JPH11282849A - Image inspection device and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily give an instruction for rereading by defining a chapter of contents of a document as a unit to the document consisting of plural pages. SOLUTION: The document is stored as document images consisting of plural pages in an image storage part on a hard disk. Index information including titles to indicate chapters to divide the document into plural segments and the number of leading pages of each segment is generated and held by processing an index original in step S 1001. A page image corresponding to the leading page of the segment to be an inspecting object among plural segments (chapters) which are set in the document is retrieved based on the held title and the number of leading pages in step S1002 to step S1006. When the leading page is retrieved, the images equivalent to the number of pages in the corresponding section are inspected in steps S1007, S1008 and its result is presented in step S1009.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image inspection apparatus and an image inspection method for inspecting document image data obtained by reading a document original.

[0002]

2. Description of the Related Art In general, there is known a system for automatically inspecting the quality of an image when a document document or the like is read by an image reading device such as a scanner and stored as image data in a database. In this type of automatic inspection, image data is automatically inspected for image quality, such as front / back inversion, missing pages, double feed, missing images, and poor image density. If an abnormality is detected in the automatic inspection, the document original is read again by the image reading device.

[0003]

However, in the conventional system, if an error is detected by the automatic inspection when the image document is continuously read by the image reading apparatus, the entire document document is read again. It is only possible to give an instruction for re-reading or to give an instruction that is difficult to understand, such as re-reading pages 105 to 213.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and has an image inspection apparatus and method for easily providing a re-read instruction to a document having a plurality of pages in units of document contents. The purpose is to provide.

Another object of the present invention is to make it possible to easily give a re-read instruction in units of a desired number of pages.

Another object of the present invention is to make it possible to give an instruction for re-reading in units of document content breaks set based on the table of contents information of a document manuscript.

[0007]

An image inspection apparatus according to one aspect of the present invention for achieving the above object has, for example, the following configuration. That is, storage means for storing a document as a document image composed of a plurality of page images, and storage for storing table of contents information including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and the number of pages at each delimiter position. Means, based on the table of contents information held by the holding means,
Determining means for determining a range of a document image corresponding to a section to be inspected among the plurality of sections of the document as an inspection range; and each page image of the document image within the inspection range determined by the determining means And inspection means for inspecting the data.

Further, an image inspection apparatus according to another aspect of the present invention for achieving the above object has, for example, the following configuration. That is, storage means for storing a document as a document image composed of a plurality of page images, and storage for storing table of contents information including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and the number of pages at each delimiter position. Means,
Searching means for searching for a page image corresponding to the first page of each of a plurality of sections of the document based on the table of contents information held by the holding means; and the document image of each page image searched by the searching means A generating means for generating error information based on an error between the number of pages at each break position indicated in the table of contents information, and the error information generated by the generating means. Presentation means for presenting a page error.

Further, an image inspection apparatus according to another aspect of the present invention for achieving the above object has, for example, the following configuration. That is, storage means for storing a document as a document image composed of a plurality of page images, setting means for setting a desired number of pages, and a page image corresponding to a page number for each page number set by the setting means. Searching means for searching from a document image; and generating error information based on an error between the number of pages in the document image of each page image searched by the searching means and a page number obtained by the set number of pages. A generating unit; and a presenting unit that presents a page error in units of the number of pages set by the setting unit based on the error information generated by the generating unit.

[0010]

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings.

[First Embodiment] FIG. 1 is a block diagram showing a configuration of a system for realizing document original reading and automatic image inspection according to a first embodiment.

In FIG. 1, reference numeral 51 denotes an image reading device, which comprises a scanner for optically reading a document original. Reference numeral 52 denotes a central processing unit (not shown),
M, RAM. By executing the control program stored in the ROM, the central processing unit 52 realizes functions as an image processing unit 53 for performing block selection processing and a processing unit 54 for instructing operation of the device. An output device 55 includes a display device such as a display, a printer, and the like. Reference numeral 56 denotes a storage device, which is constituted by, for example, a hard disk or the like, and includes an image storage unit 57 for storing image data read by the image reading device 51 and an image inspection result recording unit 58 for storing image inspection results. Reference numeral 59 denotes a bus which connects the above-described components to each other. Note that the block selection process executed by the image processing unit 53 is an image processing method of dividing image data into regions for each attribute such as a character region, a graphic, and a table, and is a technique well known to those skilled in the art.

