applies the second compression to the second image data for which the application of the second compression method is determined by the compression condition determination unit 130 among the preprocessed image data. By performing compression processing using the two-compression method, second image data subjected to the second compression processing (compressed second image data) is created.

  The file composition unit 180 summarizes the input compressed first image data and / or compressed second image data based on the number of pages constituting the input image data as a basis and the page order, or one page or a plurality of data Output as a file (output image data) containing compressed image data for a page. The output image data is transmitted to, for example, the terminal device 20 via the network 30 illustrated in FIG.

FIG. 4 is a block diagram showing a functional configuration of the compression condition determination unit 130, which is realized by executing the control program described above.
The compression condition determination unit 130 according to the present embodiment includes a color number calculation unit 131, an object separation unit 132, a gradation region extraction unit 133, a uniform color region extraction unit 134, and a type determination unit 135. .

  The number-of-colors calculation unit 131 as an example of the calculation unit and the color reduction unit extracts one or a plurality of color information constituting the image for each page from the input preprocessed image data, and extracts the extracted color information. Is converted to the specific color to which the image belongs, the representative color is determined based on the converted specific color, and the result including the number of representative colors (number of colors) obtained is stored in the memory 12 (see FIG. 2). Remember me. The detailed configuration of the color number calculation unit 131 will be described later.

  The object separation unit 132 detects whether characters, line drawings, figures, and photographs are included for each page of input preprocessed image data. When the object separation unit 132 detects that the image data of the target page includes an object (in this example, at least one of a character, a line drawing, a figure, and a photo), the included character, line drawing, and figure are included. The range of the photograph in the image data is determined, and the determined character, line drawing, figure, and coordinate values indicating the range of the photograph are stored in the memory 12. In the following description, among the detection results by the object separation unit 132, an area where a character is detected is called a “character area”, an area where a line drawing is detected is called a “line drawing area”, and a figure is detected. This area is called a “graphic area”, and an area where a photograph is detected is called a “photo area”.

  The gradation area extraction unit 133 as an example of the gradation area extraction unit is based on the detection result by the object separation unit 132, and the area (floor) expressed by the gradation image from the graphic area and the photograph area of the target page. Key area) is extracted and stored in the memory 12. Various types of gradation area extraction processing are applied.

  Based on the detection result by the object separation unit 132, the uniform color region extraction unit 134 as an example of the uniform region extraction unit is a region (uniform color) expressed in a uniform color from the graphic region and the photograph region of the target page. Region) is extracted and stored in the memory 12. Further, the uniform color area extraction unit 134 determines the range of the uniform color area in the image data of the target page together with the presence of the uniform color area, and stores the coordinate value indicating the determined range of the uniform color area in the memory 12. Remember. Various types of uniform color region extraction processing are applied.

  The type determination unit 135 as an example of a determination unit is obtained based on the image data of the same target page, and is read from the memory 12, the color number calculation result by the color number calculation unit 131, and the gradation region extraction unit 133. Based on the gradation region extraction result, the uniform color region extraction result by the uniform color region extraction unit 134, and the uniform color region range, the image data of the target page is classified as a type to which the first compression technique is applied (first Whether to be a type to be applied to the second compression method (corresponding to a second type). A specific type determination procedure by the type determination unit 135 will be described later.

FIG. 5 is a block diagram illustrating a functional configuration of the color number calculation unit 131 realized by executing the control program described above.
The number-of-colors calculation unit 131 according to the present embodiment includes a smoothing unit 1311, an enhancement processing unit 1312, a frequency counting unit 1313, a counting result processing unit 1314, a ground color extracting unit 1315, a color extracting unit 1316, A 3D / LUT generation unit 1317 and a color replacement unit 1318 are provided.

The smoothing unit 1311 performs noise removal on the input preprocessed image data by performing a smoothing process for each page.
The enhancement processing unit 1312 performs enhancement processing on the preprocessed image data that has been smoothed using, for example, a 5 × 5 filter.
The frequency counting unit 1313 performs a process of counting the appearance frequency (histogram) of pixel values for the preprocessed image data that has been subjected to the smoothing process.

