JP2009071781A - Image processor and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To surely decompose an integrated original into each image even though there is a specific image, such as handwriting, near a boundary region of the integrated original. <P>SOLUTION: An original obtained by integrating a plurality of images is read, and a layout analyzing part 30 analyzes image regions and character regions and obtains an image for performing character recognition. A character recognizing part 32 performs character recognition about an image for performing character recognition to obtain a character recognition image whose character recognition is successful, and an integration form is determined by comparing the character recognition image with a predetermined pattern for integration form determination. In addition, an attribute data extracting part 36 extracts a non-character image existing in the boundary region of the image for performing character recognition, and an attribute data attaching part 42 attaches attribute data representing the non-character image as a page attribute. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

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

  As a technique for reading a document on which a plurality of images are aggregate-printed, disassembling the aggregated images into respective images and re-aggregating, techniques disclosed in Patent Documents 1 and 2 have been proposed.

  In the technique described in Patent Document 1, a plurality of aggregated documents obtained by consolidating and printing a plurality of document images on a single recording sheet are read by a document reading unit, and a plurality of aggregated images for each aggregated document are acquired. A boundary (at least one of a strip-shaped blank portion and a boundary line) between the aggregated images is detected by the boundary detection unit, and based on the detected boundary, the aggregation rate for each aggregated document is determined by the aggregation rate determination unit, and predetermined It has been proposed to print again at an aggregation rate of.

In the technique described in Patent Document 2, when a document group in which documents of different aggregation formats are mixed is read by a scanner, the document aggregation format is designated as necessary, and images are read and re-aggregated. Proposed.
JP 2004-304546 A Japanese Patent Laid-Open No. 2006-253974

  The present invention provides an image processing apparatus and an image processing program capable of reliably decomposing an aggregated document into each image even if there is a specific image such as handwriting near the boundary region of the aggregated document. Objective.

  In order to achieve the above object, the image processing apparatus according to claim 1, a determination unit that determines an aggregation format of a plurality of images based on a reading result obtained by reading a document in which a plurality of images are aggregated, and the determination Extraction means for extracting a specific image existing in a boundary region of a plurality of aggregated images based on the determination result of the means; and the specific image extracted by the extraction means is excluded from the read result, and the determination means Decomposition means for decomposing the read results into respective images according to the determined aggregation format.

  According to a second aspect of the present invention, in the invention according to the first aspect, the determination unit includes an analysis unit that analyzes a component including a character region and an image region of a document, and a character that is analyzed by the analysis unit. Character recognition means for recognizing characters in the region, and the aggregate format is determined by comparing the recognition result of the character recognition means with an aggregate format determination pattern for determining a predetermined aggregate format. It is characterized by that.

  According to a third aspect of the present invention, in the invention according to the first aspect, the determination unit compares the read result with an aggregation format determination pattern for determining a predetermined aggregation format. In this case, the aggregation format is determined.

  According to a fourth aspect of the present invention, in the invention according to the second aspect, the extracting means is a non-character existing in a boundary area in the aggregate format determined by the determining means from the image area analyzed by the analyzing means. An image is extracted as the specific image.

    According to a fifth aspect of the present invention, in the invention according to the third aspect, the extracting means extracts, as the specific image, a non-background image existing in a boundary region in the aggregate format determined by the determining means. It is characterized by.

  The invention according to claim 6 is the invention according to any one of claims 1 to 5, wherein the specific image is an image added to a document image by handwriting.

  An image processing apparatus according to a seventh aspect is the invention according to any one of the first to sixth aspects, wherein the specific image extracted by the extraction unit is added so as to be displayed as page attribute data of the extracted page. It is characterized by further comprising an adding means.

  An image processing apparatus according to an eighth aspect of the present invention is the image processing apparatus according to any one of the first to sixth aspects, further comprising an adding unit that collectively adds the specific image extracted by the extracting unit to a new page. It is characterized by providing.