FIG. 2 is a diagram showing an example of a table of contents document included in a document document to be read. FIG. 3 is a diagram showing an example of a memory table created from the table of contents original shown in FIG. First, the table of contents original shown in FIG. 2 is read using the image reading device 51, and is stored in the image storage unit 57. Next, block selection processing is performed on the read image data to read information on the number, title, and start page of each chapter. The read information is arranged in chapter units as shown in the example of constructing the memory table in FIG.
In this memory table, the data on the number of end pages and the number of pages of a chapter are obtained from the start page of the chapter and the next chapter, (number of end pages of chapter) = (number of start pages of next chapter) −1 (page Number of sheets = (number of end pages)-(number of start pages)
The table of contents information can be read from the table of contents original as easily as +1. For the last chapter in the document, the end page number of the chapter is the last page number of the document document, and the number of pages is the number obtained by subtracting the start page number from the last page number of the document and adding one. The memory table obtained as described above is stored in the RAM of the central processing unit 52.
Is held. In the following description, the number of pages indicates a page number and is used separately from the number of pages.

Next, an automatic inspection procedure according to the first embodiment will be described. FIG. 4 is a flowchart illustrating a procedure of the automatic image inspection according to the first embodiment. First, the block selection of the table of contents original shown in FIG. 2 is executed to generate a memory table as shown in FIG. 3 (step S1001). Next, the title and the number of pages of the chapter to be checked are read from the memory table and acquired as table of contents information (step S1002). Here, the chapter to be checked may be specified by, for example, inputting a chapter number by the user.

Next, a page image corresponding to the number of pages indicated by the start page number of the chapter to be checked is obtained, and it is checked whether or not the image corresponds to the start page of the chapter. First, block selection is performed on the acquired image (step S1003), and it is checked whether the chapter title (obtained from the memory table) in the table of contents information is the same as the chapter title read from the start page. (Step S1004) If they are the same, step S1 is executed to start the image check from the start page.
Proceed to 007.

On the other hand, if the chapter title cannot be read or the chapter title is different at step S1004,
It is checked whether the number of pages in the table of contents information is the same as the page number of the acquired image (step S1005). If they are the same, the image check is started from the acquired page.

Here, if the page number cannot be read or the page number is different, it is checked whether the start page is shifted to the previous or next page. That is, the start page of the automatic inspection is shifted back and forth (step S100).
6), it is checked whether or not the page is the start page by executing steps S1004 and S1005. The value to be shifted in step S1006 is −1, 2 for the first time with respect to the page position of the original document acquired.
The absolute value to be shifted is gradually increased by setting +1 for the third time, -2 for the third time, and +2 for the fourth time.

As described above, if any of the chapter title or the page number matches in the image acquired as the start page, the process proceeds to step S1007 to start the automatic inspection of the image.

In the image check in step S1007, for example, the image is checked for double feed, missing image, page shift, front / back inversion, and the like. This image check is executed until the end page of the chapter (the number of pages acquired in step S1002, that is, the “number of pages” obtained from the memory table in FIG. 3) (step S1).
008). When the image check is completed up to the end page, the check result is displayed (step S1).
009).

In step S1010, the user is inquired whether to check another chapter continuously. If there is an instruction to check another chapter, step S100
Return to 2. If the check is to be terminated, the process is terminated.

As described above, according to the first embodiment, the start page and the number of pages for each chapter are obtained from the table of contents information, and the image data obtained by reading the document manuscript is automatically inspected in chapter units. And the results are displayed in chapter units. Therefore, when there is an abnormality, a reread instruction can be issued in chapter units.

