JP2011065311A - Image processor and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor for extracting a feature quantity as pre-processing for determining the type of a document on which data are being input. <P>SOLUTION: The first image acceptance means of an image processor accepts an image of a document on which no data is input, and an input region extraction means extracts an input area from an image accepted by the first image acceptance means, and a first feature quantity extraction means extracts the feature quantity of an image accepted by the first image acceptance means, and a storage means stores information on the input region extracted by the input region extraction means and the feature quantity extracted by the feature quantity extraction means. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

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

The type of the document is determined using the document image.
As a technology related to this, for example, Patent Document 1 discloses form format identification information and an apparatus for identifying a form format that does not require printing of marks and symbols indicating the form type and allows expansion and contraction of image data. A format information registration means for obtaining a ruled line interval serving as a reference for the form data, registering a normalized result by replacing each ruled line interval with a ratio to the reference ruled line interval, and a reference for input data. The input format information generating means that uses the input format information as input format information by replacing each ruled line interval with the ratio of the reference ruled line interval, the registered format information, and the input format information are collated, and the input data is in the registered format information. It is disclosed that it has a format identification means for identifying which format is.

  In addition, for example, in Patent Document 2, high-precision table matching is performed on a similar table, a table including disturbances such as handwritten characters, a table with a broken ruled line, a distorted or inclined table, and an enlarged / reduced table. An object of the present invention is to provide a form processing apparatus including a table that accurately calculates a character reading area position, and the form processing apparatus including the table includes ruled line extraction means, table structure analysis means, table format database, table collation means, and field Consists of position search means and result display means. The ruled line extraction means reads a form including a table, the ruled lines included in the table area in the read image are extracted, and the table structure analysis means extracts a table format from the extracted ruled lines. Is created, the table format is stored in the table format database, the ruled line is collated with the table format in the table matching means, and the field position search means is on the image. Calculated shaped reading area position, a result displaying means has been disclosed that the table collation result and field position search result is output.

  Further, for example, Patent Document 3 has an object to provide a technique capable of generating a stable virtual page mark even for a non-character recognition form and identifying a stable form. For detection, key lines that can be detected stably in the form are defined in advance, virtual page marks (circumscribed rectangles) are generated based on these key lines, and redundancy is provided for the detection of key lines. Even if a key line segment cannot be detected due to holding, dirt, chipping, etc., an alternative line segment is defined, a virtual page mark is generated based on this alternative line segment, and the key line segment to be selected is (1 (2) The line segment should be thick enough to withstand the blurring of the form. (2) The line segment should be at a sufficient distance from the periphery of the form, and it should be stable against skew and chipped edges. 3) If it overlaps with the crease of the base paper of the form It is the line segment, it is those that meet the conditions are disclosed.

JP 08-31068 A JP 07-282193 A JP 2002-366895 A

  The present invention provides an image processing apparatus and an image processing program that are pre-processing for determining the type of a document that has been filled in, and that extract feature amounts for determining the type of the document. The purpose is that.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The invention of claim 1 is a first image receiving means for receiving an image of a document that has not been filled in; an entry area extracting means for extracting an entry area from an image received by the first image receiving means; A first feature amount extracting unit that extracts a feature amount of an image received by the first image receiving unit; information about an entry region extracted by the entry region extracting unit; and an extracted feature amount by the feature amount extracting unit An image processing apparatus comprising storage means for storing feature amounts.

  According to the second aspect of the present invention, the second image accepting unit accepts the image of the document in which the entry has been made, and the second image accepting unit accepts the image based on the information related to the entry area stored in the storage unit. An entry area deleting means for deleting the entry area from the image obtained, a second feature quantity extracting means for extracting a feature quantity from the image deleted by the entry area deleting means, and a second feature quantity extracting means. The apparatus further comprises a determination unit that compares the extracted feature amount with the feature amount stored in the storage unit and determines the type of the document received by the second image receiving unit. The image processing apparatus according to 1.

  According to a third aspect of the present invention, the third image receiving means receives the image of the document in which the entry has been made, and the third image receiving means accepts the information on the entry area stored in the storage means. An entry area extracting means for extracting the entry area from the received image, an ordering means for ordering the entry areas extracted by the entry area extracting means, and an output means for outputting the entry areas ordered by the ordering means The image processing apparatus according to claim 1, further comprising:

  According to a fourth aspect of the present invention, the entry area extraction unit extracts information on the entry area stored in the storage unit based on the document type determined by the determination unit, and extracts the entry area. The image processing apparatus according to claim 3.

