JP2004062459A - Image processor, image processing method, image processing program, and computer readable recording medium recorded with the program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce the identification errors of a photograph area on a document image. <P>SOLUTION: A preprocessing means 202 reduces the number of the colors of an inputted image to a prescribed number. A background color extraction means 203 specifies the background color of the document image and a partial area extraction means 204 extracts a partial area where the pixels of the colors different from the background color are connected. A pixel color number extraction means 205 obtains the number of pixel colors in the partial area and a photograph area judgement means 206 compares the number of the pixel colors with a predetermined prescribed value and identifies whether or not the partial area is the photograph area. Thus, the photograph area is accurately identified from the document image inputted as a multi-level image without errors. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an image processing apparatus, an image processing method, an image processing program, and a computer-readable recording medium on which the program is recorded, in particular, a region of a photograph is identified from a document image in which characters, photographs, figures, tables, and the like are mixed. .
[0002]
[Prior art]
In recent years, scanners, digital cameras, printers, and other devices that can input and output multi-valued images such as color and grayscale have become widespread, and the cost of recording media has been reduced. ing. The use of multivalued images in document images is increasing. There has been a demand for performing multivalued images in processes such as region identification, title character string extraction, table processing, and OCR, which have been performed mainly on binary document images. I have.
[0003]
Since various methods have already been applied to binary document images, it has been considered that existing processing for binary images can be applied if binarized multi-valued document images are successfully processed. FIG. 6 shows the contents of a document. On the document image 600, areas having different attributes such as a character area 601, a table area (not shown), a figure area 602, and a photograph area 603 are mixed. Of these, in the character area 601, the table area, and the figure area 602, the colors used to describe them are often small. It is rare that one character itself is described in multiple colors or one cell of a table is multicolor.
[0004]
On the premise of these, for example, as in the image processing method disclosed in Japanese Patent Application Laid-Open No. 2000-040153, an appropriate threshold is partially found for a multi-valued document image and binarized. Then, the existing processing for the binary image (character area 601, table area, figure area 602, etc.) becomes effective. However, in the photograph area 603, the types of pixel colors are much more than in the binary image, depending on the contents of the photograph. If the photo area 603 is binarized by threshold processing in the same manner as the other areas, not only the content of the photograph cannot be determined, but also the processing of the binarized image causes the photo area 603 to be lost. Was erroneously classified into another area.
[0005]
In a multi-valued document image, if only the photo region 603 is identified in advance and binarization and application of subsequent processing are excluded from the photo region 603, errors caused by binarization of the photo region 603 can be eliminated. Therefore, it is necessary to extract the photograph region 603 in the multi-valued document image.
[0006]
As a method of classifying a partial area such as a photograph with respect to such a multi-valued image, there is an image processing method disclosed in Japanese Patent Application Laid-Open No. 2001-086328. That is, a plurality of thresholds for binarization are prepared, rectangle information is extracted from a plurality of images after binarization, rectangle information of a plurality of images is compared, and a predetermined condition is determined. Based on this, the partial areas are classified.
[0007]
[Problems to be solved by the invention]
However, in this method, in a plurality of binary images, a partial region in which the position and size of the rectangular information are significantly shifted is defined as a photograph region. For this reason, in the character region of the intermediate color, the displacement of the rectangular information becomes large, so that the photograph region is erroneously classified as a photograph region. Was. In addition, since the optimal threshold value for creating a plurality of binary images and the number of the threshold values are not fixed, whether rectangular information that can be appropriately classified can be extracted has a great influence on the content of the image. There was a drawback of receiving it.
[0008]
SUMMARY OF THE INVENTION The present invention solves the above-described problems of the related art, and therefore, an image processing apparatus, an image processing method, an image processing program, and a computer-readable recording recording the program, which can identify a photographic area on a document image without error. The purpose is to provide a medium.
[0009]
[Means for Solving the Problems]
In order to solve the above-described problem and achieve the object, an image processing apparatus according to the present invention is an image processing apparatus having a function of identifying a photographic area from a document image input as a multi-valued image. Background color extracting means for specifying a background color of the document image; partial area extracting means for extracting a partial area in which pixels of colors different from the specified background color are connected; and a pixel color for determining the number of pixel colors of the partial area A number extracting unit, a photographic region determining unit that compares the number of the pixel colors with a predetermined value to determine whether the partial region is a photographic region, and controls the respective units. And control means for performing the control.
