JP6281739B2 - Processing apparatus and program - Google Patents

Description

  The present invention relates to a processing apparatus and a program.

  Japanese Patent Laid-Open No. 2004-133867 discloses a device that easily and reliably generates a character code with attribute information such as a search key from image data read using a scanner, and reduces the time required for registration work. An apparatus for providing attribute information to a character area of the image data before performing character recognition processing is disclosed. Specifically, a character area is designated by the area frame formed by the area frame forming unit, the position information of the designated area is associated with attribute information arbitrarily selected from the attribute information file, and the correspondence information is associated with the correspondence information. A character code that is stored in a file, subjected to character recognition processing by the character recognition unit for the character region specified in the region frame, and outputs the recognition result and the corresponding attribute information at the same time. Get.

  Japanese Patent Application Laid-Open No. 2005-228867 evaluates the validity of a manuscript with the configuration of an image input device that scans an image document and stores the image and index in a document management system, a form recognition, an OCR, and a user interface. An image input apparatus for inputting an image document and an index to a management system is disclosed.

  Patent Document 3 discloses an electronic document registration system capable of generating metadata of a document to be registered as follows. In the system disclosed in Patent Document 3, an electronic form is used when a document is created, and data is input to the electronic form, thereby creating electronic data of the document and printing the electronic form in which the data is input. A document is created. The printed document is given a two-dimensional barcode encoded with a part of the data of the electronic form. When registering the image data of the document as an electronic document, the two-dimensional barcode included in the image data of the document is used. Data obtained by decoding a barcode image is used as metadata.

  Patent Document 4 discloses the following as an electronic resume system that enables unified management of resume data using an electronic form and a two-dimensional barcode. The terminal device creates an electronic resume in accordance with the resume form, and when printing the resume, the server converts the resume data from the terminal device into a two-dimensional barcode and prints the electronic resume data with the two-dimensional barcode for printing. The terminal device prints a resume with a two-dimensional barcode. The personnel information system reads a resume with a two-dimensional barcode sent from the applicant with a scanner, restores the two-dimensional barcode into resume data, and each of the resume data, photo image data, seal image data, A common receipt number is assigned and registered in the registration database.

Japanese Patent Laid-Open No. 8-083285 JP 2008-293353 A JP 2008-097066 A JP 2006-163677 A

  An object of the present invention is to provide a processing apparatus and a program capable of extracting content information entered in a specific area of a recording medium on which a printing process is performed without receiving an area designation after the printing process.

  According to a first aspect of the present invention, there is provided a first acquisition means for acquiring first image data to which information representing a position and a range is added, and a recording medium on which an image corresponding to the first image data is printed A second acquisition means for acquiring the second image data obtained by reading the image, and recognizing the content information entered in the recording medium from the area of the second image data corresponding to the area specified from the position and range And a recognition device.

  According to a second aspect of the present invention, the first acquisition means acquires first image data to which information on the type of data to be entered is added in addition to the information indicating the position and range, and the recognition The processing device according to claim 1, wherein the means recognizes the content information with reference to information on the data type.

  The present invention according to claim 3 further includes reading means for reading a recording medium on which information representing the position and range is printed, and the second acquisition means includes the position and range printed on the recording medium. The processing apparatus according to claim 1, wherein information representing the above is acquired.

  The present invention according to claim 4 further includes a reading unit that reads a recording medium on which storage destination information in which the information indicating the position and the range is stored is printed, and the second acquisition unit includes the recording medium. The processing apparatus according to claim 1, wherein the storage destination information printed is acquired.

  According to a fifth aspect of the present invention, in the processing apparatus according to any one of the first to fourth aspects, the recognizing unit recognizes a region of the first image data in which content information is not entered. It is.

  The present invention according to claim 6 further comprises update means for updating content information recognized by the recognition means to third image data added to the first image data. It is a processing device.

  According to a seventh aspect of the present invention, when there is a region where the content information cannot be recognized by the recognizing unit, the updating unit converts the second image data corresponding to the region into the first image data. The processing apparatus according to claim 6 to be added.

  The present invention according to claim 8 further includes extraction means for extracting a difference between a plurality of image data and extracting a position and a range from information regarding the difference, wherein the recognition means is extracted by the extraction means. The processing apparatus according to claim 1, wherein content information entered in an area corresponding to a position and a range is recognized.

