JP2014006636A - Image processor, image processing method, image processing program, and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor capable of automatically detecting a non-comparison target document, correcting a shift of a comparison target thereafter, and thereby continuously comparing the comparison target documents corresponding to each other even when each document set on which the document comparison is to be performed includes the same number of non-comparison target documents, and thereby reducing the number of processes for rearranging a document set.SOLUTION: An image processor 100 comprises: an image data set acquisition part 101; a page division part 102; an image pair generation part 103; an image comparison part 104; an image determination part 105; a page correction part 106; and a position shift display image output part 107. The image pair generation part 103 makes a pair of image data determined to have high similarity with each other between image data of each image data set. The image determination part 105 determines image data not to be the pair as a non-comparison target document. The page correction part 106 removes the non-comparison target document from the image data set, and performs a page correction.

Description

  The present invention relates to an image processing apparatus, an image processing method, an image processing program, and a recording medium that perform processing related to misregistration between a plurality of document sets.

  The operations of comparing two printed documents, checking whether the documents are different, or searching for differences are very common in business situations. There are various types of business documents, such as forms, text documents, and drawings. To compare two documents, read the document with a reader, convert it to digital image data, perform alignment, compare and detect misalignment, display the result in an easy-to-understand manner, and output it Technology exists.

  For example, in Patent Document 1, two print images are converted into data, and after correction of misregistration, the data of the two print images are compared, and misregistration display in which a portion that does not match a pixel is color-coded. A technique for creating an image is disclosed. This technique makes it possible to easily grasp pixel differences.

  In order to compare two documents, a technique is used in which a document is scanned and converted into digital image data, alignment and comparison processing are performed, misregistration is detected, and the result is displayed and output. The block configuration of this system is illustrated in FIG. The system shown in FIG. 12 includes an image processing device 500, a scanner 510, and an output device 520. Two printed documents are converted into data, and their misalignment is output so as to be visible. In this system, a plurality of document sets can be compared with each other by the image processing apparatus 500 performing the processing a plurality of times.

  For the purpose of easily grasping the difference between two documents, Patent Document 1 discloses an apparatus that detects, visualizes, and outputs a positional deviation between document images. This misalignment detection device can easily grasp the difference by digitizing the two images, comparing and comparing them, and generating a result image that displays the same part and the difference color-coded and displayed in an easy-to-understand manner. It has a configuration.

  Further, in Patent Document 2, when a document that is not a comparison target (hereinafter referred to as “non-comparison target document”) is inserted in the document set, the non-comparison target document is automatically detected, and the subsequent comparison is performed. There is disclosed a technique capable of correcting a difference between objects and performing comparison between corresponding comparison objects. With this technology, when a non-comparison target document is inserted into only one document set, the document set including the non-comparison target document must be newly reconfigured into a document set excluding the non-comparison target document. Can also compare documents.

  However, according to the conventional document comparison system as described above, when comparing a plurality of document sets, the same number or the same number of non-comparison target documents are inserted in both document sets. When there is a missing document, there is a problem that the document sets cannot be compared well because there is no difference in the number of pages. For example, as shown in FIG. 13, a document set 610A (Document 1, Document 2, Document 3, Document 4, Document b, Document 5) and Document Set 610B (Document 1 ′, Document 2 ′, Document a, Document 3 ′) In the comparison between the document 4 ′ and the document 5 ′), after comparing the document 1 and the document 1 ′ and the document 2 and the document 2 ′, respectively, the non-comparison target document a is inserted in the document set 610B. Since the non-comparison target document b is inserted in the document set 610A, the number of pages of the document set 610A and the document set 610B is the same, so it is determined which of the non-comparison target document a and the document 3 should be excluded. It is not possible to do the intended comparison.

  Therefore, in such a case, a new document set obtained by removing the non-comparison target document b from the document set 610A or a new document set obtained by removing the non-comparison target document a from the document set 610B must be recreated. I must. Here, whether or not a non-comparison target document has been inserted can be known when the comparison result is confirmed after comparison.If the number of inserted documents is large, a new document set is recreated after all comparisons are completed, and the comparison is performed. It will have to start over and it will take a lot of steps.

  The present invention has been made in view of the above-described problems of the prior art, and automatically detects non-comparison target documents even when the same number of non-comparison target documents are included in each document set to be compared. It is an object of the present invention to provide an image processing apparatus that can continuously compare corresponding comparison objects by correcting a shift in comparison objects thereafter and reduce the number of steps for recreating a document set. To do.