Here, the histogram generation by the frequency counting unit 1313 will be described.
FIG. 6 is a schematic diagram for explaining region division of the color space. In generating the histogram, the frequency counting unit 1313 divides the three-dimensional color space in the preprocessed image data for each page into a plurality of regions, and counts the frequency for each divided region.

  As shown in FIG. 6, for example, when the gradation values that can be taken in the RGB color space are 0 to 255 (8 bits), the frequency counting unit 1313 divides the RGB gradation values into 8 equal parts every 32 gradations. To do. Thereby, the RGB color space is divided into 8 × 8 × 8 = 512 regions. The frequency counting unit 1313 counts the frequency of pixel values for each of the 512 divided areas. The division unit is merely an example.

Returning to FIG.
The counting result processing unit 1314 performs a filtering process for extracting only the histograms for the divided areas counted by the frequency counting unit 1313 that exceed a predetermined frequency threshold. The counting result processing unit 1314 extracts a histogram peak using a three-dimensional second-order differential filter.

  The background color extraction unit 1315 performs a process of extracting the background color (background color) of the image data based on the histogram filtered by the counting result processing unit 1314. For example, the most frequent of the plurality of candidate colors that are preset ground colors is extracted as the ground color. Various types of ground color extraction processing are applied.

  The color extraction unit 1316 performs a process of extracting a specific color (representative color) from the histogram peaks extracted and filtered by the counting result processing unit 1314. Specifically, first, from the extracted histogram peaks (peak colors), a color lower than a preset saturation is excluded from the candidate colors. Next, a representative color is selected from the remaining peak colors. For the selection of the representative color, for example, a color whose feature value such as hue is separated by a predetermined amount or more is selected. Also, the number of representative colors should not exceed a preset upper limit. That is, the colors selected as representative colors are selected in order of decreasing frequency so as not to exceed the upper limit number of colors.

  The 3D / LUT generation unit 1317 generates a 3D / LUT (three-dimensional lookup table) for replacing the color of the smoothed preprocessed image data with the representative color extracted by the color extraction unit 1316. To do. That is, the 3D / LUT associates a predetermined pixel value range of image data with a selected representative color. Thereby, each pixel value of the image data is converted into a specific representative color associated with the range to which the pixel value belongs.

  The color replacement unit 1318 uses the 3D / LUT generated by the 3D / LUT generation unit 1317 to perform processing for replacing the pixel value of the preprocessed image data with one of the representative colors for each page. As a result, the preprocessed image data is reduced to the representative color.

  Note that the first image data output to the first compression processing unit 150 via the compression condition determination unit 130 has been subjected to the color reduction processing by the color replacement unit 1318. On the other hand, the second image data output to the second compression processing unit 170 via the compression condition determination unit 130 is the one before being subjected to the color reduction processing by the color replacement unit 1318.

  FIG. 7 is a schematic diagram for explaining data separation by the color separation processing unit 140 shown in FIG. The color separation processing unit 140 separates the first image data replaced with the representative color for each representative color to obtain layered data. The layer structure data includes the binarized pixel values of the image elements for each representative color and the information of the circumscribed rectangle including the image element of the representative color, that is, the coordinates of the starting point of the circumscribed rectangle in the page, the rectangle height And rectangular width information.

  In the example shown in FIG. 7, four colors of “red”, “blue”, “green”, and “gray” are selected as representative colors, which are separated for each representative color and output as layer structure data. The The image element data of each representative color is binarized.

  In addition to the representative color, the background color is also output as layer structure data. The background color data includes a landscape color value and information indicating the background. Since the background is specified for the entire page, it is not necessary to have rectangle information. Note that the background color may also have rectangular information (in this case, rectangular information of the entire page) as in the representative color data. As a result, the data structure does not distinguish between the representative color and the background color.

  The information (first image data for each color) separated by the color separation processing unit 140 for each representative color and background color (first image data for each color) is separated for each layer structure data (for each color) by the first compression processing unit 150. Compression processing (first compression technique) is performed. Here, since the data for each color is binarized, compression processing such as run-length encoding is performed. It should be noted that compression is not necessary in the structure including the color value and information indicating the background as the background color.

  Further, the page composition unit 160 shown in FIG. 3 performs a process of collecting and outputting the compressed representative color and background color layer structure data into a single file as a layer structure data format. An example of the data format of the layer structure is MRC (Mixed Raster Content).