[Second Embodiment] Next, a second embodiment will be described. In the second embodiment, an image inspection apparatus that allows a user to easily recognize in which chapter a page shift has occurred in an entire document is described. The configuration of the image inspection apparatus according to the second embodiment is the same as that of the first embodiment. Hereinafter, the operation of the second embodiment will be described. FIG.
FIG. 6 is a flowchart illustrating a procedure of an automatic image inspection according to the second embodiment.

First, block selection of a table of contents document is executed, the title and page number of each chapter are obtained as table of contents information, and a memory table is generated (step S200).
1). This process is the same as step S1001 (first embodiment, FIG. 4). At this point, a memory table as shown in FIG. 7 is generated. However, the scan result column is blank at the end of step S2001.

Next, the position of the number of title pages of the chapter is provisionally determined from the table of contents information and the accumulated error (step S20).
02). At the time of the first processing in step S2002, the accumulated error is naturally 0. However, if the title of the chapter, the preamble, etc. are not included in the number of pages, the first page is not the first page. Will be done.

Block selection is performed on the page tentatively determined to be the title page, and the page number of the page and the chapter title are read (step S2).
003). Then, it is checked whether the page number has been read (step S2004). If the page number has been read, the read page number is compared with the number of pages obtained by block selection of the table of contents document (step S200).
6). If the page number matches the page number in the table of contents information, the read page number is correct and the page number error is recorded as 0 (step S2009), and if not, the difference is recorded as a page number error (step S2010).

If the page number cannot be read, it is checked whether the chapter title has been read (step S200).
5) If the chapter title can be read, the title of the chapter in the table of contents information is compared with the title of the read chapter (step S2007), and if they are the same, the page number error is recorded as 0 (step S2008).

If the page number cannot be read and the chapter title cannot be read or does not match the chapter title in the table of contents information, the position of the number of pages on which block selection is performed is shifted to check the previous and next pages (step S2101). ). It should be noted that this shift amount is determined in step S
In the repetition of the loop formed by step 2107, the absolute value to be shifted is gradually set to -1, the second time is +1, the third time is -2, and the fourth time is +2 for the page processed in step S2003. Make it bigger.

Block selection is executed for the image of the page located at the number of pages shifted in step S2101, and the page number is read (step S2102). Check whether the page number has been read (step S210)
3) If the page number has been read, the read page number and the number of pages based on the table of contents information (the value obtained by adding the number of pages shifted in step S2101 to the start page of the table of contents information)
Are compared (step S2105). If they match, the page number error is recorded as 0 (step S210).
8) If they are different, the difference is recorded as a page number error (step S2109).

If the number of pages cannot be read, it is checked whether the title of the chapter has been read (step S210).
4) If the title of the chapter is read, the title of the chapter in the table of contents information is compared with the title of the read chapter (step S2106). If they match, the number of sheets shifted at that time is recorded as an error (step S2110). ).

If the number of pages cannot be read and the chapter title cannot be read or does not match the chapter title in the table of contents information, it is checked whether the number of pages shifted is the same as the number determined in the previous chapter check (step S2107). , If the same,
The number of pages shifted and the number of pages from the previous chapter are recorded as a page number error (step S2111). If they are different, the number of pages to be shifted is changed, and the check of the number of pages before and after is repeated.

The page error in the current chapter is added to the accumulated error (step S2011). The above operation is performed up to the last chapter, and when all the chapters have been checked, the result is displayed to the user as a table in FIG. 6 (step S2013).