  In order to solve the above-described problems and achieve the object, an image processing apparatus of the present invention includes an image data set acquisition unit that acquires at least two digital image data sets, and each of the image data set acquisition units acquired by the image data set acquisition unit. An image data group for similarity determination having the number of images specified in page order from one of the image data sets is created, and each image data of the image data set in which the image data group has not been created and the image data group The image pair creating unit which determines the similarity between each of the image data and sets the image data determined to have a high similarity as a pair, and the image data having a high similarity by the image pair creating unit An image determination unit that determines that the image data determined not to exist is a non-comparison target image, and image data that includes the non-comparison target image based on the determination of the image determination unit A page correction unit for correcting the page after the said non-comparison image for Tsu bets, characterized by comprising a.

  According to the present invention, even when the same number of non-comparison target documents are included in each document set for document comparison, the non-comparison target documents are automatically detected and the subsequent comparison target deviation is corrected. Thus, it is possible to provide an image processing apparatus that can continuously compare corresponding comparison objects and reduce the number of steps for recreating a document set.

FIG. 1 is a diagram illustrating a hardware configuration of an image processing apparatus and peripheral devices according to the first embodiment of the present invention. FIG. 2 is a block diagram showing a hardware configuration of the image processing apparatus according to the first embodiment of the present invention. FIG. 3 is a block diagram showing a functional configuration of the image processing apparatus according to the first embodiment of the present invention. FIG. 4 is a view for explaining an image pair creation method (part 1) using an image data group according to the first embodiment of the present invention. FIG. 5 is a diagram for explaining an image pair creation method (part 2) using the image data group according to the first embodiment of the present invention. FIG. 6 is a flowchart showing an example of image pair creation processing according to the first embodiment of the present invention. FIG. 7 is a diagram for explaining a method for outputting the result of image comparison according to the first embodiment of the present invention. FIG. 8 is a diagram for explaining an image pair creation method in a case where pages are changed in the image data set according to the second embodiment of the present invention. FIG. 9 is a flowchart showing an example (part 1) of the image pair creation processing according to the second embodiment of the present invention. FIG. 10 is a flowchart showing an example (part 2) of the image pair creation processing according to the second embodiment of the present invention. FIG. 11 is a diagram for explaining a method of outputting the result of image comparison according to another embodiment of the present invention. FIG. 12 is a diagram illustrating a functional configuration in an image processing apparatus that performs conventional misregistration detection. FIG. 13 is a diagram for explaining a problem that may occur in the conventional image comparison process.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(First embodiment)
FIG. 1 is a diagram illustrating a hardware configuration of the image processing apparatus 100 and peripheral devices according to the first embodiment of the present invention. The image processing apparatus 100 reads a plurality of document sets (for example, the first document set 210 and the second document set 220) with the scanner 110, and converts each into a digital image data set.

  The image processing apparatus 100 compares the images of the two digital image data sets acquired via the scanner 110 one page at a time, and repeats the misregistration detection process, so that the misregistration display image set 230 as the processing result is obtained. Is output to the output device 120. Details of the processing in the image processing apparatus 100 will be described later.

  FIG. 2 is a block diagram showing a hardware configuration of the image processing apparatus 100 according to the present embodiment. As shown in FIG. 2, the image processing apparatus 100 has a configuration in which a controller 10 and an engine unit (Engine) 60 are connected via a PCI (Peripheral Component Interface) bus.

  The controller 10 is for controlling the entire image processing apparatus 100 and drawing, communication, and input from the input unit 21.

  The controller 10 includes a CPU 11, a system memory (MEM-P) 12, a north bridge (NB) 13, a south bridge (SB) 14, an ASIC (Application Specific Integrated Circuit) 16, and a local memory (MEM-C). 17 and a hard disk drive (HDD) 18, and the NB 13 and the ASIC 16 are connected by an AGP (Accelerated Graphics Port) bus 15.

  The CPU 11 performs overall control of the image processing apparatus 100, has a chip set composed of MEM-P 12, NB 13, and SB 14, and is connected to other devices via this chip set.

  The MEM-P 12 is a system memory used as a memory for storing programs and data, a memory for developing programs and data, and a drawing memory for printers. The ROM (Read Only Memory) 12a and a RAM (Random Access Memory) 12b. And have.

  The ROM 12a is a read-only memory used as a memory for storing programs and data. The RAM 12b is a writable and readable memory used as a program and data development memory, a printer drawing memory, and the like.

  The NB 13 is a bridge for connecting the CPU 11 to the MEM-P 12, SB 14, and AGP 15. The NB 13 includes a memory controller that controls reading and writing with respect to the MEM-P 12, a PCI master, and an AGP target (both not shown).