  According to a ninth aspect of the present invention, there is provided an acquisition step of first image data to which information indicating a position and a range is added, and second image data obtained by reading a recording medium on which the first image data is printed. A program for causing a computer to execute an acquiring step and a step of recognizing content information entered on the recording medium from the second image data in an area specified by the position and range.

  According to the first aspect of the present invention, the content information entered in a specific area of the recording medium on which the printing process is performed can be extracted without receiving an area designation after the printing process.

  According to the second aspect of the present invention, it is possible to increase the accuracy of extracting the content information as compared with the case where the content information is extracted without referring to the information regarding the data type.

  According to the third aspect of the present invention, it is possible to acquire information representing the position and range from which the content information is extracted from the recording medium.

  According to the fourth aspect of the present invention, it is possible to specify the storage destination of information representing the position and range from which the content information is extracted.

According to the fifth aspect of the present invention, it is possible to reduce the number of areas to be extracted as compared with the case where extraction is performed for all areas.

  According to the sixth aspect of the present invention, it is possible to generate image data reflecting the added content.

  According to the seventh aspect of the present invention, image data reflecting content information can be generated even when extraction is impossible.

  According to the eighth aspect of the present invention, content information entered in a specific area can be extracted without receiving any area designation even on a recording medium that does not have information indicating the position and range.

  According to the ninth aspect of the present invention, the content information entered in a specific area of the recording medium on which the printing process is performed can be extracted without receiving the area designation after the printing process.

It is a mimetic diagram showing document processing system 2 concerning an embodiment of the present invention. 2 is a cross-sectional view showing an image forming apparatus 4. 2 is a block diagram illustrating a hardware configuration of an image forming apparatus 4. FIG. It is a block diagram which shows the function structure of the image forming apparatus 4 implement | achieved by running a program. 6 is a flowchart illustrating an example of an operation until an electronic document with a form field is printed in the image forming apparatus 4 as a document processing apparatus. It is a schematic diagram which shows an example of the electronic document with a form field which the 1st acquisition part 70 acquires. It is a schematic diagram which shows an example of the recording medium with which the electronic document was printed with the information which shows the place of a memory | storage destination. 6 is a flowchart illustrating an example of an operation when extracting meta information from a printed recording medium after printing an electronic document with a form field in the image forming apparatus 4 as a document processing apparatus. FIG. 7 is a schematic diagram illustrating an example of a read image on a recording medium when the electronic document illustrated in FIG. 6 is printed on the recording medium and additional recording is performed on the recording medium. FIGS. 10A and 10B are schematic diagrams showing meta information extracted from the electronic document and the read image shown in FIGS. 6 and 9, wherein FIG. 10A shows meta information extracted from the electronic document, and FIG. Meta information extracted from It is a block diagram which shows the function structure of the image forming apparatus 4 which concerns on 2nd embodiment implement | achieved by running a program. It is a schematic diagram shown about the some read image which the 3rd acquisition part 110 acquires. It is the schematic diagram which showed the description common in the some read image shown in FIG. It is a schematic diagram explaining an example of the form field information produced | generated by the entry column information production | generation part. It is a flowchart shown about an example of the operation | movement at the time of producing | generating form field information in 2nd embodiment.

Hereinafter, a first embodiment of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a schematic diagram showing a document processing system 2 according to an embodiment of the present invention. As shown in FIG. 1, the document processing system 2 includes an image forming apparatus 4 that functions as a document processing apparatus and a terminal device 6, and the image forming apparatus 4 and the terminal device 6 are LAN and WAN. Are connected by a network 8 constituted by the Internet or the like.

  The terminal device 6 is configured as a personal computer, for example, and creates image data by executing application software. The image data created by the terminal device 6 includes an electronic document (document data). Further, the terminal device 6 transmits the image data to the image forming device 4 as a document processing device.

  In the present embodiment, the image data generated by the terminal device 6 represents at least the position of the entry field (for example, the coordinates of the entry field) and the range (for example, the vertical length and the horizontal length of the entry field). Information is added. As an example of such image data, the terminal device 6 creates an electronic document with a form field, for example. The form field is information indicating the position and range of the entry field provided in the document and the type of data entered in the entry field. Note that the entry field only needs to have an area where entry is made, and does not necessarily have a frame made of ruled lines or the like. Data type refers to the type of data that has been grouped (classified) in advance to be used to improve the recognition accuracy of the content information by referring to it when recognizing the content information entered in the entry field. For example, there are “character”, “English character”, “number”, and the like. The type of data entered in the entry field indicates which type of data is entered among predetermined data types. The predetermined data types are not limited to “letters”, “English letters”, “numbers”, etc., but also “check boxes”, “radio buttons”, “formulas”, “money amounts”, “dates”, etc. It may be “image”.