  The image processing apparatus according to claim 9 is the invention according to any one of claims 1 to 6, wherein the extracted specific image is within a page area after being decomposed into respective images by the decomposing means. The image processing apparatus further includes an adding unit that further converts the resolution so as to be included and adds the specific image in the page area.

  The image processing program according to claim 10, a determination step for determining an aggregation format of a plurality of images based on a reading result obtained by reading a document on which a plurality of images are aggregated on a computer, and a determination result of the determination step Based on the extraction step of extracting a specific image existing in the boundary region of a plurality of aggregated images, and the aggregation format determined in the determination step, excluding the specific image extracted in the extraction step from the read result And a decomposing means for decomposing the read result into respective images.

  According to the first aspect of the present invention, there is an effect that even if there is a specific image such as handwriting in the boundary region of the aggregated documents, the aggregated documents can be reliably decomposed into each image.

  According to the second aspect of the present invention, there is an effect that, when determining the aggregation format, it is possible to perform determination with less noise compared to a case where this configuration is not adopted.

  According to the third aspect of the present invention, there is an effect that it is possible to easily determine the aggregation format as compared with the case where this configuration is not adopted.

  According to the invention described in claim 4, there is an effect that a specific image such as handwriting can be extracted.

  According to the invention described in claim 5, there is an effect that a specific image such as handwriting can be extracted.

  According to the sixth aspect of the present invention, there is an effect that it is possible to extract a handwritten part added to the boundary region of the aggregated images.

  According to the seventh aspect of the invention, there is an effect that the extracted specific image can be displayed without being deleted.

  According to the invention described in claim 8, there is an effect that the extracted specific image can be added to the document without being deleted.

  According to the ninth aspect of the invention, there is an effect that the extracted specific image can be added to the document without being deleted.

  According to the invention described in claim 10, even if there is a specific image such as handwriting in the boundary region of the aggregated documents, there is an effect that the aggregated documents can be reliably decomposed into each image.

Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings.
(First embodiment)
FIG. 1 is a block diagram showing a schematic configuration of an image processing apparatus according to the first embodiment of the present invention.

  The image processing apparatus 10 according to the first embodiment of the present invention reads a document in which a plurality of images are aggregated, decomposes each image, and outputs or re-aggregates the images.

  The image processing apparatus 10 according to the first embodiment of the present invention includes an image reading unit 12, a memory 14, a CPU 16, an operation key 18, a display device 20, an image processing unit 22, a network interface 24, and a hard disk 26. Each is connected to a bus 28.

  The image reading unit 12 scans the original by irradiating light, collects the light reflected from the original through a mirror or lens, and converts the image signal photoelectrically converted by the CCD into digital image data. To read the original. In this embodiment, a document in which a plurality of images are collected is read as a document.

  The memory 14 functions as a work area when temporarily storing image data obtained by reading an original with the image reading unit 12 or performing image processing on the image data.

  The operation key 18 includes various buttons for performing various instructions such as starting reading of a document by the image reading unit 12, settings relating to reading of a document by the image reading unit 12, and various settings of image processing for image data obtained by reading. ing.

  The display device 20 displays an operation state of the image processing device 10, an interface screen for various settings, and the like.

  The image processing unit 22 performs various types of image processing on image data obtained by reading a document image by the image reading unit 12. Specifically, in this embodiment, based on image data obtained by reading an original on which a plurality of images are aggregated by the image reading unit 12, the image aggregated on the original is decomposed and output for each page. Alternatively, image processing for re-aggregating and outputting is performed.

  The network interface 24 is connected to various networks such as the Internet and an intranet, and outputs image data processed by the image processing apparatus 10 to an external device or the like in response to a request. In the present embodiment, an example of connection to a network will be described. However, the present invention is not limited to this, and the network interface 24 may be an interface connected to various communication means.