  The SB 14 is a bridge for connecting the NB 13 to a PCI device and peripheral devices. The SB 14 is connected to the NB 13 via a PCI bus, and a network interface (I / F) unit and the like are also connected to the PCI bus.

  The AGP bus 15 is a bus interface for a graphics accelerator card proposed for speeding up graphics processing. The AGP bus 15 speeds up the graphics accelerator card by directly accessing the MEM-P 12 with high throughput. It is.

  The ASIC 16 is an IC (Integrated Circuit) for image processing having hardware elements for image processing, and has a role of a bridge that connects the AGP 15, the PCI bus, the HDD 18, and the MEM-C 17.

  Although not specifically illustrated, the ASIC 16 includes a PCI target and an AGP master, an arbiter (ARB) that forms the core of the ASIC 16, a memory controller that controls the MEM-C 17, and a plurality of image data that are rotated by hardware logic or the like. And a PCI unit that performs data transfer between the DMAC (Direct Memory Access Controller) and the engine unit 60 via the PCI bus.

  The ASIC 16 is connected to an FCU (Facile Control Unit) 30, a USB (Universal Serial Bus) 40, and an IEEE 1394 (the Institute of Electrical Engineers 50) interface via an PCI bus. The operation display unit 20 and the input unit 21 are connected to the ASIC 16.

  The MEM-C 17 is a local memory used as a copy image buffer and a code buffer. The HDD 18 is a storage for storing image data, programs, font data, and forms.

  The input unit 21 is a unit that outputs to the ASIC 16 the number of non-comparison target documents that are predicted to be continuously included in the document set input by the user.

  The engine unit 60 is a printer engine that can be connected to a PCI bus, and is, for example, a monochrome plotter, a one-drum color plotter, a four-drum color plotter, a scanner, or a fax unit. The engine unit 60 includes an image processing part such as error diffusion and gamma conversion in addition to a so-called engine part such as a plotter.

  FIG. 3 is a block diagram showing a functional configuration of the image processing apparatus 100 according to the first embodiment of the present invention. A scanner 110 and an output device 120 are connected to the image processing apparatus 100.

  The image processing apparatus 100 includes an image data set acquisition unit 101, a page division unit 102, an image pair creation unit 103, an image comparison unit 104, an image determination unit 105, a page correction unit 106, and a misalignment display image output. Part 107.

  The image data set acquisition unit 101 acquires digital image data of each document set (first document set 210 and second document set 220 in FIG. 1) read by the scanner 110 as an image data set.

  The page dividing unit 102 divides the two image data sets acquired by the image data set acquisition unit 101 into image data for each page for each document set in order to perform actual image comparison.

  The image pair creation unit 103 is an image data group for similarity determination (hereinafter, simply referred to as “image data group”) from one of the two image data sets acquired by the image data set acquisition unit 101. , And the similarity between the other image data set and each image data of the image data group is determined, and the image data having a high similarity are made into a pair.

  The image comparison unit 104 compares the two image data paired by the image pair creation unit 103, and creates data having a value indicating whether each pixel matches or is different.

  Here, the image comparison processing of the two image data made into a pair by the image pair creation unit 103 may be performed using, for example, a technique (Patent Document 3) previously proposed by the present applicant. it can.

  When there is no image data with high similarity in the image data for which the similarity is determined by the image pair creation unit 103, the image determination unit 105 determines that the determined image data is an image that is not a comparison target (that is, non-comparison). Target document).

  The page correction unit 106 discards the image data determined to be a non-comparison target document by the image determination unit 105, and corrects the page so that the image data set and the determination image data group correspond correctly. That is, the page correction unit 106 corrects a page after the non-comparison target image for the image data set including the non-comparison target image.

  The misalignment display image output unit 107 outputs the result of comparison by the image comparison unit 104 as a misalignment display image. The method for outputting the misalignment display image is described in detail in the aforementioned Patent Document 1, so please refer to it.

  4 (a) to 4 (d) and FIGS. 5 (a) to 5 (d) show an image pair creation method according to the present embodiment, that is, create a pair having a high similarity between document sets. It is a figure explaining the method to do.

  FIG. 4A is a diagram illustrating a state in which the document data set is divided into pages by the page dividing unit 102. The image pair creation unit 103 determines similarity using the document data sets 4A and 4B divided for each page.