  For example, a document data format such as a PDF (Portable Document Format) format or a DocumentWorks (registered trademark) format is a document data format to which a form field can be added. In such a document data format, a text is used as a form field. Fields, check boxes, radio buttons, list boxes, combo boxes, etc. are available.

  Note that the text field is an entry field for entering characters, the check box is an entry field for designating a corresponding option among a plurality of options, and the radio button is one of a plurality of options. It is an entry field for specifying one, the list box is an entry field for designating a list of predetermined options and selecting one of them, and the combo box is for displaying a list of predetermined options. This is an entry field in which either one of them can be designated or a character can be entered.

  Thus, for example, document data with a form field such as a PDF format or a DocuWorks format is transmitted as image data from the terminal device 6 to the image forming device 4. The image forming apparatus 4 prints or stores the received image data. As described above, when document data with form fields is printed by the image forming apparatus 4, for example, document data with form fields is directly transmitted to the image forming apparatus 4 instead of being converted into data for printing by a printer driver. Print (direct print).

  FIG. 2 is a cross-sectional view showing the image forming apparatus 4. The image forming apparatus 4 includes a UI device 10, a printing device 12, a reading device 14, and a communication device 16.

  The UI device 10 is configured as a touch panel, for example, and includes a function as a display device that displays information and a function as an input reception device that receives an input made by an operator.

  The printing device 12 is a device that performs printing. The printing apparatus 12 includes, for example, three stages of recording medium supply cassettes 18, and each of the recording medium supply cassettes 18 is provided with a supply head 20.

  When one of the recording medium supply cassettes 18 is selected, the supply head 20 is actuated and supplied from the selected recording medium supply cassette 18 to the image forming mechanism 24 via the recording medium supply path 22.

  The image forming mechanism 24 is provided with yellow, magenta, cyan, and black photoconductors 26 and an intermediate transfer belt 28.

  Around each photoconductor 26, a charging device, an exposure device, a developing device, a primary transfer device, a cleaning device, and the like (not shown) are arranged, and a toner image formed on each photoconductor 26 is transferred to the intermediate transfer belt 28. Transcribed. When black and white is set, only black is enabled.

  The toner image on the intermediate transfer belt 28 is transferred to the sent recording medium by the secondary transfer roll 30 and fixed by the fixing device 32, and the recording medium on which the toner image is fixed passes through the recording medium discharge path 34. And discharged to the discharge unit 36.

  However, when duplex printing is set, the recording medium whose surface is fixed by the fixing device 32 is sent from the recording medium discharge path 34 to the reversing device 38, reversed by the reversing device 38, and recorded on the recording medium reversing path 40. To the recording medium supply path 22 again and sent to the image forming mechanism 24 to print the back side.

  The reading device 14 has an automatic document feeder 42 capable of reading a double-sided document. The automatic document feeder 42 feeds the document to a platen 44, and the document is scanned on the platen 44 by a reading unit 46 composed of a CCD or the like. Images are read.

  A document set detector 48 for detecting whether or not a document is set on the automatic document feeder 42 is provided. The automatic document feeder 42 also serves as a platen cover, and the document can be placed on the platen 44 by opening the platen cover. The opening / closing of the platen cover can be detected by a platen cover opening / closing detector 50.

  The communication device 16 is a device that communicates with an external device such as the terminal device 6 via the network 8, and corresponds to, for example, a data line termination device. The image forming apparatus 4 acquires the document data transmitted from the terminal device 6 by using, for example, the communication device 16.

  FIG. 3 is a block diagram illustrating a hardware configuration of the image forming apparatus 4.

  As shown in FIG. 3, the image forming apparatus 4 has a configuration in which a CPU 60, a memory 62, and a storage device 64 are connected by a bus in addition to the above-described printing device 12, reading device 14, UI device 10, and communication device 16. ing.

  As described above, the image forming apparatus 4 includes a component as a computer capable of communicating with the terminal device 6 and other devices.

  The CPU 60 controls the operation of the image forming apparatus 4 by executing a program written in the memory 62 or the storage device 64. In addition, an input received via the UI device 10 is transmitted to the CPU 60, and display information from the CPU 60 is transmitted to the UI device 10.

  The CPU 60 may execute a program stored in a portable storage medium such as a CD-ROM (not shown), or may execute a program provided through the communication device 16.