FIG. 7 is a diagram showing the page number deviation in chapter units. In this way, by displaying the page number shift in chapter units, it is possible to see at a glance in which chapter the page shift has occurred, and to instruct rereading for each chapter. FIG.
The above processing will be specifically described using the example shown in FIG. FIG.
FIG. 1 is a diagram illustrating some of the page images of the document image data from which the scan result of FIG. 7 has been obtained. First, for the first page of the first chapter, the start page of the table of contents information and the start page of the scan result (page image (1)) match, and at this point, the accumulated error is zero. Next, the first page of the second chapter is checked. At this point, since the accumulated error is zero, the 28th page image (28) is checked according to the table of contents information. However, since the page number of the 28th page image is 29, step S
At 2010, the error -1 (28-29 = -1) is recorded as the page error of the first chapter. Next, the first page of Chapter 3 is checked. At this point, since the accumulated error is “−1”, the accumulated error is added to the number of pages 56 of the table of contents information, and 5
The fifth page image (55) is extracted. As a result of checking this page image (55), the page number "56" is read. Since this matches the number of pages in the table of contents information, it is determined that there is no error in the number of pages in the second chapter. “0” is recorded in the page error of the chapter. Even if the page number of the page image (55) cannot be read, if the title "intermediate edition 1" is read, the title matches the table of contents information.
It is determined that there is no error in the number of pages of the second chapter (step S2008). Next, the first page of Chapter 4 is checked. At this point, the cumulative error is “−1”, and the cumulative error is added to the number of pages 89 of the table of contents information to extract the 88th page image (88). . It is assumed that as a result of checking this page image (88), the page number cannot be read and the title cannot be read. Then, in step 2101, the 87th page image (87) is extracted by shifting the number of pages to be processed. Then, according to FIG. 11, as a result of checking the page image (87), the page number “8” is obtained.
9 "will be obtained. Here, the number of sheets shifted is-
Since it is 1, it should be 88 pages according to the table of contents information. Accordingly, in step S2105, a mismatch in the number of pages is detected, and in step S2010, the error “−1” is recorded as the page error in Chapter 3.
Next, the first page of Chapter 5 is checked. At this point, the accumulated error is “−2”, and the number of pages of the table of contents information is 110.
To the 108th page image (108)
Is extracted. If the page number and title cannot be read, the number is shifted and a check is performed in step S2101 and thereafter. First, the page image (107) is checked by shifting the number by −1, but the page number and title cannot be read from the page image (107). Next, the number of pages is shifted by +1 and the 109th page image (109) is checked. Here, it is assumed that the page number is read as “111”. In this case, the shifted number is +1 and
Since it matches the number of pages according to the silent information (110 + 1 = 111), zero is recorded as the page error in Chapter 4 (step S2108). Also, at the time of checking the first page of Chapter 4, even if the page number cannot be read from the page image (87) as shown in FIG. Step S2
Proceeding to 110, the number of shifts "-1" is recorded as the page error of the third chapter.

As described above, when the start page and the number of pages for each chapter are obtained from the table of contents information, and the image data obtained by reading the document manuscript in chapter units is checked for page misalignment, an extra page is checked. Inspection can be performed efficiently without
In addition, by displaying in chapter units, it is possible to give an instruction for re-reading in chapter units when there is an abnormality.

[Third Embodiment] In the above-described second embodiment, a page shift is detected in chapter units. In the third embodiment, a page shift is detected using a desired number of pages as a unit. Hereinafter, the operation of the third embodiment will be described with reference to the flowcharts of FIGS. 8 and 9.

First, the user inputs the number of page skips for how many sheets of the document are to be checked (step S30).
01). The number of pages to be subjected to block selection is determined from the number of page skips, the number of skips, and the accumulated error (step S3002). In the first time, the number of skips is 1, and the accumulated error is naturally 0. If the title of the sentence, the preamble, and the like are not included in the number of pages, the first sheet is not included in the first page, and is added to the accumulated error.

Next, block selection is executed for the determined number of pages, and the page number is read (step S3003). It is checked whether the page number has been read (step S3004). If the page number can be read, the read page number is compared with the number of pages on which block selection has been performed (step S300).
5). If they match, the number of read pages is correct and the page number error is recorded as 0 (step S300).
6) If they are different, the difference between them is recorded as a page number error (step S3007).