  According to a fifth aspect of the present invention, there is provided a first image receiving means for receiving an image of a document that has not been filled in, and an entry area extraction for extracting an entry area from the image received by the first image receiving means. Means, first feature amount extraction means for extracting the feature amount of the image received by the first image reception means, information on the entry area extracted by the entry area extraction means, and the feature amount extraction means. An image processing program that functions as a storage unit that stores extracted feature amounts.

  According to the image processing apparatus of the first aspect, it is a pre-process for determining the type of the document in which the entry is performed, and the feature amount for determining the type of the document can be extracted.

  According to the image processing apparatus of the second aspect, the type of the document can be determined even for the image of the document in which the entry has been made.

  According to the image processing apparatus of the third aspect, it is possible to output the ordered entry areas.

  According to the image processing apparatus of the fourth aspect, it is possible to suppress extraction of unnecessary entry areas.

  According to the image processing program of the fifth aspect, it is a pre-process for determining the type of the document in which the entry has been made, and the feature quantity for determining the type of the document can be extracted.

It is a conceptual module block diagram about the structural example of this Embodiment. It is explanatory drawing which shows the example of a data structure of a form characteristic table. It is explanatory drawing which shows the example of a data structure of an entry area table. It is a flowchart which shows the process example which a registration module performs. It is a flowchart which shows the process example which a form form determination module performs. It is a flowchart which shows the process example which an entry area output module performs. It is explanatory drawing which shows the process example (1) which a registration module performs. It is explanatory drawing which shows the process example (1) which a registration module performs. It is explanatory drawing which shows the process example (2) which a registration module performs. It is explanatory drawing which shows the example of the target image and entry area of a registration module. It is explanatory drawing which shows the process example which a form form determination module performs. It is explanatory drawing which shows the process example which an entry area output module performs. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
FIG. 1 shows a conceptual module configuration diagram of a configuration example of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a computer program, a system, and a method. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. It is the control to be stored in the device. Modules may correspond to functions one-to-one, but in mounting, one module may be configured by one program, or a plurality of modules may be configured by one program, and conversely, one module May be composed of a plurality of programs. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is included. “Apparatus” and “system” are used as synonymous terms. “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. In addition, if it is before the target processing, it is used in accordance with the situation / state at that time or with the intention to be decided according to the situation / state up to that point.

As illustrated in FIG. 1, the image processing apparatus according to the present embodiment includes a registration module 110, a form form determination module 130, and an entry area output module 150.
The registration module 110 includes an image reception module 112, a storage module 114, an entry area extraction module 116, and a feature amount extraction module 118.

  The image reception module 112 receives an image of a document. Accepting an image means, for example, reading an image with a scanner, a camera, etc., receiving an image from an external device via a communication line by fax, etc., a hard disk (in addition to what is built in a computer, via a network) And the like, and the like read out the images stored in the device etc.). The image may be a binary image or a multi-value image (including a color image). In the following description, a binary image is described as an example. One image may be received or a plurality of images may be received.

  The contents of the image may be a document used for business. However, this includes documents that have not been filled in and documents that have been filled in. An unfilled document is a document with a predetermined format, which should be filled in by the user, but has not been filled in yet. Documents called so-called forms, templates, and templates, for example, forms such as invoices and application forms. Hereinafter, description will be made using a form as a document. The document that has been filled in is a document that has been filled in by a user with respect to a document that has not been filled in. This entry may be handwritten, or may be other than handwritten, for example, text data or the like entered using document data of a document that has not been filled in. The image receiving module 112 in the registration module 110 receives an unfilled document, and the image receiving module 112 in the form form determination module 130 and the filling area output module 150 receives the filled-in document.