  The hard disk 26 stores the image data and the like processed by the image processing unit 22 and outputs the stored image data in response to requests from various devices connected to the network. For example, when printing out image data processed by the image processing unit 22, the image data is sent to a device that forms an image based on the image data processed by the image processing unit 22 and stored in the hard disk 26. Output.

  The CPU 16 controls the operation of the image processing apparatus 10 by controlling these devices. For example, a display corresponding to the operation state of the operation key 18 is displayed on the display device 20, or reading of a document image by the image reading unit 12 is controlled according to an operation instruction by the operation key 18, and the image reading unit 12 obtains the display. The image processing by the image processing unit 22 for the image data to be processed is controlled.

  FIG. 2 is a block diagram showing a detailed configuration of the image processing unit 22 of the image processing apparatus 10 according to the first embodiment of the present invention.

  As shown in FIG. 2, the image processing unit 22 of the image processing apparatus 10 according to the first embodiment of the present invention includes a layout analysis unit 30, a character recognition unit 32, an aggregation format analysis unit 34, an attribute data extraction unit 36, an aggregation. A canceling unit 38, a resolution converting unit 40, an attribute data adding unit 42, and an output image data generating unit 44 are provided.

  The layout analysis unit 30 analyzes an image such as a picture of a document and a layout of characters based on image data obtained by reading the document by the image reading unit 12, and obtains an image for character recognition. For example, by extracting a block of information with the contrast to the background or extracting an image area from the continuity of color tone, etc., the image of the document or the layout of the characters is analyzed, and an image for character recognition is extracted. To do. An example of a document image is shown in FIG. 3A, and an example of an image for character recognition generated by the analysis of the layout analysis unit 30 is shown in FIG. Moreover, in FIG. 3, a part of character part is shown with a line.

  The character recognition unit 32 performs character recognition by performing a known OCR (Optical Character Recognition) process or the like using the document layout analyzed by the layout analysis unit 30. For example, an example of a character recognition image that has been successfully recognized by the character recognition unit 32 is shown in FIG.

  The aggregation format analysis unit 34 compares the character recognition image (for example, FIG. 3B) that has been successfully recognized by the character recognition unit 32 with a predetermined aggregation format determination pattern, thereby determining the aggregation format. judge. It should be noted that instead of the character recognition image, it is possible to determine the aggregate format using layout elements that have been successfully recognized.

  For example, as the predetermined aggregation format determination pattern, the pattern shown in FIG. 4 can be applied, and FIG. 4A shows an aggregation format determination pattern for determining an image aggregated by two pages. FIG. 4B shows an aggregation format determination pattern for determining an image aggregated by 4 pages, and FIG. 4C shows an aggregation format determination pattern for determining an image aggregated by 6 pages. The aggregate format can be determined by comparing the pattern for use with the character recognition image and extracting the pattern for aggregate format with a high degree of coincidence of the boundary regions.

  The attribute data extraction unit 36 includes an image for character recognition (for example, FIG. 3B) obtained by the analysis of the layout analysis unit 30 and a character recognition image (for example, FIG. 3 (C)), and from the aggregation format determined by the aggregation format analysis unit 34, a block (specific image) of non-character images such as handwritten comments existing in the boundary region of the aggregated images is extracted as attribute data. For example, in the case of the original image shown in FIG. 3A, the attribute data represented by the specific image existing in the determined aggregated area is obtained by obtaining an image excluding the character recognition image from the image for character recognition. To extract. Thus, in the case of FIG. 3, the specific image represented by the extracted attribute data is as shown in FIG.

  Based on the analysis result of the aggregation format analysis unit 34, the aggregation cancellation unit 38 performs aggregation by excluding the attribute data extracted by the attribute data extraction unit 36 from the image data obtained by reading the document by the image reading unit 12. Decompose images into individual images.

  The resolution conversion unit 40 converts the resolution of each image canceled by the aggregation cancellation unit 38 in accordance with the re-aggregation format and resolution set by the operation key 18 or the like.