  FIG. 4B shows a case where similarity is determined between the document data set 4A (hereinafter simply referred to as “document set 4A”) and the image data group 4B1 using the image data group 4B1 for similarity determination. It is a figure which shows the process of. As shown here, the image pair creation unit 103 extracts a predetermined number of pages (four pages in the illustrated example) from the document data set 4B (hereinafter simply referred to as “document set 4B”). And the similarity is determined between the first page of the document set 4A and the first page of the image data group 4B1. Here, the number of pages extracted as the image data group 4B1 from the document set 4B can be arbitrarily designated by the user via the input unit 21 (FIG. 2).

  FIG. 4C is a diagram illustrating a state in which the image data group 4B1 is updated when a document having a high similarity exists between the document set 4A and the image data group 4B1. As shown here, when it is determined that a document having a high similarity to the document set 4A exists in the image data group 4B1, the image pair creation unit 103 sets the documents as an image pair (one pair). Then, the image pair creation unit 103 excludes the pages that are image pairs from the image data group 4B1, and replenishes the image data group 4B1 with the same number of excluded pages from the document set 4B.

  FIG. 4D is a diagram showing processing when the first page of the image data group 4B1 is a document b that does not exist for comparison. As shown here, when the image pair creation unit 103 determines that the similarity between the document b and the document 2 in the document set 4A is low, the document 2 ′ and the document that are the next page of the document b in the image data group 4B1 The similarity of the document 2 in the set 4A is determined. If it is determined that the similarity between the document 2 ′ and the document 2 is high, the image pair creation unit 103 excludes the document b from the similarity determination target.

  FIG. 5A is a diagram showing processing when a non-comparison target document is inserted in the image data group 4B1. As shown here, the image pair creation unit 103 displays a total of two pages: a document b determined to have a low similarity and a document 2 ′ determined to have a high similarity to the document 2 in the document set 4A. The image data group 4B1 is newly supplemented with two pages of documents 5 ′ and 6 ′. As described above, the image pair creation unit 103 supplements the image data group 4B1 with the same number of pages as the number of excluded pages.

  FIG. 5B is a diagram showing processing when the document in the document set 4A is a document a that does not exist for comparison. As shown here, the similarity between all the documents in the image data group 4B1 and the document a in the document set 4A is determined, and the document a in the document set 4A has a similarity to all the documents in the image data group 4B1. The result is low.

  (C) of FIG. 5 is a figure which shows a process when the result that the similarity of the document a of the document set 4A and all the documents of the image data group 4B1 is low is obtained. As shown here, the image pair creation unit 103 determines the similarity between the document 3 that is the next page of the document a in the document set 4A and the document 3 ′ that is the first page of the image data group 4B1. When it is determined that the similarity between the document 3 in the document set 4A and the document 3 ′ in the image data group 4B1 is high, the image pair creation unit 103 excludes the document a from the similarity determination target.

  FIG. 5D is a diagram showing processing when the number of remaining pages of the document set 4B is smaller than the number of pages constituting the image data group 4B1. As shown here, when the number of remaining pages of the document set 4B is smaller than the number of pages constituting the image data group 4B1, the image pair creation unit 103 extracts all the pages of the document set 4B as the image data group 4B1. .

  In the image processing apparatus 100 according to the present embodiment, as illustrated in (d) of FIG. 4 and (a) to (c) of FIG. 5, a non-comparison target document is detected, and the next document is excluded from the document. By continuing to determine similarity, comparisons can be made as intended without recreating the document set.

  Further, in the image processing apparatus 100 according to the present embodiment, as exemplified in FIGS. 4A to 4D and FIGS. 5A to 5D, the image data group 4B1 is created and the similarity is determined. I do. As a result, when there is a non-comparison target document in the document set 4A, the non-comparison target document of the document set 4A can be determined only by determining the similarity between each document extracted as the image data group 4B1 and the document set 4A. Therefore, the processing speed of the image processing apparatus 100 can be improved.

  FIG. 6 is a flowchart showing an example of image pair creation processing according to the present embodiment.

  First, the scanner 110 (FIG. 1) reads the first document set 210 and the second document set 220 as image data, respectively, and the image data set acquisition unit 101 (FIG. 3) reads the image data set 6A and the image data set 6B, respectively. Obtain (step S201).

  Next, the image pair creation unit 103 initializes the value of the comparison target page i in the image data set 6A and the value of the comparison target page j in the image data set 6B (step S202).

  Next, the image pair creation unit 103 sets the page number X of non-comparison target images that are predicted to be continuously included in the image data set 6B designated by the user via the input unit 21 (FIG. 2). (Step S203).

  Next, the image pair creation unit 103 sets the final page number k of the document extracted as the image data group 6B1 from the image data set 6B (step S204).

  Next, the image pair creation unit 103 performs similarity determination on the image of page i in the image data set 6A and the image on page j in the image data set 6B (hereinafter referred to as “similarity determination target”). (Step S205).