The entry area extraction module 116 extracts an entry area from the image received by the image reception module 112. Then, information regarding the extracted entry area is stored in the storage module 114. The entry area is an area scheduled for entry by the user, and is physically a blank area that is larger than a predetermined area in the form image. The entry area extraction module 116 extracts an area having this feature. It may also be selected from a blank area by the user. The blank area may include an area having a density equal to or lower than a predetermined value.
The entry area extraction module 116 may determine the order of the entry areas. For example, in the case of a horizontally written document, the order of the entry areas is set from left to right and from top to bottom. For this purpose, for example, a coordinate system having the upper left corner of the image as the origin, the right direction of the X coordinate in the right direction, and the lower direction of the Y coordinate in the positive direction is used. Will be described. The entry area whose representative coordinates are at the upper left of the image is numbered 1, and the Y coordinate of the representative coordinates of the entry area and the entry areas within a predetermined range are sequentially arranged from left to right (in the order of the X coordinates), and The entry area which is outside the above-mentioned range and whose representative coordinates are at the upper left in the remaining image may be set in the next order and similarly ordered. In the case of a vertically written document, the same processing is performed so that the order of the entry areas is from top to bottom and from right to left.

The feature amount extraction module 118 extracts the feature amount of the image received by the image reception module 112. Then, the extracted feature amount is stored in the storage module 114. The extracted feature amount is used later by the form form determination module 130 to determine the document type. The document type is, for example, a form type of a form. For example, the number, size, distribution (coordinates), etc. of the pixel block. Here, the pixel block includes at least a pixel region that is continuous in four or eight connections, and also includes a set of these pixel regions. The set of these pixel areas means that there are a plurality of continuous pixel areas such as 4-connected, and the plurality of pixel areas are in the vicinity. Here, what is in the vicinity is, for example, an image area in which the pixel areas are close to each other in distance, an image area that is projected vertically or horizontally so as to cut out one character at a time from a line as a sentence, and cut out at a blank spot Or an image region cut out at regular intervals.
In many cases, an image of one character is formed as one pixel block. Therefore, the number of pixel blocks corresponds to the number of characters, and the distribution of pixel blocks corresponds to the distribution of characters. However, it is not necessary that the pixel area is actually recognizable as a character by humans. There are a part of a character, a pixel region that does not form a character, and the like, and any pixel block may be used.

The storage module 114 stores information related to the entry area extracted by the entry area extraction module 116 and the feature quantity extracted by the feature quantity extraction module 118.
An example of the information regarding the entry area extracted by the entry area extraction module 116 is an entry area table 300. FIG. 3 is an explanatory diagram showing an example of the data structure of the entry area table 300. The entry area table 300 exemplifies a form as a document, and has a form ID field 310, an entry area ID field 320, an entry area position field 330, an entry area size field 340, and an order field 350.
The form ID column 310 stores a form ID (IDentification) that uniquely identifies the form.
The entry area ID column 320 stores an entry area ID that uniquely identifies the entry area in the form.
The entry area position column 330 stores a predetermined position (for example, coordinates of the upper left corner) of the entry area. The entry area position column 330 has an X column 331 and a Y column 332. The X column 331 stores the X coordinate. The Y column 332 stores the Y coordinate.
The entry area size column 340 stores the size of the entry area. The entry area size column 340 includes a W column 341 and an H column 342. The W column 341 stores the width of the entry area. The H column 342 stores the height of the entry area.
The order column 350 stores the order of the entry areas.

Examples of the feature amount extracted by the feature amount extraction module 118 include a form feature table 200. FIG. 2 is an explanatory diagram showing an example of the data structure of the form feature table 200. The form feature table 200 is an example of a form as a document. The form ID field 210, form name field 220, thumbnail image field 230, image field 240, feature amount A field 250, feature amount B field 252, feature amount C Column 254 and the like.
The form ID column 210 stores a form ID.
The form name column 220 stores the name of the form.
The thumbnail image column 230 stores a thumbnail image (reduced image) of the form image or a position (file name, URL (Uniform Resource Locator), etc.) where the thumbnail is stored.
The image column 240 stores the form image or a position where the form image is stored.
The feature amount A columns 250, 252, 254, etc. store the feature amount of the form image.

The form form determination module 130 includes an image reception module 112, a storage module 114, an entry area deletion module 132, a feature amount extraction module 134, and a form determination module 136.
The entry area deletion module 132 deletes the entry area from the image received by the image reception module 112 based on the information regarding the entry area stored in the storage module 114. That is, the entry area is deleted (blank) from the entered form, and the form of the form is created. However, since the form image received by the image receiving module 112 of the form determination module 130 is unknown at this point, this deletion process is performed for each form in the entry area table 300. .