[0010]
According to the first aspect of the present invention, a photographic area can be determined based on the number of pixel colors of a partial area in a multi-valued input document image, and the photographic area of the multi-valued image can be determined simply and accurately. Can be identified without error.
[0011]
Further, in the image processing apparatus according to the second aspect of the present invention, in the first aspect of the present invention, the pixel color number extracting means performs a process of deeming the same color when the distance in the color space is less than a predetermined value. It is characterized by.
[0012]
According to the second aspect of the present invention, the colors whose distances in the color space are less than the predetermined value are regarded as the same color, so that the color of the pixel is shifted with a slight shift in luminance. Can be prevented and the processing efficiency can be improved.
[0013]
An image processing apparatus according to a third aspect of the present invention is the image processing apparatus according to the first aspect, further comprising a preprocessing unit that reduces the pixel color of the input document image to a predetermined number. I do.
[0014]
According to the third aspect of the present invention, when the background color is specified and the photograph area is identified, the number of colors is reduced in advance, so that the color of the pixel is shifted with a slight shift in luminance. Can be prevented.
[0015]
Further, in the image processing apparatus according to a fourth aspect of the present invention, in the invention according to any one of the first to third aspects, the control unit determines the partial area identified as a photographic area by the photographic area determination unit. The processing is performed by each means assuming that the image is an input image, and the photograph area is identified again.
[0016]
According to the fourth aspect of the present invention, by recursively identifying a photograph area, only a photograph area can be correctly extracted even when the photograph area is included in another area.
[0017]
The image processing method according to claim 5, wherein in the image processing method for identifying a photograph area from a document image input as a multi-valued image, a background color extracting step of specifying a background color of the document image; A partial area extraction step of extracting a partial area in which pixels of different colors from the specified background color are connected, a pixel color number extraction step of calculating the number of pixel colors of the partial area, and a predetermined number of the pixel colors; And determining whether the partial area is a photographic area by comparing the partial area with a predetermined value.
[0018]
According to the fifth aspect of the present invention, it is possible to determine a photographic area based on the number of pixel colors of a partial area for a multi-valued input document image, and to easily and highly accurately determine a photographic area of a multi-valued image. Can be identified without error.
[0019]
In the image processing method according to a sixth aspect of the present invention, in the invention according to the fifth aspect, the pixel color number extracting step performs a process in which when the distance in the color space is less than a predetermined value, the pixel is regarded as the same color. It is characterized by.
[0020]
According to the sixth aspect of the present invention, the colors whose distances in the color space are less than the predetermined value are regarded as the same color, so that the color of the pixel is shifted with a slight shift in luminance. Can be prevented and the processing efficiency can be improved.
[0021]
According to a seventh aspect of the present invention, in the image processing method according to the fifth aspect, the pre-processing is performed in which the pixel color of the input document image is reduced to a predetermined number and passed to the background color extracting step. It is characterized by including a step.
[0022]
According to the seventh aspect of the present invention, when the background color is specified and the photographic area is identified, the number of colors is reduced in advance, so that the color of the pixel shifts with a slight shift in luminance. Can be prevented.
[0023]
An image processing method according to an eighth aspect of the present invention is the image processing method according to any one of the fifth to seventh aspects, wherein the partial area after being identified as a photographic area in the photographic area determination step is defined as an input image. Assuming that the processing of each step is executed again to re-identify the photograph area.
[0024]
According to the eighth aspect of the present invention, by recursively identifying a photograph region, only a photograph region can be correctly extracted even if the photograph region is included in another region.
[0025]
An image processing program according to a ninth aspect of the present invention is an image processing program for identifying a photographic area from a document image input as a multi-valued image, wherein the image processing program stores a background color of the document image in a computer. Is specified, a partial region in which pixels of colors different from the specified background color are connected is extracted, the number of pixel colors of the partial region is obtained, the number of the pixel colors, a predetermined value, and Are compared to determine whether or not the partial region is a photograph region.
[0026]
According to the ninth aspect of the present invention, it is possible to determine a photographic area based on the number of pixel colors of a partial area in a multi-valued document image during computer processing. In addition, identification can be performed with high accuracy without errors.
[0027]
According to a tenth aspect of the present invention, in the image processing program according to the ninth aspect, when the number of pixel colors is obtained, when the distance in the color space is less than a predetermined value, the processing is regarded as the same color. It is characterized by
[0028]
According to the tenth aspect of the present invention, the colors whose distances in the color space are smaller than a predetermined value are regarded as the same color during the computer processing, so that the color of the pixel is shifted with a slight shift in luminance. Can be prevented, and the processing efficiency can be improved.