  The storage device 64 stores data in a hard disk or the like so as to be able to write and read data.

Next, a functional configuration of the image forming apparatus 4 as a document processing apparatus will be described.
FIG. 4 is a block diagram illustrating a functional configuration of the image forming apparatus 4 realized by executing the program.

  As shown in FIG. 4, the image forming apparatus 4 of the present embodiment includes a first acquisition unit 70, a storage control unit 72, a print control unit 74, a second acquisition unit 76, and a code detection unit 78. A recognition unit 80, an analysis unit 82, a content information extraction unit 84, and a document update unit 86. With such a configuration, for example, when an electronic document with a form field is printed on a recording medium such as paper, and after the printing is added to the printed recording medium, such as handwritten entry or entry by printing, The recording medium on which the post-printing has been added is read, and the description content after the printing is recognized. Further, content information (meta information) representing content already described as data in the electronic document before printing and content information (meta information) representing content added after printing are extracted. Hereinafter, “content information” may be referred to as “meta information”.

  The first acquisition unit 70 acquires image data to which information indicating the position and range of the entry field is added. In the present embodiment, the first acquisition unit 70 acquires an electronic document with a form field. In the present embodiment, the terminal device 6 transmits an electronic document with a form field to be printed out by the image forming apparatus 4 to the image forming apparatus 4, and the first acquisition unit 70 of the image forming apparatus 4 acquires the electronic document. The first acquisition unit 70 acquires image data (electronic document) stored in the storage device 64 as will be described later.

  The storage control unit 72 performs control so that the image data acquired by the first acquisition unit 70 is stored in the storage device 64. In the present embodiment, an electronic document with a form field acquired from the terminal device 6 for printing out is stored in the storage device 64 and the storage location is notified to the print control unit 74. In the present embodiment, the configuration of storing in the storage device 64 provided in the image forming apparatus 4 has been described. However, the configuration may be stored in a device different from the image forming apparatus 4 via, for example, the network 8.

  The print control unit 74 controls to print the image data to be printed acquired by the first acquisition unit 70. At this time, the print control unit 74 prints information indicating the storage location notified from the storage control unit 72 together with the electronic document. In the present embodiment, the print control unit 74 is an optical code image such as a two-dimensional code in which information indicating a storage location is encoded in an electronic document with a form field to be printed acquired by the first acquisition unit 70. And control to print the electronic document to which the optical code image is added.

  With the above configuration, an electronic document with a form field is printed on a recording medium. Thereafter, additional recording is performed on the printed recording medium as described above. Hereinafter, a configuration for recognizing additional contents from a recording medium that has been additionally recorded on a printed recording medium and extracting content information (meta information) will be described.

  The second acquisition unit 76 acquires an image obtained by reading a recording medium on which the image data acquired by the first acquisition unit 70 is printed. In the present embodiment, an image obtained by reading a recording medium on which an electronic document is printed is acquired together with information indicating a storage location notified from the storage control unit 72. In the present embodiment, the second acquisition unit 76 acquires an image obtained by reading the recording medium with the reading device 14. Note that although the image acquired by the second acquisition unit 76 is described as having been additionally written, it is not necessarily required to be additionally written.

  The code detection unit 78 detects an optical code image from the image acquired by the second acquisition unit 76. Further, the first acquisition unit 70 decodes information indicating the storage location of the image data that is the basis of the read image from the optical code image detected by the code detection unit 78, and obtains the original image data. Obtain from the storage location.

  The recognition unit 80 performs recognition processing such as OCR (Optical Character Recognition) on the image acquired by the second acquisition unit 76, and recognizes the content added in the entry column. Here, the recognizing unit 80 fills the image acquired by the second acquiring unit 76 in the entry column after printing based on the information added to the image data acquired by the first acquiring unit 70. Recognize the contents. In the present embodiment, the recognition unit 80 positions the entry field obtained from the form field information added to the electronic document acquired by the first acquisition unit 70 with respect to the image acquired by the second acquisition unit 76. Based on the range and the type of data entered in this entry field, the contents entered in the entry field are recognized after printing.

  Specifically, the recognizing unit 80 specifies the position of the entry field and its region based on the form field information in the image acquired by the second acquiring unit 76, and performs recognition processing on the specified portion. In recognition, the type of data to be recognized is limited based on the form field information. For example, if the form field information indicates that the type of data to be entered in the entry field of the recognition target is a number, the recognition unit 80 compares it with a number pattern image on the assumption that the recognition target is a number. Recognition.