  The feature amount extraction module 134 extracts a feature amount from the image deleted by the entry area deletion module 132. Feature amount extraction equivalent to the feature amount extraction module 118 of the registration module 110 is performed. Therefore, the feature amount extraction module 118 (134) may be shared between the registration module 110 and the form form determination module 130.

The form determination module 136 compares the feature amount extracted by the feature amount extraction module 134 with the feature amount stored in the storage module 114, and determines the type of the document received by the image reception module 112. The determination of the document type means matching with a document corresponding to the feature amount stored in the storage module 114. In other words, if the feature amount of the form form and the image of the form accepted by the image receiving module 112 of the form form determination module 130 are those entered in the form form, the feature amount of the image from which the entry area is deleted And compare.
In addition to selecting one, the determination includes extracting a plurality of candidates, arranging them in order from the candidate with the highest reliability of recognition, and the like. In addition, including supplementary judgments as described above, the user may finally select, confirm, etc. For example, when the difference is equal to or less than a predetermined value as a result of comparison, the form may be recognized as a form image form in which the form ID is entered. In addition, the thumbnails of the form form (thumbnail image column 230 of the form feature table 200) are displayed on a display device such as a display in ascending order of the difference (in descending order of coincidence), and selected according to the user's operation. May be.

The entry area output module 150 includes an image reception module 112, a storage module 114, an entry area extraction module 152, an ordering module 154, and an output module 156.
The entry area extraction module 152 extracts the entry area from the image received by the image reception module 112 based on the information regarding the entry area stored in the storage module 114. The reverse process of the entry area deletion module 132 is performed. Further, the entry area extraction module 152 may extract information related to the entry area stored in the storage module 114 based on the document type determined by the form determination module 136 and extract the entry area. . That is, after the processing by the form form determination module 130 is completed, the processing by the entry area output module 150 is performed.

The ordering module 154 orders the entry areas extracted by the entry area extraction module 152. That is, the entry areas are ordered using the order column 350 of the entry area table 300.
The output module 156 outputs the entry areas ordered by the ordering module 154. To output the entry area is, for example, passing the entry area to a character recognition device, printing with a printing device such as a printer, displaying on a display device such as a display, or transmitting an image with an image transmission device such as a fax machine. Including writing an image to an image storage device such as an image database, storing the image in a storage medium such as a memory card, and passing the image to another information processing device.

FIG. 4 is a flowchart illustrating an example of processing performed by the registration module 110.
In step S400, the registration module 110 starts a registration process.
In step S402, the image reception module 112 reads a blank form (form).
In step S404, the entry area extraction module 116 extracts a blank area (entry area). A first example of blank area extraction processing will be described with reference to FIGS.

7 and 8 are explanatory diagrams showing a processing example (1) performed by the entry area extraction module 116. FIG.
A form image (form) 700 illustrated in FIG. 7A is an image read in step S402. It is a form of a form called an application form. Each item name is described but not filled in.
The entry area extraction module 116 generates a projection result 710 that is a histogram of black pixels counted in the horizontal direction of the form image (form) 700. Then, the form image (form) 700 is divided in the middle of the valley portion of the projection result 710 (the portion in which the black pixel is not more than a predetermined value in the horizontal direction). That is, as illustrated in FIG. 7B, the form image (form) 700 is divided into a line connecting the dividing point 721 and the dividing point 722, a line connecting the dividing point 723 and the dividing point 724, and a dividing point 725 and the dividing point 725. It is divided into six regions by dividing the line by connecting a line connecting the point 726, a line connecting the dividing point 727 and the dividing point 728, and a line connecting the dividing point 729 and the dividing point 730. Then, a projection result 716 is generated from the projection result 711 which is a histogram of black pixels counted in the vertical direction in each region (see FIG. 7C).

  Next, each region is divided so as to surround a mountain portion (a portion where the black pixel is a predetermined value or more in the vertical direction) such as the projection result 711 which is a histogram of black pixels counted in the vertical direction. The area surrounding the mountain portion is to take a margin of a predetermined value and surround the pixel block. That is, as illustrated in FIG. 8D, for example, an area surrounded by division points 731, 732, 734, and 735 (area surrounding a character “invoice” that is a pixel block), division points 721, 733, An area surrounded by 723 and 736 (area surrounding a character “date” which is a pixel block) is generated. Then, other areas are extracted as blank areas. That is, for example, the upper left corner of the form image (form) 700, the area surrounded by the dividing points 731, 721, and 733 (the entry area candidate 751 illustrated in FIG. 8E), the dividing point 732, and the form image (form) 700. , An area surrounded by division points 735 and 722 (entry area candidate 752 illustrated in FIG. 8E), and an area surrounded by division points 733, 722, 736 and 724 (illustrated in FIG. 8E). Entry area candidate 753).