  On the other hand, the second compression processing unit 170 shown in FIG. 3 directly performs the compression process on the second image data that has not been subjected to the above-described color reduction process (replacement with a representative color).

FIG. 8 is a flowchart for explaining a processing procedure in the compression condition determination unit 130 in a document reading operation using the image reading apparatus 10.
Here, first, preprocessed image data (file) is input from the preprocessing unit 110 to the compression condition determining unit 130 (step 11).
Next, the compression condition determination unit 130 sets n = 1 (step 12), and among the preprocessed image data input in step 11, the nth page (initially the first page) image data. Obtain (step 13).

Subsequently, the compression condition determination unit 130 determines a compression processing condition (first compression method or second compression method) for the image data of the nth page (step 14).
Thereafter, the compression condition determination unit 130 determines whether or not there are remaining pages in the preprocessed image data input in step 11 (step 15).
If an affirmative determination (Yes) is made in step 15, the compression condition determination unit 130 sets n = n + 1 (step 16), returns to step 13, and continues processing for the image data of the next page. On the other hand, when a negative determination (No) is made in step 15, the compression condition determination unit 130 completes a series of processes.

FIG. 9 is a flowchart for explaining a specific procedure in step 14 described above, that is, a procedure for determining a compression processing technique in the compression condition determining unit 130.
First, the color number calculation unit 131 calculates the number of representative colors based on the image data of the target page (step 141). Further, the object separation unit 132 performs object separation based on the image data of the target page. Based on the result of the object separation, the gradation area extraction unit 133 extracts the gradation area (step 142). Further, based on the object separation result, the uniform color area extraction unit 134 extracts the uniform color area (step 143) and extracts the size of the uniform color area (step 144).

  Then, the type determining unit 135 determines whether or not the number of representative colors obtained in step 141 is equal to or less than a predetermined threshold (for example, five colors) (step 145). When a negative determination (No) is made in step 145, the type determining unit 135 determines the compression method to be applied to the target page as the second compression method (step 149).

  If the determination in step 145 is affirmative (Yes), the type determination unit 135 next determines whether or not the target page has no gradation area based on the extraction result in step 142 (step 146). ). If a negative determination (No) is made in step 146, the type determining unit 135 determines the compression method to be applied to the target page as the second compression method (step 149).

  Furthermore, when a positive determination (Yes) is made in step 146, the type determination unit 135 next selects a uniform color area that is equal to or larger than a predetermined reference size for the target page based on the extraction results in steps 143 and 144. It is determined whether or not there has been (step 147). If a negative determination (No) is made in step 147, the type determining unit 135 determines the compression method to be applied to the target page as the second compression method (step 149). On the other hand, when a positive determination (Yes) is made in step 147, the type determining unit 135 sets the compression method to be applied to the target page to the first compression method (step 148), and completes a series of processes.

  In step 148, the first image data subjected to the color reduction processing is output as image data of the target page from the compression condition determination unit 130 to the first compression processing unit 150 (color separation processing unit 140). The On the other hand, in step 149, the second image data that has not been subjected to the color reduction process is output from the compression condition determination unit 130 to the second compression processing unit 170 as the image data of the target page.

Now, a procedure for determining a compression method to be applied to image data will be described with a specific example.
FIG. 10 is a diagram illustrating an example of input image data read by the scanner 16. In this example, the input image data is composed of image data for three pages.

  Here, the image data on the first page is obtained by reading an estimate. This estimate includes characters and line drawings (frames and lines) drawn in black, and characters and line drawings (company mark, approval mark, and person-in-charge mark) drawn in red.

  The image data on the second page is obtained by reading a magazine article. This article includes letters and line drawings drawn in black (such as maps), letters drawn in green (sites marked "Athens"), and photographs (photos of the temple). The photograph has a temple part composed of a gradation image including white and a sky part composed of a gradation image including blue.

  Further, the image data on the third page is obtained by reading a learning notebook or the like. This note includes letters (alphabet) drawn in black and graphics (parts overlapping “is”, “am”, “are”) drawn in pink. The portion drawn in pink is written on an English character image using, for example, a marker pen.