The recognition unit 80 may further perform a recognition process using an analysis result obtained by the following analysis unit 82.
The analysis unit 82 analyzes the content entered on the electronic document in the entry field provided in the electronic document acquired by the first acquisition unit 70. In addition, in the analysis of the contents entered, whether or not there is an entry on the electronic document in the entry field (whether it is an entry field that has been filled in) or not (whether it is an entry field that has not been filled in) Including analysis of. Thus, the analysis unit 82 does not analyze the contents of the entry field from the read image, but analyzes the contents described in the electronic document from the electronic document. For example, when a character string is electronically entered in a certain entry field designated by the form field, the analysis unit 82 extracts this character string from the electronic document.

  Thereby, the recognition unit 80 uses the second acquisition unit for the entry field that has not been entered by the analysis unit 82 and the entry field that has been analyzed by the analysis unit 82 among the entry fields provided in the document acquired by the first acquisition unit 70. A recognition process is performed on the image acquired in 76. As described above, the recognition unit 80 does not recognize all the entry fields in the document as a recognition target, but restricts the entry fields not filled in the electronic document, that is, the entry fields that are assumed to be added after printing. Recognition processing.

  The content information extraction unit 84 converts the content information (meta information), which is information representing the content shown in the image acquired by the first acquisition unit 70 and the image acquired by the second acquisition unit 76, to the first information. Extraction is performed from the image acquired by the acquisition unit 70 and the image acquired by the second acquisition unit 76. Specifically, the content information extraction unit 84 extracts, as content information, the content entered in the completed entry field analyzed by the analysis unit 82 from the image acquired by the first acquisition unit 70, The content recognized by the recognition unit 80 is extracted as content information from the image acquired by the second acquisition unit 76.

  The content information (meta information) extracted by the content information extraction unit 84 is registered in a database provided in the storage device 64 or the like, and is used for data processing, for example. Meta information may be added to the original electronic document or read image.

  The document update unit 86 adds the content recognized by the recognition unit 80 to the image data acquired by the first acquisition unit 70, and updates the image data. As a result, it is used as image data including the added content. Further, the document update unit 86 sets the partial image data of the image region for the image region that has failed to be recognized by the recognition unit 80 or the image region of the entry column whose data type in the entry column is defined as “image”. The image data acquired by one acquisition unit 70 may be added.

  In the case where only the unfilled entry field is to be recognized, the recognizing unit 80 recognizes the entry field determined as the unfilled entry field based on the image data updated by the document update unit 86. It may be configured. For example, in the case of three entry fields A, B, and C, when an addition is made in entry field A in the first addition and entry is made in entry fields B and C in the second addition, the image is read after each addition. Assuming the situation in which the content of additional writing is recognized, the recognition unit 80 recognizes the entry fields A, B, and C in the first recognition, and the recognition unit 80 recognizes only the entry fields B and C in the second recognition. Recognized. In the first recognition, if the entry fields A, B, and C are not filled, the analysis unit 82 analyzes the entry fields A, B, and C, and the recognition unit 80 sets the entry fields A, B, and C as recognition targets. Then, after the first recognition, the document update unit 86 updates the image data to the image data in which the entry field A is entered, and in the second recognition, the recognition unit 80 is based on the updated image data. The entry fields B and C that have been analyzed as unfilled are recognized.

Next, the operation of the image forming apparatus 4 as a document processing apparatus will be described.
FIG. 5 is a flowchart illustrating an example of an operation until an electronic document with a form field is printed in the image forming apparatus 4 as a document processing apparatus.

  In step 100 (S100), the first acquisition unit 70 acquires the electronic document transmitted from the terminal device 6.

  In step 102 (S102), it is determined whether or not the acquired electronic document is an electronic document with a form field. If the electronic document has a form field, the process proceeds to step 104. If not, the process proceeds to step 108. Transition.

  In step 104 (S104), the storage control unit 72 controls to store the acquired electronic document in the storage device 64.

  In step 106 (S106), the print control unit 74 adds an optical code image indicating the storage location to the electronic document, and controls to print the electronic document.

  In step 108 (S108), the electronic document is printed. Thereafter, in step 110 (S110), it is determined whether or not all pages have been completed. If there are unprocessed pages, the process returns to step 102. If all pages have been completed, the process is terminated.