  The attribute data adding unit 42 gives the attribute data extracted by the attribute data extracting unit 36 as a page attribute or adds it as a new page according to a method preset by the operation key 18. For example, the attribute data adding unit 42 may add the attribute data together as a new page, may add the attribute data as a page attribute as shown in FIG. In this case, the attribute data of the boundary area is converted into a page that has been decomposed so that the resolution is slightly smaller than the specified resolution so that the boundary at the time of decomposition of the aggregated image is inside the page margin. You may make it add attribute data so that it may be included. FIG. 5 shows an example of a display screen that displays each page obtained by disassembling the aggregated image and attribute data of each page.

  The output image data generation unit 44 uses the image data and attribute data decomposed into each page by the aggregation cancellation unit 38 to perform re-aggregation according to the re-aggregation format set by the operation key 18 or an external device. By doing so, output image data is generated. The generated output image data is stored in the hard disk 26 or output to an external device via the network interface 24.

  Next, processing performed by the image processing apparatus 10 according to the first embodiment of the present invention configured as described above will be described. FIG. 6 is a flowchart showing an example of the flow of processing performed by the image processing apparatus 10 according to the first embodiment of the present invention. Note that the flowchart of FIG. 6 starts when, for example, a re-aggregation instruction is given by the operation key 18.

  First, in step 100, the layout of the document image read by the image reading unit 12 is analyzed by the layout analysis unit 30, and the character area and the image area are determined, and the process proceeds to step 102.

  In step 102, the character region analyzed by the layout analysis unit 30 is extracted, and the character recognition unit 32 recognizes the character, and the process proceeds to step 104.

  In step 104, the aggregation format analysis unit 34 determines the aggregation format from the character recognition image successfully recognized by the character recognition unit 32, and the process proceeds to step 106. For example, a predetermined aggregation format determination pattern shown in FIG. 4 is compared with a character recognition image (for example, FIG. 3C), and the degree of coincidence of boundary areas among a plurality of aggregation format determination patterns The aggregation format is determined by extracting the ones with high values.

  In step 106, the attribute data extraction unit 36 determines whether there is an image in the boundary region of the aggregation format determined by the aggregation format analysis unit 34. The determination is made by using an image for character recognition (for example, FIG. 3B) obtained by layout analysis of the layout analysis unit 30 and a character recognition image for which character recognition by the character recognition unit 32 is successful (for example, FIG. C)) and from the analysis result of the aggregation format analysis unit 34, it is determined whether or not there is a non-character image in the boundary region of the aggregated image. If the determination is negative, the process proceeds to step 108. If the determination is affirmative, the routine proceeds to step 112.

  In step 108, the aggregation cancellation unit 38 cancels the aggregation according to the aggregation format determined by the aggregation format analysis unit 34, and the process proceeds to step 110.

  In step 110, the resolution conversion unit 40 converts the resolution of each image that has been canceled to the resolution set by the operation key 18 or the like, and the process proceeds to step 120.

  On the other hand, in step 112, the non-character image existing in the boundary region is extracted by the attribute data extraction unit 36, and the process proceeds to step 114.

  In step 114, attribute data representing the non-character image extracted by the attribute data extraction unit 36 is removed by the aggregation cancellation unit 38, and aggregation is canceled according to the aggregation format determined by the aggregation format analysis unit 40. Migrate to

  In step 116, the resolution conversion unit 40 converts the resolution of each image that has been unaggregated according to the re-aggregation format or resolution set by the operation key 18 or the like, and the process proceeds to step 118.

  In step 118, attribute data is added by the attribute data adding unit 42 according to the setting by the operation key 18 or the like, and the process proceeds to step 120. For example, according to the setting by the operation key 18 or the like, the attribute data is added together as a new page, or the attribute data is added as a page attribute as shown in FIG. The resolution data is converted so that the resolution is slightly smaller than the specified resolution so that the boundary when the image is decomposed is inside the page margin, so that the attribute data of the boundary area is included in the decomposed page. Or add. In addition, when attribute data is added as a page attribute as shown in FIG. 5 or when attribute data is added so that the attribute data of the boundary region is included in the decomposed page, the attribute data is extracted by the attribute data extraction unit 36. At the time of extraction, it is added as an attribute of the page with the closest non-character image block in the boundary area.