Next, a second example of blank area extraction processing will be described with reference to FIG.
A form image (form) 800 illustrated in FIG. 9A is an image read in step S402. This is the same as the form image (form) 700 illustrated in FIG.
The entry area extraction module 116 divides the form image (form) 800 into blocks having a predetermined size. Here, as the predetermined size, for example, the size of a pixel block in the form image (form) 800 may be calculated, and a value based on the average size may be adopted.
Then, it is determined whether or not there is a black pixel in each block. In the example illustrated in FIG. 9B, a block without black pixels is shaded, and a block with black pixels is left as it is.
Next, a blank area is extracted by integrating blocks without black pixels. For example, as illustrated in FIG. 9C, blocks adjacent to each other in a block having no black pixels are integrated, and the integration result is rectangular, and a blank area is extracted. However, according to the integrated size of blocks necessary to enclose the pixel block (the height of the integrated block group for horizontal writing documents, the width of the integrated block group for vertical writing documents) To extract a blank area. For example, as illustrated in FIG. 9C, the entry area candidates 856, 857, and 858 are a block group (2 ×) surrounding the characters “address”, “amount”, and “remarks” that are pixel blocks on the left side. It is extracted according to the height of 2).

In step S406, the entry area extraction module 116 deletes unnecessary areas from the extracted areas in accordance with user operations. The blank area extracted in step S404 is displayed on a display device such as a display of the registration module 110, and the user selects an unnecessary area (blank area that is not an entry area) and deletes the selected area. For example, entry area candidates 751 and 752 illustrated in FIG. 8E can be selected as areas to be deleted.
In step S408, the entry area extraction module 116 stores the extracted area (an area other than the area deleted in step S406) in the storage module 114 (entry area table 300) as a confirmed entry area. Further, the blank area extracted in step S404 may be stored in the entry area table 300. In that case, a column for storing valid region information (flag) may be added to the entry region table 300, and a flag may be set in that column corresponding to the confirmed entry region. That is, the blank area where the flag of the column is set is handled as the fixed entry area.

In step S410, the entry area extraction module 116 saves the read image in the storage module 114 (form feature table 200) for preview. A thumbnail image may be stored.
In step S412, the feature quantity extraction module 118 extracts the feature quantity of the blank form and stores it in the storage module 114 (form feature table 200).
In step S499, the registration module 110 ends the registration process.

  In the above-described entry area extraction example, the form without a ruled line (form image (form with no ruled line 900) illustrated in FIG. 10A) has been described. However, a form with a ruled line (form image illustrated in FIG. 10B). (Form with ruled lines) 910) may be targeted. In that case, an area surrounded by the ruled line is taken out, and a process as shown in the processes after FIG. 7C is performed in the area, thereby obtaining a blank area (an entry area 951 illustrated in FIG. 10C). The entry area 958) may be extracted from

FIG. 5 is a flowchart showing an example of processing performed by the form form determination module 130.
In step S500, the form form determination module 130 starts form determination processing.
In step S502, the image reception module 112 reads the completed form.
In step S <b> 504, the entry area deletion module 132 determines whether there is a registered form whose degree of coincidence is not calculated in the storage module 114. If there is, the process proceeds to step S506, and otherwise, the process proceeds to step S514.

  In step S506, the entry area deletion module 132 creates a mask image of the confirmed entry area of the registered form. That is, a blank image having the same size as the image read in step S502 is prepared, and information on the finalized entry area (entry area position field 330, entry area size field 340) stored in the entry area table 300 in the storage module 114 is prepared. ) Is used to create an image in which the area of the blank image corresponding to the confirmed entry area is filled with black pixels as a mask image.

  In step S508, the entry area deletion module 132 combines the completed image and the reverse mask image. First, the mask image created in step S506 is inverted. That is, the black pixel is a white pixel and the white pixel is a black pixel. Then, the logical product (AND) of the image read in step S502 and the inverted mask image is calculated. As a result, an image in which the entry area in the registered form is deleted is generated. This combining process will be described with reference to the example of FIG.