When these images are read by the image reading apparatus 10 of the present embodiment, the following compression processing is selected for each image data.
For example, when the first page is the target page, the number of colors is small, the gradation area does not exist, and the size of the uniform color area is smaller than the reference size. Is subject to application.
For example, when the second page is the target page, the number of colors is small, but the gradation area is present in the photographic area, so the image data of the second page is an application target of the second compression method.
Further, for example, when the third page is the target page, the number of colors is small, the gradation area does not exist, and the size of the uniform color area is smaller than the reference size. The compression method is applied.

  In the present embodiment, the first compression method or the first compression method is applied based on the number of colors in the target page, the presence / absence of a gradation region in the target page, and the presence / absence of a uniform color region equal to or larger than the reference size in the target page. Although the application of the two compression method is determined, the present invention is not limited to this. For example, it may be determined based on the number of colors in the target page and the presence / absence of a gradation region in the target page (a uniform color region is not considered).

  In the present embodiment, the image reading apparatus 10 having the scanner 16 and the image processing apparatus 100 has been described as an example. However, the present invention is not limited to this, and the image reading apparatus 10 is obtained by an imaging apparatus such as a digital camera. The image data may be processed using the image processing apparatus 100.

  Furthermore, in the present embodiment, the case where the image reading apparatus 10 is connected to the network 30 as a single unit has been described as an example. However, the present invention is not limited to this. For example, the image reading apparatus 10 and a laser printer, etc. The image forming apparatus may be combined with a copying machine.

DESCRIPTION OF SYMBOLS 10 ... Image reading apparatus, 16 ... Scanner, 100 ... Image processing apparatus, 120 ... Compression processing part, 130 ... Compression condition determination part, 140 ... Separation processing part classified by color, 150 ... First compression processing part, 160 ... Page composition part , 170 ... second compression processing unit, 180 ... file composition unit

Claims (6)

Calculating means for calculating the number of colors constituting the image data;
Gradation area extraction means for extracting gradation areas represented by gradations in the image data;
When the number of colors calculated by the calculation unit is equal to or less than a predetermined threshold value and the gradation region extracted by the gradation region extraction unit does not exist, the image data is defined as a first type. The number of colors calculated by the calculation means exceeds the threshold, or the number of colors calculated by the calculation means is equal to or less than the threshold and is extracted by the gradation area extraction means An image processing apparatus comprising: a determination unit that determines that the image data is the second type when the gradation area exists. A color reduction means for reducing the number of colors in the image data determined to be the first type;
First compression processing means for performing compression processing on the first type of image data reduced in color by the color reduction means;
The image processing apparatus according to claim 1, further comprising: a second compression processing unit that performs a compression process on the image data determined to be the second type. A uniform color region extracting means for extracting a uniform color region expressed in a uniform color in the image data;
The determination means has the number of colors calculated by the calculation means equal to or less than a predetermined threshold, the gradation area extracted by the gradation area extraction means does not exist, and the uniform color 3. The image data is determined to be the first type when the size of the uniform color area extracted by the area extraction unit is smaller than a predetermined reference size. Image processing device. Reading means for reading an image of a document;
Calculating means for calculating the number of colors constituting the image data read by the reading means;
Gradation area extraction means for extracting gradation areas represented by gradations in the image data;
When the number of colors calculated by the calculation unit is equal to or less than a predetermined threshold value and the gradation region extracted by the gradation region extraction unit does not exist, the image data is defined as a first type. The number of colors calculated by the calculation means exceeds the threshold, or the number of colors calculated by the calculation means is equal to or less than the threshold and is extracted by the gradation area extraction means An image reading apparatus comprising: a determination unit that determines that the image data is the second type when the gradation area exists. The reading unit outputs a plurality of image data corresponding to a plurality of pages by sequentially reading a plurality of pages of an original,
The image reading apparatus according to claim 4, wherein the determination unit determines, for each page, the plurality of image data. On the computer,
A function for calculating the number of colors constituting the image data;
A function of extracting a gradation area represented by gradation in the image data;
When the calculated number of colors is equal to or less than a predetermined threshold value and the extracted gradation area does not exist, the image data is determined as the first type, and the calculated number of colors is A function of determining the image data as the second type when the threshold value is exceeded or the calculated number of colors is equal to or less than the threshold value and the extracted gradation region exists is realized. program.

Images