  In step 120, the output image is obtained by performing re-aggregation or the like according to the re-aggregation format set by the operation key 18 or an external device or the like using the image data and attribute data that has been de-aggregated and decomposed into each page. Data is generated by the output image data generation unit 44 and stored in the hard disk 26 or output to an external device via the network interface 24 or the like, and the series of processing ends.

  That is, in the present embodiment, as shown in FIG. 3A, a document in which a plurality of images are aggregated is read and the image area and the character area are analyzed by the layout analysis unit 30 and shown in FIG. Such an image for character recognition can be obtained. Then, by performing character recognition on the image for character recognition by the character recognition unit 32, a character recognition image that has been successfully recognized as shown in FIG. 3C is obtained. Since this character recognition image does not include a non-character image that exists in the boundary area that causes noise in the aggregate format determination, the character recognition image is reliably compared with a predetermined aggregate format determination pattern. The aggregation form is determined.

When the aggregation format is determined, the attribute data extraction unit 36 extracts a non-character image existing in the boundary region of the image for character recognition as shown in FIG. Since the attribute data representing the non-character image is added as a page attribute by the attribute data adding unit 42, the aggregated image is decomposed without deleting a specific image such as a comment added to the boundary region. .
(Second Embodiment)
Next, an image processing apparatus according to the second embodiment of the present invention will be described. In the second embodiment, the configuration of the image processing unit is different from that of the first embodiment, and the other configurations are the same, so only the differences will be described.

  FIG. 7 is a block diagram showing a detailed configuration of the image processing unit of the image processing apparatus according to the second embodiment of the present invention. In addition, the thing of the same function structure as 1st Embodiment attaches | subjects and demonstrates the same code | symbol as 1st Embodiment.

  As shown in FIG. 7, the image processing unit of the image processing apparatus according to the second embodiment of the present invention includes an aggregation format analysis unit 46, an attribute data extraction unit 48, an aggregation release unit 38, a resolution conversion unit 40, and attribute data addition. A unit 42 and an output image data generation unit 44.

  The aggregation format analysis unit 46 determines the aggregation format by comparing the image data obtained by reading the document with the image reading unit 12 and a predetermined aggregation format determination pattern. For example, the aggregation format is determined by extracting a pattern having a high degree of coincidence of the boundary areas from the predetermined aggregation format determination patterns shown in FIG.

  The attribute data extraction unit 48 extracts, from the aggregation format determined by the aggregation format analysis unit 46, a non-background image block (specific image) such as a handwritten comment existing in the boundary area of the image aggregated in the document as attribute data. To do. In the present embodiment, the attribute data is extracted by extracting a specific image existing in the determined boundary region of the aggregate format from the document image.

  Based on the analysis result of the aggregation format analysis unit 46, the aggregation cancellation unit 38 performs aggregation by excluding the attribute data extracted by the attribute data extraction unit 48 from the image data obtained by reading the document by the image reading unit 12. Decompose images into individual images.

  The resolution conversion unit 40 converts the resolution of each image canceled by the aggregation cancellation unit 38 in accordance with the re-aggregation format and resolution set by the operation key 18 or the like.

  The attribute data adding unit 42 gives the attribute data extracted by the attribute data extracting unit 48 as a page attribute or adds it as a new page according to a method preset by the operation key 18. For example, the attribute data adding unit 42 may add the attribute data together as a new page, may add the attribute data as a page attribute as shown in FIG. The page where the attribute data of the boundary area is decomposed so that the resolution is slightly smaller than the specified resolution so that the boundary when decomposing the aggregated image is inside the page margin when canceling The attribute data may be added so as to be included in. FIG. 5 shows an example of a display screen that displays each page obtained by disassembling the aggregated image and attribute data of each page.