FIG. 11 is an explanatory diagram showing a processing example performed by the form form determination module 130.
A form image (with entry) 1000 illustrated in FIG. 11A is an image read in step S502. It is an image that has been filled out in the form of the application form.
An entry area 951 to an entry area 958 illustrated in FIG. 11B are mask images created based on the entry area of the form whose form has been determined. Then, an inverted mask image obtained by inverting this mask image is generated.
A form image (deletion area deletion) 1030 illustrated in FIG. 11C is a combination of the form image (with entry) 1000 in FIG. 11A and an inverted mask image obtained by inverting the mask image in FIG. It is an image of the result. That is, an image from which the entry area is deleted is generated.

In step S510, the feature amount extraction module 134 extracts feature amounts from the image synthesized in step S508.
In step S512, the feature quantity extraction module 134 calculates and stores the degree of coincidence between the two feature quantities (the feature quantity in the form feature table 200 of the storage module 114 and the feature quantity extracted in step S510). For example, the reciprocal of the difference obtained by comparing the feature amounts is set as the degree of coincidence.
In step S514, the form determination module 136 presents the documents in descending order of matching. In other words, the registration form (form) in the storage module 114 (the thumbnail image field 230 or the image field 240 of the form feature table 200) similar to the image read in step S502 is displayed in the order of similarity in the form form determination module 130 display and the like. Displayed on the display device. And according to a user's operation, you may determine a registration form (form).
In step S599, the form determination module 130 ends the form determination process.

FIG. 6 is a flowchart showing an example of processing performed by the entry area output module 150. This flowchart is performed after the processing illustrated in FIG. 5 is completed.
In step S600, the entry area output module 150 starts an entry area extraction process.
In step S <b> 602, the entry area extraction module 152 uses the form determination result by the form determination module 136 to create a mask image of the confirmed entry area of the corresponding form. That is, an empty image having the same size as the image read in step S502 is prepared, and information on the finalized entry area of the corresponding form stored in the entry area table 300 in the storage module 114 (entry area position field 330, entry area). Using the size column 340), an image in which the area of the blank image corresponding to the fixed entry area is filled with black pixels is created as a mask image.

  In step S604, the entry area extraction module 152 combines the entered image and the mask image. The logical product (AND) of the image read in step S502 and the mask image is obtained. As a result, an image of only the entry area in the registered form is generated. This synthesis process will be described with reference to the example of FIG.

FIG. 12 is an explanatory diagram illustrating an example of processing performed by the entry area output module 150.
A form image (with entry) 1000 illustrated in FIG. 12A is an image read in step S502.
An entry area 951 to an entry area 958 illustrated in FIG. 12B are mask images created based on the entry area of the form whose form has been determined.
A form image (entry region) 1130 illustrated in FIG. 12C is an image obtained as a result of combining the form image (with entry) 1000 in FIG. 12A and the mask image in FIG. That is, an image in which only the entry area remains is generated.

In step S606, the ordering module 154 orders the entry areas based on the ordering information in the storage module 114 (order field 350 of the entry area table 300).
In step S608, the output module 156 outputs the ordered entry areas.
In step S699, the entry area output module 150 ends the entry area extraction process.

  A hardware configuration example of the image processing apparatus according to the present embodiment will be described with reference to FIG. The configuration shown in FIG. 13 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 1317 such as a scanner and a data output unit 1318 such as a printer.

  The CPU (Central Processing Unit) 1301 includes various modules described in the above-described embodiments, that is, the entry area extraction module 116, the feature quantity extraction module 118, the entry area deletion module 132, the feature quantity extraction module 134, and the form determination module. Reference numeral 136 denotes a control unit that executes processing according to a computer program that describes the execution sequence of each module such as the entry area extraction module 152 and the ordered module 154.

  A ROM (Read Only Memory) 1302 stores programs used by the CPU 1301, calculation parameters, and the like. A RAM (Random Access Memory) 1303 stores programs used in the execution of the CPU 1301, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 1304 including a CPU bus.

  The host bus 1304 is connected to an external bus 1306 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 1305.