  FIG. 6 is a schematic diagram illustrating an example of an electronic document with form fields acquired by the first acquisition unit 70. In the example shown in FIG. 6, each hatched area in the figure indicates an entry field with form field information. In FIG. 6, the entry fields 90 to 98 enter “character” as the data type. The entry field 100 is an entry field in which an image such as a seal is described. In the example shown in FIG. 6, the entry fields 90 and 92 are already filled in on the electronic document. The entry field 90 has the character string “XXX”, and the entry field 92 has the character string “YYY”. Is filled in.

  FIG. 7 is a schematic diagram illustrating an example of a recording medium on which an electronic document is printed with information indicating a storage location. As shown in FIG. 7, in this embodiment, a two-dimensional code 102 is superimposed and printed on the electronic document as information indicating the storage location of the electronic document.

  FIG. 8 is a flowchart illustrating an example of an operation in the case of extracting meta information from a printed recording medium after printing an electronic document with a form field in the image forming apparatus 4 as a document processing apparatus.

  In step 200 (S200), the second acquisition unit 76 acquires an image obtained by reading a recording medium on which an electronic document is printed.

  In step 202 (S202), the code detector 78 detects the optical code image included in the image acquired in step 200. If an optical code is detected (Yes in step 204), the process proceeds to step 206. If not detected (No in step 204), the process proceeds to step 218.

  In step 206 (S206), the first acquisition unit 70 acquires the storage destination electronic document indicated by the optical code from the storage device 64.

  In step 208 (S208), the analysis unit 82 analyzes the form field information added to the electronic document acquired in step 206. If the entry field of interest has already been entered on the electronic document (Yes in Step 210), the process proceeds to Step 212, and if it has not been entered on the electronic document (No in Step 210), Control goes to step 214.

  In step 212 (S212), the content information extraction unit 84 acquires the content described in the entry field of interest from the electronic document, and uses the acquired content as meta information.

  On the other hand, in step 214 (S214), the recognizing unit 80 performs a recognition process on the entry field of interest based on the form field information, and acquires the contents added to the entry field from the read image. In step 216 (S216), the content information extraction unit 84 uses the content acquired in step 214 as meta information.

  On the other hand, if no optical code is detected in step 204, the recognition unit 80 performs recognition processing in step 218 without using form field information. In this case, for example, the recognition unit 80 performs recognition processing on the entire image.

  In step 220 (S220), it is determined whether or not the processing has been completed for all entry fields indicated by the form field information. If completed, the process proceeds to step 222. If not completed, the process proceeds to step 208. Return.

  In step 222 (S222), it is determined whether or not the processing has been completed for all the recording media from which the meta information is to be extracted. If the processing has been completed, the series of processing is terminated. Return to.

  FIG. 9 is a schematic diagram showing an example of a read image on a recording medium when the electronic document shown in FIG. 6 is printed on the recording medium and then added to the recording medium. Here, of the entry fields shown in FIG. 6, the entry fields 94 to 100 are additionally written.

  FIG. 10 is a schematic diagram showing meta information extracted from the electronic document and the read image shown in FIGS. 6 and 9, and FIG. 10A shows meta information extracted from the electronic document. 10 (b) indicates meta information extracted from the read image. In the example shown in FIG. 10, it is assumed that the entry fields shown in FIGS. 6 and 9 are managed as A1, A2, A3.

  As shown in FIG. 10 (a), meta information is extracted from the electronic document for the contents already filled in the electronic document. Further, as shown in FIG. 10B, meta information is extracted from the read image for the contents added after printing. The contents described in the entry field 100 are extracted as an image.

  Next, a second embodiment of the present invention will be described. In the first embodiment, document processing for an electronic document to which form field information has already been added has been described. However, in the present embodiment, the first embodiment is provided in that form field information is generated from a read image of a recording medium. And different. Specifically, as described below, the entry fields provided in the document are extracted from the differences between the read images of a plurality of recording media that are documents of the same template, and are filled in each entry field. Form field information is generated by determining the data type.

  FIG. 11 is a block diagram showing a functional configuration of the image forming apparatus 4 according to the second embodiment realized by executing a program.

  As shown in FIG. 11, the image forming apparatus 4 according to the present embodiment includes a third acquisition unit 110, a difference extraction unit 112, an entry column extraction unit 114, an entry column information generation unit 116, and a sub-recognition unit. The image forming apparatus 4 is different from the image forming apparatus 4 according to the first embodiment in that a data type determination unit 120 is added.