On the other hand, if the page number cannot be read, a check is made for the previous and next pages. First, in step S3101, the number of pages to be subjected to block selection is shifted. This shift amount is 1
The first time is -1, the second time is +1, the third time is -2, the fourth time is +
As 2, the absolute value to be shifted is gradually increased. Block selection is executed for the shifted number of pages, and the number of pages is read (step S310).
2).

Next, it is confirmed whether the page number has been read (step S3103). If the page number can be read, the read page number is compared with the number of pages subjected to block selection (step S3105). Then, the read page number is correct and the page number error is recorded as 0 (step S3107), and if different, the difference is recorded as the page number error (step S31).
08).

If the page number could not be read, it is checked whether or not the shifted number is the same as the number determined in the block selection at the previous skip count (step S310).
4) If they are the same, the number of shifted pages and the difference between the skip numbers are recorded as page number errors (step S31).
06) If they are different, change the number of sheets to be shifted, and repeat the check of the number of sheets before and after.

In step S3008, the page error at the current skip count is added to the accumulated error. Then, the above operation is repeated until the last page (step S300)
9). When the check is completed up to the last page, the result is displayed to the user as shown in the table of FIG. 10 (step S3010).

FIG. 10 is a table showing the deviation of the number of pages in skip units. By displaying the page number shift in the skip unit in this manner, it is possible to check the position where the page shift occurs at a desired page number interval, and to easily perform a reread instruction. The above process will be specifically described using the example shown in FIG. FIG. 12 is a diagram showing some page images of the document image data from which the scan result of FIG. 10 has been obtained. First, the 21st page image (21) is acquired according to the skip number. In the page image (21), the page number is read as "21", which matches the skip page number. Zero is recorded as the page error (step S3006). Next, the first page of the skip number 3 is searched. At this point, the accumulated error is zero,
The 41st page image (41) is extracted and the page number is checked. Here, the page number is read as “42”, which is different from the skipped page number 41. Therefore, “−1” is recorded as the page error of the skip number 2 (step S3007). Next, the first page of the skip number 4 is searched. At this point, since the accumulated error is “−1”, the accumulated error is added to the number of skipped pages 61 to extract the 60th page image. Since the page number of the 60th page image cannot be read, the number is shifted. -1 is shifted, and the page number is read from the 59th page image. In FIG. 12, "5
9 "is read. Here, according to the skip number,
This page image (59) should have a page number "60". Therefore, the pages do not match, and the error “+1” is recorded as the page error of skip number 3 (step S3108). At this time, the accumulated error becomes zero again.

As described above, when performing a page shift check on image data obtained by reading a document original in skip units specified by the user, the check can be performed efficiently without checking an extra page. By displaying in skip units, it is possible to give an instruction for re-reading in skip units when there is an abnormality.

As described above, according to each of the above-described embodiments, the automatic inspection and the re-reading instruction of the read image data of the text original can be performed in units of chapters or desired number of pages. Therefore, the operation for re-reading the defective image becomes extremely easy.

Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), an apparatus (for example, a copying machine, a facsimile, etc.) comprising one device Device).

Another object of the present invention is to provide a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or apparatus, and to provide a computer (or CPU) of the system or apparatus.
And MPU) read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

As a storage medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD
-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.

When the computer executes the readout program code, not only the functions of the above-described embodiment are realized, but also an OS (Operating System) running on the computer based on the instruction of the program code. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided on a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instructions of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

[0050]

As described above, according to the present invention,
It is possible to easily give an instruction for re-reading in units of breaks of document contents described in a document manuscript having a plurality of pages.

Further, according to the present invention, it is possible to easily give a rereading instruction in units of a desired number of pages.

[0052]

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a system for realizing document original reading and automatic image inspection according to a first embodiment.

FIG. 2 is a diagram illustrating an example of a table of contents document included in a document document to be read.

FIG. 3 is a diagram showing an example of a memory table created from the table of contents original shown in FIG. 2;

FIG. 4 is a flowchart illustrating a procedure of automatic image inspection according to the first embodiment;

FIG. 5 is a flowchart illustrating a procedure of automatic image inspection according to a second embodiment.