  Next, the image pair creation unit 103 determines the similarity between the image of page i of the image data set 6A and the image of page j of the image data set 6B (step S206).

  Here, with respect to the determination of the similarity between the image of the page i of the image data set 6A and the image of the page j of the image data set 6B (step S206), for example, a technique previously proposed by the present applicant (Patent Document) 4).

  When it is determined that the similarity is not high between the image of the page i of the image data set 6A and the image of the page j of the image data set 6B (step S206, NO), the image pair creation unit 103 selects the image data set 6B. It is determined whether or not the page number j is the same as k (step S209).

  If it is determined that the page number j of the image data set 6B is not the same as k (step S209, NO), the image pair creation unit 103 adds 1 to the page number j (step S210), and the step The process returns to S205 (see FIG. 4D).

  On the other hand, when it is determined that the page number j of the image data set 6B is the same as k (step S209, YES), the image pair creation unit 103 adds 1 to the page number i of the image data set 6A, The set value X is subtracted from the page number j of the image data set 6B (step S211), and the process returns to step S205. As a result, when an image having a high similarity to the image of page i of the image data set 6A does not exist in the image data group B1, the image pair creation unit 103 changes the image of the image data set 6A by one page, and the image data group The page to be determined in B1 is returned to the top (see FIGS. 5B and 5C).

  When it is determined that the similarity between the image of page i in the image data set 6A and the image of page j in the image data set 6B is high (step S206, YES), the image pair creation unit 103 selects the image data set 6A. The image of page i and the image of page j of image data set 6B are set as an image pair (step S207).

  Next, the image pair creation unit 103 determines whether the similarity determination target page is the last page of the image data set 6A (step S208). If the similarity determination target page is determined to be the last page of the image data set 6A (YES in step S208), the image pair creation process ends (END).

  On the other hand, when it is determined that the similarity determination target page is not the last page of the image data set 6A (step S208, NO), the image pair creation unit 103 sets the page numbers of the image data sets 6A and 6B to one each. Addition is performed (step S212), and the process returns to step S204 (see FIG. 4C).

  7A to 7C describe in detail an example of processing of the misalignment display image output unit 107 (FIG. 3) that displays the comparison result in the image comparison unit 104. FIG.

  FIG. 7A is a diagram illustrating a method of displaying a comparison result between documents determined as image pairs in the image pair creation unit 103. Here, the images 71A and 71B are images of each document set, and the image 71C is an output image based on a comparison result between the images 71A and 71B. As shown here, a portion common to each image is displayed in black.

  FIG. 7B is a diagram for explaining processing when the image determination unit 105 determines that the image 72B of the document set in which the image data group for similarity determination is created is a non-comparison target document. is there. Here, the image 72A is an image used for comparison with a non-comparison target document, and for example, a white image is used. As shown here, in the output image 72C based on the comparison result between the images 72A and 72B, a portion that exists only in the image 72B is displayed in red.

  FIG. 7C is a diagram exemplifying processing when the image determination unit 105 determines that the image 73A of the document set in which the image data group for similarity determination is not created is a non-comparison target document. . Here, the image 73B is an image used for comparison with a non-comparison target document, and for example, a white image is used. As shown here, in the output image 73C based on the comparison result between the images 73A and 73B, a portion that exists only in the image 73A is displayed in yellow.

  The misalignment display image output unit 107 according to the present embodiment displays that the non-comparison target document has been inserted in a different color regardless of whether the non-comparison target document is inserted in any of the document sets. Can easily recognize the presence or absence of non-comparison target documents.

  As described above, according to the present embodiment, since the image pair is created using the image data group, the image processing apparatus 100 can be used even when a non-comparison target document is inserted in any of the document sets. Can perform processing as intended.

  In addition, since the image pair is created using the image data group, when the non-comparison target document is inserted in the document set in which the image data group is not created, the image processing apparatus 100 selects the other document set. Since it is not necessary to determine the similarity with all the images, it is possible to efficiently determine the similarity. This contributes to an improvement in processing speed.

(Second Embodiment)
In the second embodiment, an image processing apparatus 100 and peripheral devices (FIG. 1) having the same configuration as in the first embodiment are used. Therefore, a detailed description of the configuration and function of the image processing apparatus 100 is omitted.

  FIGS. 8A to 8C are diagrams illustrating a method for creating a set having high similarity between document sets in the second embodiment. Here, unlike the method in the first embodiment, the image pair creation unit 103 uses a method of creating an image pair without excluding the replaced page as a non-comparison target document.