  The output image data generation unit 44 uses the image data and attribute data decomposed into each page by the aggregation cancellation unit 38 to perform re-aggregation according to the re-aggregation format set by the operation key 18 or an external device. By doing so, output image data is generated. The generated output image data is stored in the hard disk 26 or output to an external device via the network interface 24.

  Next, processing performed by the image processing apparatus according to the second embodiment of the present invention configured as described above will be described. FIG. 8 is a flowchart showing an example of the flow of processing performed by the image processing apparatus according to the second embodiment of the present invention. Note that the flowchart of FIG. 8 starts when, for example, a re-aggregation instruction is given by the operation key 18.

  First, in step 200, the aggregation format of the document images read by the image reading unit 12 is determined by the aggregation format analysis unit 46, and the process proceeds to step 202. In other words, the image data obtained by reading the document by the image reading unit 12 is compared with a predetermined aggregation format determination pattern (for example, the aggregation format determination pattern shown in FIG. 4) to perform aggregation. The format is determined.

  In step 202, the attribute data extraction unit 48 determines whether or not there is an image in the boundary region of the aggregation format determined by the aggregation format analysis unit 46. In this determination, it is determined whether or not there is a non-background image in the boundary area of the document image corresponding to the determined aggregation format. If the determination is negative, the process proceeds to step 204. Goes to Step 208.

  In step 204, the aggregation cancellation unit 38 cancels the aggregation according to the aggregation format determined by the aggregation format analysis unit 46, and the process proceeds to step 206.

  In step 206, the resolution of each image whose aggregation has been canceled is converted by the resolution conversion unit 40 according to the re-aggregation format or resolution set by the operation key 18 or the like, and the process proceeds to step 216.

  On the other hand, in step 208, the non-background image existing in the boundary region is extracted by the attribute data extraction unit 48, and the process proceeds to step 210.

  In step 210, the attribute data extracted by the attribute data extraction unit 48 is removed by the aggregation cancellation unit 38, the aggregation is canceled according to the aggregation format determined by the aggregation format analysis unit 46, and the process proceeds to step 212.

  In step 212, the resolution conversion unit 40 converts the resolution of each image that has been canceled to the resolution set by the operation key 18 or the like, and the process proceeds to step 214.

  In step 214, attribute data is added by the attribute data adding unit 42 according to the setting by the operation key 18 or the like, and the process proceeds to step 216. For example, according to the setting by the operation key 18 or the like, the attribute data is added together as a new page, or the attribute data is added as a page attribute as shown in FIG. Attribute data so that the attribute data of the boundary area is included in the decomposed page by converting the resolution slightly smaller than the specified resolution so that the boundary when the image is decomposed is inside the page margin. Or add. In addition, when attribute data is added as a page attribute as shown in FIG. 5 or when attribute data is added so that the attribute data of the boundary region is included in the decomposed page, the attribute data is extracted by the attribute data extraction unit 48. At the time of extraction, it is added as an attribute of the page with the closest non-background image block in the boundary region.

  In step 216, based on the image data and attribute data that have been de-aggregated and decomposed into each page, an output image that has been re-aggregated according to the re-aggregation format set by the operation key 18 or an external device, etc. Data is generated by the output image data generation unit 44 and stored in the hard disk 26 or output to an external device via the network interface 24 or the like, and the series of processing ends.

  That is, in the present embodiment, an aggregate format is determined by reading a document in which a plurality of images are aggregated and comparing the document with a predetermined aggregation format determination pattern. Thus, although the noise at the time of determining the aggregation format is larger than that in the first embodiment, the determination of the aggregation format is performed reliably.

  When the aggregation format is determined, the attribute data extraction unit 48 extracts a non-background image existing in the boundary area. Then, the attribute data representing the non-background image is added as an attribute of the page by the attribute data adding unit 42 as in the first embodiment, so that a specific image such as a comment added to the boundary region is not deleted, Aggregated images are reliably decomposed.