FIG. 6 is a flowchart illustrating a procedure of an automatic image inspection according to the second embodiment.

FIG. 7 is a diagram illustrating a display example in a case where a page number shift is displayed in chapter units.

FIG. 8 is a flowchart illustrating a procedure of automatic image inspection according to the third embodiment.

FIG. 9 is a flowchart illustrating a procedure of automatic image inspection according to the third embodiment.

FIG. 10 is a diagram illustrating a display example in a case where a page number shift is displayed in a desired page number unit.

11 is a diagram showing some page images of document image data obtained from the scan result of FIG. 7;

FIG. 12 is a diagram showing some page images of document image data obtained from the scan result of FIG. 10;

Claims (18)

[Claims] A storage unit configured to store a document as a document image including a plurality of page images; and a table of contents including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and a page number at each delimiter position. Holding means for holding, and determining means for determining, based on the table of contents information held by the holding means, a range of a document image corresponding to a section to be inspected among the plurality of sections of the document as an inspection range. An image inspection apparatus, comprising: inspection means for inspecting each page image of the document image within the inspection range determined by the determination means. 2. The method according to claim 1, wherein the division is a chapter in a document, and the delimiter character string is a chapter title.
An image inspection apparatus according to claim 1. 3. The determining unit searches for a page image that matches at least one of a delimiter character string and a page number corresponding to a section to be inspected, and determines the searched page image as a head of the inspection range. The image inspection apparatus according to claim 1, wherein the inspection is performed. 4. The determination means obtains the number of pages in a section to be inspected based on the table of contents information, and inspects the acquired page images starting from the retrieved page images to inspect the acquired page images for the number of pages. The image inspection apparatus according to claim 3, wherein the image inspection apparatus determines the range. 5. The determination means obtains the number of pages corresponding to the section to be inspected from the table of contents information, extracts page images at the number of pages corresponding to the number of pages, and thereafter, determines the number of pages before and after that. Extracting means for sequentially extracting the page images, and each time one page image is extracted by the extracting means, a character string corresponding to the delimiter character string of the section to be inspected or a page corresponding to the number of pages 4. A determination means for determining whether at least one of the numbers is present in the page image, and determining that the page image is the first page of the section when it is determined that the number is present. An image inspection apparatus according to claim 1. 6. A storage unit for storing a document as a document image composed of a plurality of page images, and a table of contents including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and the number of pages at each delimiter position. Holding means for holding; searching means for searching for a page image corresponding to each first page of a plurality of sections of the document based on the table of contents information held by the holding means; Generating means for generating error information based on an error between the number of pages of the page image in the document image and the number of pages at each break point indicated in the table of contents information, and based on the error information generated by the generating means. And a presentation unit for presenting a page error in units of the sections. 7. The search unit searches, for each of the plurality of sections, for a page image in which at least one of a delimiter character string corresponding to the section and the number of pages matches, and searches the searched page image for the section. The image inspection apparatus according to claim 6, wherein the first page image is used. 8. The search means obtains the number of pages corresponding to the section from the table of contents information for each of the plurality of sections, extracts a page image at the number of pages corresponding to the number of pages, and thereafter, Extracting means for sequentially extracting the page images at the number of pages, and each time one page image is extracted by the extracting means, a character string or the number of pages corresponding to the delimiter character string of the section to be inspected A determination unit configured to determine whether at least one of the corresponding page numbers exists in the page image, and to determine that the page image is the first page of the section when determined to be present. The image inspection apparatus according to claim 6. 9. The image according to claim 8, wherein the number position set first by the extraction unit is obtained by correcting the number of pages obtained from the table of contents information based on the error information. Inspection equipment. 10. A storage unit for storing a document as a document image composed of a plurality of page images, a setting unit for setting a desired number of pages, and a page corresponding to a page number for each page number set by the setting unit Searching means for searching an image from the document image; error information based on an error between the number of pages in the document image of each page image searched by the searching means and a page number obtained by the set number of pages And a presentation unit that presents a page error in units of the number of pages set by the setting unit based on the error information generated by the generation unit. . 