  FIG. 8A is a diagram showing that the document data set is divided into pages by the page dividing unit 102. As shown here, in the document set 8B, there is a document 2 ′ having a high similarity to the second page of the document 2 of the document set 8A on the first page, and the second page is the first page of the document set 8A. Document 1 ′ having a high degree of similarity with document 1 of FIG.

  FIG. 8B is a diagram showing that similarity determination is performed between the document set 8A and the image data group 8B1 using the image data group 8B1. As shown here, the image pair creation unit 103 determines that the similarity between the document 1 of the document set 8A and the document 2 ′ of the image data group 8B1 is low, and the document 1 ′ that is the next page of the image data group 8B1. And the similarity of the document 1 of the document set 8A is determined.

  (C) of FIG. 8 is a figure which shows the process about image data group 8B1 when the image determined that the similarity degree is low exists. As shown here, the image pair creation unit 103 replenishes the image data group 8B1 not only with the document 5 ′ but also with the document 2 ′ that is an image determined to have low similarity.

  As illustrated in FIG. 8C, the image processing apparatus 100 according to the present embodiment performs similarity determination without excluding pages in which pages are misplaced between document sets. Therefore, even if there is a page misplacement, the intended comparison process can be performed.

  9 and 10 are flowcharts showing an example of the image pair creation processing according to the present embodiment.

  First, the scanner 110 (FIG. 1) reads the first document set 210 and the second document set 220 as image data, respectively, and the image data set acquisition unit 101 (FIG. 3) reads the image data set 9A and the image data set 9B, respectively. Obtain (step S301).

  Next, the image pair creation unit 103 selects the value of the comparison target page i of the image data set 9A, the value of the comparison target page j of the image data set 9B, the value of the page feed count m of the image data group 9B1, and the image data set 9B. , The value of the set N that stores the page number of the page on which the image pair is created, the value of the element number p of the element Np stored in the set N, and the number q of the elements Np stored in the set N are initialized. (Step S302).

  Next, the image pair creation unit 103 designates the page number X of non-comparison target images that are predicted to be continuously included in the image data set 9B designated by the user via the input unit 21 (FIG. 2). (Step S303).

  Next, the image pair creation unit 103 stores the first page number of the image data set 9B on which image pair creation processing is performed (step S304). Here, the variable t represents the page number of the image data set 9B in which the similarity is first determined in one image pair creation process. For this reason, the variable t is updated every time one image pair is created.

  Next, the image pair creation unit 103 sets the final page number k of the document extracted as the image data group 9B1 from the image data set 9B (step S305).

  Next, the image pair creating unit 103 determines whether or not the same number as the page number j of the image data set 9B is included in the elements of the set N (step S306).

  When it is determined that the same number as the page number j of the image data set 9B is included in the elements of the set N (step S306, YES), the image pair creation unit 103 adds 1 to the page number j, q 1 is subtracted from (Step S324), and the process returns to Step S304. This is to prevent duplication of processing because the image pair creation unit 103 has already created an image pair including the page j when YES is obtained in step S306.

  On the other hand, when it is determined that the same number as the page number j of the image data set 9B is not included in the elements of the set N (NO in step S306), the image pair creation unit 103 selects the page i of the image data set 9A. The image and the image of page j of the image data set 9B are set as similarity determination targets (step S307).

  Next, the image pair creation unit 103 determines the similarity between the image of page i in the image data set 9A and the image of page j in the image data set 9B (step S308).

  When it is determined that the similarity is not high between the image of the page i in the image data set 9A and the image of the page j in the image data set 9B (NO in step S308), the image pair creation unit 103 selects the image data set 9B. It is determined whether or not the page number is the same as k (step S311).

  Here, when it is determined that the page number j of the image data set 9B is not the same as k (step S311, NO), the image pair creation unit 103 adds 1 to the page number j (step S312).

  Next, the image processing apparatus 103 adds 1 to the page feed count m of the image data group 9B1 (step S313), and returns to the process of step S306.

  On the other hand, when it is determined that the page number j of the image data set 9B is the same as k (step S311, YES), the image pair creation unit 103 adds 1 to the page number i of the image data set 9A. Then, the variable m is subtracted from the page number j of the image data set 9B (step S314). Then, the page feed count m of the image data group 9B1 is initialized (step S315), and the process returns to step S306. As a result, when there is no image in the image data group 9B1 that has a high degree of similarity to the image on page i in the image data set 9A, the image pair creation unit 103 changes the image in the image data set 9A by one page, and the image data group The page to be determined of 9B1 is returned to the top.