[0029]
An image processing program according to an eleventh aspect of the present invention is the image processing program according to the ninth aspect, wherein the background color is extracted after reducing the pixel colors of the input document image to a predetermined number. It is characterized by the following.
[0030]
According to the eleventh aspect of the present invention, the number of colors is reduced in advance at the time of specifying a background color and identifying a photographic region at the time of computer processing, so that the color of a pixel is changed with a slight shift in luminance. It is possible to prevent the displacement.
[0031]
An image processing program according to a twelfth aspect of the present invention is the image processing program according to any one of the ninth to eleventh aspects, wherein the partial area after being identified as a photographic area by the identification of the photographic area is defined as an input image. Assuming that each of the processes is executed again, and the photographic region is re-identified.
[0032]
According to the twelfth aspect of the present invention, by recursively identifying a photograph area during computer processing, even when the photograph area is included in another area, only the photograph area can be correctly extracted. .
[0033]
According to a thirteenth aspect of the present invention, there is provided a computer-readable recording medium which records the program according to any one of the ninth to twelfth aspects and is readable by a computer.
[0034]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, preferred embodiments of an image processing apparatus, an image processing method, an image processing program, and a computer-readable recording medium storing the program according to the present invention will be described in detail with reference to the accompanying drawings.
[0035]
FIG. 1 is a block diagram showing the overall configuration of the image processing apparatus of the present invention. The image processing device includes a CPU (central processing unit) 101, a memory 102, an image input device 103 such as a scanner or a digital camera, a communication device 104, a display device 105 such as a monitor, a keyboard 106, a fixed recording device 107 such as a hard disk, The system includes an external recording / reproducing device 109 using a recording medium (recording medium) 108 such as a CD-RAM / ROM, a DVD-RAM / ROM, and a flexible disk.
[0036]
The CPU 101 controls the entire system, and the memory 102 stores data and programs to be processed by the CPU 101. The communication device 104 is a device for connecting to a network such as a LAN. The keyboard 106 is used to input data and user instructions. The fixed recording device 107 and the external recording / reproducing device 109 are for saving and loading data, programs, and the like on the recording medium 108.
[0037]
FIG. 2 is a block diagram showing the internal configuration of the image processing means in the image processing device. Each function of the image processing means 200 can be obtained by executing an image processing program for the CPU 101. The image processing means 200 includes an image input means 201 for inputting a multi-valued document image from an image input device 103 such as a color scanner, a preprocessing means 202 for performing pixel color reduction on the input image, and Background color extracting means 203 for specifying the background color of the multi-valued document image, partial area extracting means 204 for extracting an area where pixels different from the background color are connected, and pixel color for extracting the number of pixel colors of the partial area Number extracting means 205, a photograph area determining means 206 for determining whether or not the partial area image is a photograph area based on the obtained number of pixel colors, a memory 207 for storing the extracted data, and a controlling means for controlling the processing flow 208. As the memory 207, the memory 102 illustrated in FIG. 1 can be used.
[0038]
(Embodiment 1)
Next, image processing according to the above configuration will be described. FIG. 3 is a flowchart showing an image processing procedure according to the first embodiment of the present invention. First, an image input process is performed (step S301), and a background color is specified for the input document image (step S302). For example, the background color can be specified using a general-purpose method such as the method described in JP-A-2001-222717.
[0039]
Next, a partial region in which pixels other than the background color are connected is extracted (step S303). The extraction of the connected pixels can be performed using an existing process that has been widely known. Next, the number of types of pixel colors constituting the partial area is obtained (step S304). Then, a photograph area is determined based on the number of types of the pixel colors (step S305). This determination of the photograph area is compared with a predetermined threshold value, and if it is larger than the threshold value, the partial area is set as a photograph area. The threshold value may be determined experimentally.
[0040]
In general, there are many types of pixel colors that make up a character, or at most several types even if they are outline or shaded characters. Photos, on the other hand, are made up of much more types of pixel colors. Also, in the figures and tables, the number of pixel colors is larger than that of the pixels constituting the character, but is often a combination of one type of solid color figure, and the types of pixel colors are not as many as in the photograph area. As described above, by using the number of pixel colors in the partial region, the photograph region can be easily identified from the multi-valued image with high accuracy.