  The third acquisition unit 110 acquires a plurality of images obtained by reading a plurality of recording media. For example, the third acquisition unit 110 acquires read images of a plurality of recording media on which documents of the same template are represented. Here, the template is provided with an entry field, and the recording medium acquired by the third acquisition unit 110 includes those recorded in the entry field. In the present embodiment, the third acquisition unit 110 acquires an image obtained by reading the recording medium with the reading device 14.

  FIG. 12 is a schematic diagram illustrating a plurality of read images acquired by the third acquisition unit 110. In the example shown in FIG. 12, an address, an amount, and the like are added to each document sheet of a predetermined template for “invoice” along an entry column defined by the template.

  The difference extraction unit 112 extracts differences in a plurality of images acquired by the third acquisition unit 110, and acquires a description part that is not common to a description part common to the plurality of images.

  FIG. 13 is a schematic diagram showing a description common to a plurality of read images shown in FIG. As shown in FIG. 13, by taking the difference between the read images, predetermined template information for “invoice” is generated. In this way, document format information (model information) is generated by extracting a description portion common to a plurality of images.

  Based on the differences between the plurality of images extracted by the difference extraction unit 112, the entry column extraction unit 114 extracts a description portion that is not common among the plurality of images as an entry column. Thereby, in each recording medium, a part arbitrarily added is extracted as an entry field. Specifically, the entry column extraction unit 114 extracts the position and range of the entry column. For example, the entry column extraction unit 114 extracts a position of a description portion that is not common among a plurality of images in the difference as a position of the entry column. In addition, the entry column extraction unit 114 is a ruled line that surrounds a description portion that is not common among a plurality of images, and a ruled line that is described in common between a plurality of images is a range surrounded by the ruled line. Extract as a range.

  The entry field information generation unit 116 generates form field information (entry field information) that is information about the entry field from the information extracted by the entry field extraction unit 114. Specifically, form field information including information on the position and range of the entry field is generated.

  For example, the form field information generated by the entry field information generation unit 116 may be added to an “invoice” electronic document that does not include the form field information. Here, as described above, the electronic document to which form field information is added is template information of a document obtained by extracting a description portion common to a plurality of images by the processing of the difference extraction unit 112. May be. Further, the first acquisition unit 70 may acquire an electronic document to which form field information generated from the extraction result by the entry column extraction unit 114 is added, and perform the above-described processing.

  In the present embodiment, the entry field information generation unit 116 generates form field information further including information indicating the data type of the entry field determined by the data type determination unit 120 described later.

  The sub-recognition unit 118 performs recognition processing for the contents described in the entry field extracted by the entry field extraction unit 114. The content recognized by the sub-recognition unit 118 may be stored in the database as dictionary data in which candidates to be entered in the entry field are recorded. Further, in recognition by the recognition unit 80, recognition may be performed based on this dictionary data.

  The data type determination unit 120 determines the type of data described in the entry field based on the content recognized by the sub recognition unit 118. Specifically, for example, when the description content of each read image for the entry column of interest is only “numbers”, it is determined that the data type is “numbers”.

  In addition, when the description content of each read image with respect to the entry column of interest is only “amount”, it may be determined that the data type is “amount”, or When the description content is only “date”, it may be determined that the data type is “date”. For example, the data type determination unit 120 determines “amount” when a number is written together with a mark indicating an amount such as “¥” or “$”. Further, for example, when numbers are separated and described by “/” or the like, the data type determination unit 120 determines “date”.

  Thus, in this embodiment, the entry field information generation unit 116 generates form field information further including information indicating the data type of the entry field determined by the data type determination unit 120.

  FIG. 14 is a schematic diagram for explaining an example of form field information generated by the entry field information generation unit 116. In the example shown in FIG. 14, the hatched areas in the figure are extracted as entry fields, and “standard”, “amount”, and “date” written in the hatched areas are Indicates the type of data in the entry field. The “standard” is a type indicating that the data is a character string.

  FIG. 15 is a flowchart illustrating an example of an operation when generating form field information in the second embodiment.

  In step 300 (S300), the third acquisition unit 110 acquires read images of a plurality of recording media.

  In step 302 (S302), the difference extraction unit 112 performs a difference extraction process for each read image acquired in step 300. At this time, a description portion common to a plurality of images (No in step 304) is extracted as document format information (model information) in step 306 (S306). On the other hand, a description portion that is not common among a plurality of images (Yes in Step 304) is extracted as an entry field in Step 308 (S308).

  In step 310 (S310), the sub-recognition unit 118 performs recognition processing for the contents described in the entry column extracted in step 308.