  A keyboard 1308 and a pointing device 1309 such as a mouse are input devices operated by an operator. The display 1310 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 1311 has a built-in hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 1301 and information. The hard disk stores received images, thumbnail images, a form feature table 200, an entry area table 300, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 1312 reads data or a program recorded on a removable recording medium 1313 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and reads the data or program into an interface 1307 and an external bus 1306. , The bridge 1305, and the RAM 1303 connected via the host bus 1304. The removable recording medium 1313 can also be used as a data recording area equivalent to a hard disk.

  The connection port 1314 is a port for connecting the external connection device 1315 and has a connection unit such as USB and IEEE1394. The connection port 1314 is connected to the CPU 1301 and the like via the interface 1307, the external bus 1306, the bridge 1305, the host bus 1304, and the like. A communication unit 1316 is connected to a network and executes data communication processing with the outside. The data reading unit 1317 is, for example, a scanner, and executes document reading processing. The data output unit 1318 is, for example, a printer, and executes document data output processing.

  Note that the hardware configuration of the image processing apparatus illustrated in FIG. 13 shows one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 13, and the modules described in the present embodiment are executed. Any configuration is possible. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line Alternatively, a plurality of systems shown in FIG. 13 may be connected to each other via communication lines so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

In the above-described embodiment, the case where the registration module 110, the form form determination module 130, and the entry area output module 150 are provided in one case (image processing apparatus) has been described. Also good. In that case, the image receiving module 112 is provided in each housing. When the storage module 114 is provided in each housing, the storage module 114 has a copy module for making the stored contents equivalent through communication means or the like. In addition, the storage module 114 may be provided in any one or more housings or another storage device, but may be used from other housings via a communication unit or the like. Two or more combinations of the registration module 110, the form form determination module 130, and the entry area output module 150 (for example, the form form determination module 130 and the entry area output module 150) may be installed in one housing.
Note that the technology described in the background art may be adopted as the processing content of each module.
Further, in the description of the above-described embodiment, “more than”, “less than”, “greater than”, and “less than (less than)” in a comparison with a predetermined value contradicts the combination. As long as the above does not occur, “larger”, “smaller (less than)”, “more than”, and “less than” may be used.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray Disc (registered trademark), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM), flash Includes memory, random access memory (RAM), etc. .
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

DESCRIPTION OF SYMBOLS 110 ... Registration module 112 ... Image reception module 114 ... Storage module 116 ... Fill area extraction module 118 ... Feature amount extraction module 130 ... Form form determination module 132 ... Fill area deletion module 134 ... Feature amount extraction module 136 ... Form determination module 150 ... Entry area output module 152 ... Entry area extraction module 154 ... Ordered module 156 ... Output module

Claims (5)

First image receiving means for receiving an image of an unfilled document;
Entry area extracting means for extracting an entry area from the image received by the first image receiving means;
First feature quantity extraction means for extracting the feature quantity of the image received by the first image reception means;
An image processing apparatus comprising: storage means for storing information on the entry area extracted by the entry area extraction means and the feature quantity extracted by the feature quantity extraction means. A second image receiving means for receiving an image of a document in which entry has been made;
An entry area deleting means for deleting the entry area from the image received by the second image receiving means based on the information about the entry area stored in the storage means;
Second feature quantity extraction means for extracting feature quantities from the image deleted by the entry area deletion means;
A determination unit that compares the feature amount extracted by the second feature amount extraction unit with the feature amount stored in the storage unit and determines the type of the document received by the second image reception unit; The image processing apparatus according to claim 1, further comprising: Third image receiving means for receiving an image of a document in which entry has been made;
An entry area extracting means for extracting the entry area from the image received by the third image receiving means based on the information about the entry area stored in the storage means;
Sequencing means for sequencing the entry areas extracted by the entry area extraction means;
The image processing apparatus according to claim 1, further comprising: an output unit that outputs the entry areas ordered by the ordering unit. 4. The entry area extraction unit extracts information on the entry area stored in the storage unit based on the document type determined by the determination unit, and extracts the entry area. An image processing apparatus according to 1. Computer
First image receiving means for receiving an image of an unfilled document;
Entry area extracting means for extracting an entry area from the image received by the first image receiving means;
First feature quantity extraction means for extracting the feature quantity of the image received by the first image reception means;
An image processing program that functions as a storage unit that stores information on an entry region extracted by the entry region extraction unit and a feature amount extracted by the feature amount extraction unit.

Images