[0041]
・ Counting of pixel color type
Generally, TrueColor used for a color image has eight bits of red (R), green (G), and blue (B) values for each pixel, and which of 256 × 256 × 256 = 16777216 colors Or will be assigned. Therefore, the simplest method of counting the number of colors in the pixel color number extracting means 205 can be performed based on a histogram of the number of pixels for 16777216 types of colors. Then, the number of colors can be determined by counting the colors whose pixel numbers are not 0.
[0042]
(Embodiment 2)
According to the second embodiment of the present invention, when calculating the number of types of pixel colors constituting the partial area in the first embodiment (step S304), colors whose distances in the color space are smaller than a predetermined value are not determined. The number of types of pixel colors is determined assuming the same color. For example, when an image is input with a general TrueColor (about 16.770,000 colors) using an input device such as a color scanner, even a slight shift in illumination (luminance) in scanning reacts sensitively. In some cases, the luminance of any of the RGB components of the pixel colors constituting the characters that should be one type of character is slightly shifted, and is determined to be a different type of color. This is to avoid this. Note that a distance in a color space that is regarded as the same color is experimentally obtained in advance.
[0043]
By regarding colors whose distance in the color space is less than a predetermined value to be the same color, it is possible to prevent the pixel color from being shifted due to a slight luminance shift.
[0044]
・ About color space, distance and threshold
The color space described above indicates TrueColor in which each of RGB has an integer value of 0 to 255, and the distance is a so-called Euclidean distance. When the color of pixel 1 is represented by (r1, g1, b1) and the color of pixel 2 is represented by (r2, g2, b2), their Euclidean distance d is
[0045]
d = sqrt ((r1-r2) ² + (G1-g2) ² + (B1-b2) ² )
[0046]
Is represented by The above notation of sqrt () indicates a square root. A representative value of 24 is used as a threshold value of the distance for considering the same type of color.
[0047]
(Embodiment 3)
FIG. 4 is a flowchart showing an image processing procedure according to the third embodiment of the present invention. The same processing steps as those in the first embodiment are denoted by the same step numbers. In the third embodiment, a process of reducing the pixel color by the pre-processing unit 202 (step S401) is added to the document image input in step S301, and the pixel color of the input document image is determined in advance. After the number is reduced to the number of types, identification of a background color (step S302), extraction of a partial area (step S303), extraction of the number of pixel colors (step S304), and determination of a photograph area (step S305) are executed.
[0048]
As described in the second embodiment, for example, when an image is input with a general TrueColor (about 16.770,000 colors) using an input device such as a color scanner, even a slight shift in illumination (luminance) during scanning is sensitive. In some cases, the brightness of any of the RGB components of the pixel colors constituting the characters that should be one type of character in the obtained image is slightly shifted, so that it is determined that the colors are different types. Is to avoid. The number of colors after color reduction may be determined experimentally so that a set of pixels that are visually one type of color becomes one type of color by quantization.
[0049]
As described above, when the background color is specified and the photograph area is identified, by reducing the number of colors in advance, it is possible to prevent the pixel color from being shifted due to a slight luminance shift. Become like
[0050]
・ About color reduction of pixel color
As described above, a specific example in which the pre-processing unit 202 performs color reduction will be described. Instead of assigning 8 bits to each of RGB, 3 bits are used. That is, each of the RGB values is a value from 0 to 255, is divided by 32, the fractional part is cut off, and the value is converted to a value from 0 to 7. Thereby, the number of colors can be reduced to 8 × 8 × 8 = 512 colors. As described above, the configuration is not limited to converting RGB from 8 bits to 3 bits (color reduction), but may be configured to convert (color reduction) to 2 bits or 4 bits.
[0051]
(Embodiment 4)
FIG. 5 is a flowchart showing an image processing procedure according to the fourth embodiment of the present invention. In the fourth embodiment, the photograph area identified in step S305 in the first embodiment is regarded as a newly input image, and the photograph area is recursively identified.
[0052]
In the flowchart of FIG. 5, a recursion determination process (step S306) is added, and it is determined that the first time is a recursion (step S306: Yes), the process returns to step S302, and a series of processes (steps S302 to S305) is performed again. After the execution (step S306: No), the process ends. This makes it possible to correctly extract only the photographic region even when the photographic region is included in another region on the document image.
[0053]
The image processing method described in the present embodiment can be realized by executing a prepared program on a computer such as a personal computer or a workstation. This program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. The program may be a transmission medium that can be distributed via a network such as the Internet.