  In step 312 (S312), the data type determination unit 120 determines the type of data described in the entry field based on the recognition result in step 310.

  In step 314 (S314), the entry field information generation unit 116 generates form field information based on the information about the entry fields obtained in step 308 and step 312.

  In step 316 (S316), an electronic document with a form field is created from the format information of the document generated in step 306 and the form field information generated in step 314.

  As described above, the embodiment in which the document processing apparatus is realized by the image forming apparatus has been described. However, the document processing apparatus does not necessarily have to be realized by the image forming apparatus, and the document processing apparatus does not include a printing apparatus and a reading apparatus. May be.

  The first acquisition unit 70 has been described with respect to the configuration for acquiring the image data transmitted from the terminal device 6. However, the first acquisition unit 70 may acquire the image data held by the image forming apparatus 4 itself, or the image forming apparatus 4. You may acquire the image data which self produced.

  In the embodiment described above, the content information about the read image of the recording medium printed based on the image data to which the information indicating the position and range of the entry field and the type of data entered in the entry field is added. Although an example of extracting the content information has been described, the content information may be extracted without using the information regarding the data type.

  That is, for example, the first acquisition unit 70 acquires first image data to which information indicating the position and range of the entry field is added, and the second acquisition unit 76 generates an image corresponding to the first image data. An area of the second image data corresponding to an area specified by the recognition unit 80 from the position and range information added to the first image data by acquiring the second image data obtained by reading the printed recording medium It may be configured to recognize the content information entered in.

  Further, the position and range information added to the first image data used by the recognition unit 80 may be obtained from other than the first image data stored in the storage device 64. For example, the print control unit 74 records information indicating the position and range of the entry field added to the first image when the first image acquired by the first acquisition unit 70 is printed together with the first image. Printing on the medium, the reading device 14 reads the recording medium, the second acquisition unit 76 acquires the first image and the second image including information indicating the position and range of the entry field, and the recognition unit 80 You may comprise so that a recognition process may be performed based on the information showing the position and range of the entry column obtained by reading this recording medium.

2 Document processing system 4 Image forming device 6 Terminal device 12 Printing device 14 Reading device 64 Storage device 70 First acquisition unit 72 Storage control unit 74 Print control unit 76 Second acquisition unit 78 Code detection unit 80 Recognition unit 82 Analysis unit 84 Content information extraction unit 86 Document update unit 110 Third acquisition unit 112 Difference extraction unit 114 Entry field extraction unit 116 Entry field information generation unit 118 Sub-recognition unit 120 Data type determination unit

Claims (7)

First acquisition means for acquiring first image data to which information representing a position and a range is added;
Second acquisition means for acquiring second image data obtained by reading a recording medium on which an image corresponding to the first image data is printed;
Recognizing means for recognizing content information entered in the recording medium from the area of the second image data corresponding to the area specified from the position and range;
Updating means for updating the content information recognized by the recognition means to the third image data added to the first image data,
When there is an area where the content information cannot be recognized by the recognizing means, the updating means adds the second image data corresponding to the area to the first image data.
Processing equipment. The first acquisition means acquires first image data to which information on the type of data to be filled is added in addition to the information indicating the position and range,
The processing device according to claim 1, wherein the recognizing unit recognizes the content information with reference to information on a type of the data. It further comprises reading means for reading a recording medium on which information representing the position and range is printed,
The processing apparatus according to claim 1, wherein the second acquisition unit acquires information representing the position and range printed on the recording medium. Further comprising reading means for reading a recording medium on which storage destination information in which information indicating the position and range is stored is printed;
The processing apparatus according to claim 1, wherein the second acquisition unit acquires the storage destination information printed on the recording medium. The processing apparatus according to any one of claims 1 to 4, wherein the recognition unit recognizes an area in the first image data in which content information is not entered in the area. It further has an extraction means for extracting a difference between a plurality of image data and extracting a position and a range from information regarding the difference,
The processing apparatus according to claim 1, wherein the recognition unit recognizes content information written in a region corresponding to the position and range extracted by the extraction unit. A step in which information representing the position and range to obtain the first image data added,
Obtaining second image data obtained by reading a recording medium on which the first image data is printed;
Recognizing from the second image data content information entered on the recording medium in an area specified from the position and range;
An update step for updating the recognized content information to the third image data added to the first image data;
In the update step, when there is an area where the content information cannot be recognized, the program adds the second image data corresponding to the area to the first image data .

Images