  When it is determined that the degree of similarity is high between the image of page i of image data set 9A and the image of page j of image data set 9B (step S308, YES), image pair creation unit 103 performs image data set 9A. The image of page i and the image of page j of image data set 9B are set as an image pair (step S309).

  Next, the image pair creation unit 103 determines whether the similarity determination target page is the last page of the image data set 9A (step S310). When the similarity target page is determined to be the last page of the image data set 9A (step S310, YES), the image pair creation process ends (END).

  On the other hand, when it is determined that the similarity determination target page is not the last page of the image data set 9A (step S310, NO), the image pair creation unit 103 has the page number j of the image data set 9B equal to the variable t. It is determined whether or not (step S316). Here, when it is determined that the page number j of the image data set 9B is the same as the variable t (step S316, YES), the image pair creation unit 103 sets the page numbers of the image data sets 9A and 9B to 1 each. Addition is performed (step S317), and the process returns to step S304.

  On the other hand, when it is determined that the page number j of the image data set 9B is not the same as the variable t (step S316, NO), the current page number is stored (step S318). Here, the element Np corresponds to the page number of the image data set 9B when there is a page that is an image pair other than the first page of the image data group 9B1.

  Next, the image pair creation unit 103 adds the element Np as one element of the set N (step S319). Here, the set N is a set that can store a plurality of elements Np.

  Next, the image pair creation unit 103 returns the page number j of the image data set 9B to the state before page turning (step S320).

  Next, the image pair creation unit 103 adds 1 to the number q of the elements Np stored in the set N (step S321). As a result, the number of pages included in the image data group 9B1 is increased by 1, and the number of images extracted from the image data set 9B as the similarity determination target to the image data group 9B1 is maintained from the initial setting.

  Next, the image pair creation unit 103 adds 1 to the number p of the element Np (step S322). For example, when 1 is added when p = 1 and p = 2, the element Np changes from the element N1 to the element N2, and the element N1 and the element N2 become separate independent elements. That is, when a plurality of images are exchanged, the image pair creation unit 103 can save all the number of pages of the image data set 9B that has previously become an image pair in the set N.

  Next, the image pair creation unit 103 initializes the value of the page feed count m (step S323), and returns to the process of step S304.

  As described above, according to the second embodiment, when a page is replaced in the image data set 9B, the processing is performed without excluding the replaced page. , Can perform the processing as intended.

  In addition, since the determination of the similarity is not performed again for the page in which the image pair has already been created, the image processing apparatus 100 does not need to determine the overlapping similarity and performs the processing efficiently. be able to.

(Other embodiments)
Also in other embodiments, the image processing apparatus 100 and peripheral devices (FIG. 1) having the same configuration as in the first embodiment are used. Therefore, a detailed description of the configuration and function of the image processing apparatus 100 is omitted.

  FIG. 11 is a diagram for explaining an example of processing of the misalignment display image output unit 107 (FIG. 3) as another embodiment. Here, processing when a non-comparison target document is inserted on the same page (first page) of the document sets 11A and 11B will be described.

  In FIG. 11, 11A is a document set including the non-comparison target document a on the first page, 11B is a document set including the non-comparison target document b on the first page, 11C is an output result image by the misalignment display image output device 107, Respectively.

  As shown in FIG. 11, when the non-comparison target documents a and b are inserted in the first page of the document sets 11A and 11B, the misalignment display image output unit 107 moves the non-comparison target images a and b left and right. Line up and output as a single image.

  As described above, according to the embodiment of FIG. 11, when there are non-comparison target documents on the same page of each document set, they are displayed side by side on one image. It is possible to easily recognize what kind of image has been processed.

  The image processing program executed by the image processing apparatus 100 according to each embodiment described above includes the above-described units (image data set acquisition unit 101, page division unit 102, image pair creation unit 103, image comparison unit 104, image determination unit 105). , A page correction unit 106 and a misalignment display image output unit 107). As the actual hardware, the CPU (processor) reads the image processing program from the recording medium and executes it, so that the units (101 to 107) are loaded onto the main storage device, and the units are generated on the main storage device. It has come to be.

  The above-described image processing program is an installable or executable file that is read by a computer such as a CD-ROM, floppy (registered trademark) disk (FD), CD-R, or DVD (Digital Versatile Disk). It is provided by being recorded on a possible recording medium.

  Further, the above-described image processing program may be provided by being incorporated in advance in a ROM or the like.

  Further, the above-described image processing program may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Further, the above-described image processing program may be provided or distributed via a network such as the Internet.