[0054]
【The invention's effect】
As described above, according to the first aspect of the present invention, in an image processing apparatus having a function of identifying a photographic region from a document image input as a multi-valued image, a background color of the document image is specified. Background color extraction means, partial area extraction means for extracting a partial area in which pixels of colors different from the specified background color are connected, pixel color number extraction means for determining the number of pixel colors of the partial area, And a photographic area determining means for comparing the number of the photographic areas with a predetermined value to determine whether the partial area is a photographic area, and a control means for controlling the respective means, The photo region can be determined based on the number of pixel colors in the partial region with respect to the multi-valued input document image, and the photo region of the multi-value image can be easily and accurately identified without error. To play.
[0055]
According to the second aspect of the present invention, in the first aspect of the present invention, the pixel color number extracting means performs a process of assuming the same color when the distance in the color space is less than a predetermined value. By regarding colors whose distances in the color space are smaller than a predetermined value as the same color, it is possible to prevent the color of the pixel from being shifted due to a slight shift in luminance, thereby improving processing efficiency. It has the effect that it can be achieved.
[0056]
According to a third aspect of the present invention, in the first aspect of the present invention, the image processing apparatus further includes a pre-processing means for reducing the pixel color of the input document image to a predetermined number, so that the background color can be reduced. By reducing the number of colors in advance at the time of identification and identification of a photographic region, it is possible to prevent the color of a pixel from being shifted due to a slight shift in luminance.
[0057]
According to the invention described in claim 4, in the invention described in any one of claims 1 to 3, the control means inputs the partial area identified as a photographic area by the photographic area determination means. Since the process is performed by each means assuming that the image is an image and the photo region is identified again, by recursively identifying the photo region, even if the photo region is included in another region, the photo region is correctly identified. It is possible to extract only the information.
[0058]
According to the fifth aspect of the present invention, in the image processing method for identifying a photographic region from a document image input as a multi-valued image, a background color extracting step of identifying a background color of the document image; A partial region extracting step of extracting a partial region in which pixels of different colors from the background color are connected, a pixel color number extracting step of calculating the number of pixel colors of the partial region, and a predetermined number of pixel colors. Comparing with a predetermined value to determine whether or not the partial area is a photographic area. Thus, the photograph area of the multi-value image can be easily and accurately identified without error.
[0059]
Also, according to the invention described in claim 6, in the invention described in claim 5, the pixel color number extraction step performs a process of regarding the same color when the distance in the color space is less than a predetermined value. By regarding colors whose distances in the color space are smaller than a predetermined value as the same color, it is possible to prevent the color of the pixel from being shifted due to a slight shift in luminance, thereby improving processing efficiency. It has the effect that it can be achieved.
[0060]
According to a seventh aspect of the present invention, in the invention of the fifth aspect, a pre-processing step of reducing the pixel color of the input document image to a predetermined number and passing the reduced color to the background color extracting step Therefore, when the background color is specified and the photograph area is identified, by reducing the number of colors in advance, it is possible to prevent the pixel color from being shifted due to a slight shift in luminance. This has the effect.
[0061]
According to the invention described in claim 8, in the invention described in any one of claims 5 to 7, a partial area after being identified as a photographic area in the photographic area determination step is regarded as an input image. Since the processing of each of the steps is performed again to re-identify the photographic area, the photographic area is recursively identified, so that even if the photographic area is included in another area, the photographic area can be correctly identified. There is an effect that only the region can be extracted.
[0062]
According to the ninth aspect of the present invention, there is provided an image processing program for identifying a photographic area from a document image input as a multi-valued image, wherein the image processing program causes a computer to change a background color of the document image. Let the specific area, the partial area in which the pixels of different colors from the specified background color are connected is extracted, the number of the pixel colors of the partial area is determined, the number of the pixel colors and a predetermined value are determined. In comparison, since it is determined whether or not the partial area is a photographic area, it is possible to determine the photographic area based on the number of pixel colors of the partial area with respect to the document image input in multi-value during computer processing. This makes it possible to easily and accurately identify the photographic area of the multi-valued image without error.
[0063]
According to the tenth aspect of the present invention, in the method of the ninth aspect, when the number of pixel colors is obtained, a process of regarding the same color when a distance is less than a predetermined value in a color space is performed. Therefore, it is possible to prevent the colors of the pixels from being shifted due to a slight shift in luminance by regarding the colors whose distance in the color space is less than a predetermined value as the same color during the computer processing, There is an effect that the processing efficiency can be improved.