11. The search means, for each of a plurality of divisions obtained by dividing the document by the number of pages set by the setting means, sets the number of pages corresponding to the head of the division to the set page. Extracting means for extracting the page images at the number of pages corresponding to the number of pages, and thereafter sequentially extracting the page images at the number of pages before and after that, and extracting one page image by the extracting means. Each time the page image has a page number corresponding to the top of the section in the page image, and determining that the page image is the first page of the section if it is determined that the page number exists. The image inspection apparatus according to claim 10, further comprising: 12. The image according to claim 11, wherein the number position set first by said extraction means is obtained by correcting the number of pages obtained from said table of contents information based on said error information. Inspection equipment. 13. A storing step of storing a document in a storage unit as a document image including a plurality of page images, a delimiter character string indicating a delimiter for dividing the document into a plurality of sections, and the number of pages at each delimiter position. A holding step of holding the table of contents information in the storage means; and, based on the table of contents information held in the holding step, a range of a document image corresponding to a section to be checked out of the plurality of sections of the document. And an inspection step of inspecting each page image of the document image within the inspection range determined in the determination step. 14. A storage step of storing a document in a storage unit as a document image composed of a plurality of page images, a delimiter character string indicating a delimiter for dividing the document into a plurality of sections, and the number of pages at each delimiter position. A holding step of holding the table of contents information in a storage unit, a search step of searching for a page image corresponding to a first page of each of the plurality of sections of the document based on the table of contents information held in the holding step; A generating step of generating error information based on an error between the number of pages in the document image of each page image searched in the step and the number of pages at each delimiting position indicated in the table of contents information; A step of presenting a page error in units of the sections based on the obtained error information. 15. A storing step of storing a document in a storage unit as a document image composed of a plurality of page images, a setting step of setting a desired number of pages, and a page number for each page number set in the setting step. A retrieval step of retrieving a corresponding page image from the document image, based on an error between the number of pages in the document image of each page image retrieved in the retrieval step and a page number obtained by the set number of pages And generating a page error based on the error information generated in the generating step, and presenting a page error in units of the number of pages set in the setting step. Image inspection method. 16. A storage medium for storing a control program for causing a computer to execute an image inspection, wherein the control program stores a code as a document image including a plurality of page images in a storage unit. And a code of a holding step of holding in the storage means index information including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and the number of pages at each delimiter position; and the index information held in the holding step A code of a determining step of determining a range of a document image corresponding to a section to be inspected among a plurality of sections of the document as an inspection range, based on the A code for an inspection process for inspecting each page image of the document image. 17. A storage medium for storing a control program for causing a computer to execute an image inspection, wherein the control program stores a document in a storage unit as a document image including a plurality of page images. And a code of a holding step of holding in the storage means index information including a delimiter character string indicating a delimiter for dividing the document into a plurality of sections and the number of pages at each delimiter position; and the index information held in the holding step A code of a search step of searching for a page image corresponding to each of the first pages of the plurality of sections of the document, a number of pages in the document image of each page image searched in the search step, and a table of contents A code of a generation step for generating error information based on an error with the number of pages at each break position indicated in the information, and a code generated in the generation step Storage medium based on the difference information, characterized by comprising a code presenting step for presenting a page error the segment as a unit. 18. A storage medium for storing a control program for causing a computer to execute an image inspection, wherein the control program stores a document in a storage unit as a document image including a plurality of page images. A code of a setting step of setting a desired number of pages; a code of a search step of searching a page image corresponding to a page number for each page number set in the setting step from the document image; A code of a generation step of generating error information based on an error between the number of pages of the retrieved page image in the document image and a page number obtained by the set number of pages; A code of a presentation step of presenting a page error in units of the number of pages set in the setting step based on the error information. Storage medium characterized.