  The image processing unit in each of the above embodiments has been described as a hardware configuration, but is not limited thereto, and may be a program that causes the CPU to execute the function of the image processing unit.

1 is a block diagram showing a schematic configuration of an image processing apparatus according to a first embodiment of the present invention. It is a block diagram which shows the detailed structure of the image processing part of the image processing apparatus concerning 1st Embodiment of this invention. (A) is a figure which shows an example of a manuscript image, (B) is a figure which shows an example of the image for character recognition produced | generated by the analysis of a layout analysis part, (C) is character recognition by a character recognition part. (D) is a figure which shows an example of the extracted attribute data. (A) is a diagram showing an aggregation format determination pattern for determining an image aggregated by two pages, (B) is a diagram showing an aggregation format determination pattern for determining an image aggregated by four pages, (C) is a diagram showing an aggregation format determination pattern for determining an image in which six pages are aggregated. It is a figure which shows an example of the display screen which displayed each page which decomposed | disassembled the aggregated image, and the attribute data of each page. It is a flowchart which shows an example of the flow of the process performed with the image processing apparatus concerning 1st Embodiment of this invention. It is a block diagram which shows the detailed structure of the image processing part of the image processing apparatus concerning 2nd Embodiment of this invention. It is a flowchart which shows an example of the flow of the process performed with the image processing apparatus concerning 2nd Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image processing apparatus 12 Image reading part 22 Image processing part 30 Layout analysis part 32 Character recognition part 34,46 Aggregation format analysis part 36,48 Attribute data extraction part 38 Aggregation release part 40 Resolution conversion part 42 Attribute data addition part

Claims (10)

Determination means for determining an aggregation format of a plurality of images based on a reading result obtained by reading a document in which a plurality of images are aggregated;
Extraction means for extracting a specific image existing in the boundary region of the aggregated images based on the determination result of the determination means;
A decomposing unit that removes the specific image extracted by the extracting unit from the reading result, and decomposes the reading result into respective images according to the aggregation format determined by the determining unit;
An image processing apparatus.   The determination unit includes an analysis unit that analyzes a component including a character region and an image region of a document, and a character recognition unit that recognizes a character in the character region analyzed by the analysis unit, and the recognition result of the character recognition unit The image processing apparatus according to claim 1, wherein the aggregation format is determined by comparing an aggregation format determination pattern for determining a predetermined aggregation format.   The image according to claim 1, wherein the determination unit determines the aggregation format by comparing the read result with an aggregation format determination pattern for determining a predetermined aggregation format. Processing equipment.   The extraction unit extracts a non-character image existing in a boundary region in the aggregation format determined by the determination unit as the specific image from the image region analyzed by the analysis unit. Image processing apparatus.   The image processing apparatus according to claim 3, wherein the extraction unit extracts, as the specific image, a non-background image existing in a boundary region in the aggregation format determined by the determination unit.   The image processing apparatus according to claim 1, wherein the specific image is an image that is handwritten on a document.   The image processing apparatus according to claim 1, further comprising an adding unit that adds the specific image extracted by the extracting unit so as to be displayed as page attribute data of the extracted page. .   The image processing apparatus according to claim 1, further comprising an adding unit that collectively adds the specific images extracted by the extracting unit to a new page.   And further comprising an adding means for further converting the resolution so that the extracted specific image is included in the page area after adding the specific image into the page area after being decomposed into the respective images by the decomposing means. The image processing apparatus according to claim 1, wherein: On the computer,
A determination step of determining an aggregation format of a plurality of images based on a reading result obtained by reading a document in which a plurality of images are aggregated;
Based on the determination result of the determination step, an extraction step of extracting a specific image existing in the boundary region of the aggregated images;
Decomposing means for excluding the specific image extracted in the extraction step from the reading result, and decomposing the reading result into respective images according to the aggregation format determined in the determining step;
An image processing program for executing

Images