[0064]
According to the eleventh aspect, in the ninth aspect, the pixel color of the input document image is reduced to a predetermined number before the background color is extracted. When the number of colors is reduced in advance when specifying a background color and identifying a photographic region during computer processing, it is possible to prevent the pixel color from being shifted due to a slight shift in luminance. This has the effect.
[0065]
According to the twelfth aspect of the present invention, in the invention according to any one of the ninth to eleventh aspects, a partial area after being identified as a photographic area by the identification of the photographic area is regarded as an input image. Since each of the processes is executed again and the photo region is re-identified, the photo region is recursively identified during the computer processing, so that even if the photo region is included in another region, the photograph There is an effect that only the region can be extracted.
[0066]
According to the thirteenth aspect of the present invention, the program according to any one of the ninth to twelfth aspects is recorded and can be read by a computer. The effect described above can be achieved.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating an overall configuration of an image processing apparatus according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an internal configuration of an image processing unit in the image processing apparatus.
FIG. 3 is a flowchart illustrating an image processing procedure according to the first embodiment of the present invention.
FIG. 4 is a flowchart showing an image processing procedure according to a third embodiment of the present invention.
FIG. 5 is a flowchart illustrating an image processing procedure according to a fourth embodiment of the present invention.
FIG. 6 is a diagram showing the contents of a document.
[Explanation of symbols]
101 CPU (central processing unit)
102 memory
103 Image input device
104 Communication device
105 Display device
106 keyboard
107 fixed recording device
108 Recording media (recording media)
109 External recording and playback device
200 Image processing means
201 Image input means
202 Preprocessing means
203 Background color extraction means
204 partial area extraction means
205 pixel color number extraction means
206 Photo area judgment means
207 memory
208 control means

Claims (13)

In an image processing apparatus having a function of identifying a photograph area from a document image input as a multi-valued image,
Background color extracting means for specifying a background color of the document image;
Partial region extracting means for extracting a partial region in which pixels of different colors from the specified background color are connected,
A pixel color number extraction unit for obtaining the number of pixel colors of the partial region;
A photograph region determining unit that compares the number of the pixel colors with a predetermined value to determine whether the partial region is a photograph region;
Control means for controlling each of the means,
An image processing apparatus comprising: The pixel color number extraction means,
2. The image processing apparatus according to claim 1, wherein when the distance in the color space is less than a predetermined value, a process of regarding the same color is performed. 2. The image processing apparatus according to claim 1, further comprising a preprocessing unit configured to reduce a pixel color of the input document image to a predetermined number. The control means includes:
The partial region identified as a photograph region by the photograph region determination unit is regarded as an input image, and processing by each unit is executed, and the photograph region is identified again, wherein the photograph region is identified again. The image processing apparatus according to claim 1. In an image processing method for identifying a photographic region from a document image input as a multi-valued image,
A background color extraction step of specifying a background color of the document image,
A partial region extracting step of extracting a partial region in which pixels of different colors from the specified background color are connected,
A pixel color number extraction step of obtaining the number of pixel colors of the partial region;
Comparing the number of the pixel colors with a predetermined value, and determining whether or not the partial area is a photographic area;
An image processing method comprising: The pixel color number extraction step includes:
6. The image processing method according to claim 5, wherein when the distance in the color space is less than a predetermined value, a process of regarding the same color is performed. 6. The image processing method according to claim 5, further comprising a pre-processing step of reducing a pixel color of the input document image to a predetermined number and passing it to the background color extraction step. The partial area after being identified as a photographic area in the photographic area determination step is regarded as an input image, and the processing of each of the steps is executed again to re-identify the photographic area. The image processing method according to any one of the above. An image processing program for identifying a photographic area from a document image input as a multi-valued image, the image processing program
Causing the background color of the document image to be specified,
A partial region in which pixels of different colors from the specified background color are connected,
The number of pixel colors in the partial area is determined,
An image processing program for comparing the number of pixel colors with a predetermined value to identify whether the partial area is a photographic area. 10. The computer-readable storage medium according to claim 9, wherein, when calculating the number of pixel colors, when the distance in the color space is less than a predetermined value, a process of regarding the same color is performed. 10. The image processing program according to claim 9, wherein the background color is extracted after reducing the pixel color of the input document image to a predetermined number. The partial area after being identified as a photographic area by the identification of the photographic area is regarded as an input image, the processing is executed again, and the photographic area is re-identified. An image processing program according to one. 13. A computer-readable recording medium on which the image processing program according to claim 9 is recorded.

Images