  In each embodiment described above, the image processing apparatus 100 is configured to include the page dividing unit 102. However, the image processing apparatus according to the present invention is not limited to this, and the page dividing unit 102 may not be provided. In this case, the image processing apparatus according to the present invention can specify each image data by designating a folder (directory). Furthermore, in this case, in order to arrange the image data in the page order, the image processing apparatus according to the present invention may have a page sort process.

  In each of the above-described embodiments, the three colors of black, red, and yellow have been described as being output from the misalignment display image output unit 107. However, the present invention is not limited to this, and the difference in color and brightness is obvious. Any color that can be easily recognized by the user.

  In the embodiment of FIG. 11 described above, when the non-comparison target documents are on the same page of each document set, the non-comparison target documents are output side by side as a single image. However, the present invention is not limited to this. For example, you may make it output side by side up and down.

  The image processing apparatus according to each embodiment described above can be applied to a copier, a printer, a scanner apparatus, a facsimile apparatus, a multifunction machine having at least two functions among the functions of these apparatuses, and the like.

4B1, 8B1 Image data group for similarity determination 11C Output result image 100 Image processing device 101 Image data set acquisition unit 102 Page division unit 103 Image pair creation unit 104 Image comparison unit 105 Image determination unit 106 Page correction unit 107 Misalignment display Image output unit 110 Scanner 210, 220 Document set (image data set)

JP 2007-293809 A JP 2011-003077 A Japanese Patent No. 4750047 JP 2000-57266 A

Claims (10)

An image data set acquisition unit for acquiring at least two digital image data sets;
Image data group for similarity determination having the number of images specified in page order from one of the image data sets acquired by the image data set acquisition unit is generated, and the image data group is not generated Determining the similarity between each image data of the set and each image data of the image data group, and an image pair creating unit that sets a pair of image data determined to have high similarity;
An image determination unit that determines that the image data determined by the image pair creation unit not to have image data with high similarity is a non-comparison target image;
A page correction unit that corrects a page after the non-comparison target image for the image data set including the non-comparison target image based on the determination of the image determination unit;
An image processing apparatus comprising: An image comparison unit that performs comparison between image data paired by the image pair creation unit;
A misalignment display image output unit that outputs an image representing a difference between the image data compared in the image comparison unit as a misalignment display image;
The image processing apparatus according to claim 1, further comprising:   The image comparison unit creates non-comparison target image identification image data when the image determination unit determines that the image data is a non-comparison target image, and the non-comparison target image identification image data and the image data The image processing apparatus according to claim 2, wherein the document comparison is performed.   The image pair creation unit includes the image data group including the image data when the image data set in which the image data group is created includes image data determined that there is no image data with high similarity. The image processing apparatus according to claim 2, wherein the image processing apparatus generates an image.   The misalignment display image output unit includes a non-comparison target image in both the image data set in which the image data group has not been created and the image data group, and the page number of the non-comparison target image is the same. 5. The image processing apparatus according to claim 2, wherein the non-comparison target images are output simultaneously.   6. The image processing according to claim 1, further comprising a page dividing unit that divides each image data set acquired by the image data set acquiring unit into image data in page units. apparatus. An image processing method executed by an image processing apparatus,
An image data set acquisition stage for acquiring at least two digital image data sets;
An image data set for similarity determination having the number of images specified in page order from one of the image data sets acquired in the image data set acquisition step is created, and the image data set is not created Determining the similarity between each of the image data and each image data of the image data group, and creating an image pair in which a pair of image data determined to have a high degree of similarity;
An image determination step for determining that the image data determined to have no image data with high similarity in the image pair creation step is a non-comparison target image; and
Based on the determination in the image determination step, a page correction step for correcting a page after the non-comparison target image for the image data set including the non-comparison target image,
An image processing method comprising: An image comparison stage for performing comparison between the image data paired in the image pair creation stage;
A misalignment display image output step of outputting an image representing a difference between the image data compared in the image comparison step as a misalignment display image;
The image processing method according to claim 7, further comprising: An image data set acquisition step of acquiring at least two digital image data sets;
An image data set for similarity determination having a number of images specified in page order from one of the image data sets acquired in the image data set acquisition step is created, and the image data set is not created Determining a similarity between each of the image data and each image data of the image data group, and an image pair creating step in which the image data determined to have a high similarity is a pair.
An image determination step for determining that the image data determined to have no high similarity image data in the image pair creation step is a non-comparison target image; and
A page correction step for correcting a page after the non-comparison target image for the image data set including the non-comparison target image based on the determination in the image determination step;
An image processing program for causing a computer to execute.   A computer-readable recording medium on which the program according to claim 9 is recorded.

Images