JP2010034807A - Image processor, image processing method, image processing program, and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor for correctly and efficiently manage the reception image of facsimile reception, and to provide an image processing method, an image processing program and a recording medium. <P>SOLUTION: A combined device 1 includes: a communication control part 5, which performs facsimile reception with a transmission source connected to a prescribed line in response to a facsimile control procedure, receives a facsimile image transmitted from the transmission source, and acquires transmission source-related information for specifying the transmission source, based on the communication procedure of facsimile communication; an OCR control part 15, which selects one OCR dictionary from the plurality of OCR dictionaries stored in an OCR dictionary part 17, based on the transmission source-related information, where OCR-processes the prescribed area of the reception image through the use of the OCR dictionary; and a file management part 11 which determines a reception image management method, based on the OCR processing result. Consequently, a character recognition rate in OCR processing is enhanced, by selecting the OCR dictionary suitable for the character of the facsimile reception image. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image processing method, an image processing program, and a recording medium, and more particularly, to an image processing apparatus, an image processing method, an image processing program, and an image processing apparatus for accurately and efficiently managing received images of facsimile reception. The present invention relates to a recording medium.

  Recently, computerization of information has progressed, and documents conventionally stored as paper documents have also been digitized. Along with the digitization of such documents, a large amount of digitized documents has been distributed, and how to manage and easily reuse the collected and accumulated digitized documents has become a serious problem. There is a demand for automatic classification of documents collected for a certain purpose.

  Such automatic document processing is also required for facsimile received documents. The received documents received by facsimile are digitized and sorted into folders or sent to other devices on the network. Therefore, there is a demand for effective use of facsimile received documents.

  Conventionally, using an OCR (Optical Character Reader) function, a destination, subject, and text string are extracted from an image obtained by scanning a transmission original, and an email destination, subject, and text are extracted. There has been proposed a network multi-function peripheral that is set as the above and transmits an e-mail (see Patent Document 1).

JP 2005-244411 A

  However, in the above prior art, an e-mail is generated by performing OCR analysis from an image obtained by reading a document image and extracting a character string of a destination, a subject, and a body text. There is a need for improvement in order to appropriately and efficiently perform digitization of received facsimile images while improving the OCR character recognition rate.

  Accordingly, the present invention provides an image processing apparatus, an image processing method, an image processing program, and an image processing apparatus that select an OCR dictionary suitable for a character type of a received facsimile image, perform OCR processing, and appropriately and efficiently manage the received facsimile image. The object is to provide a recording medium.

  In order to achieve the above object, the present invention performs facsimile reception according to a predetermined facsimile control procedure with a transmission source connected to a predetermined line, receives a facsimile image sent from the transmission source, When managing received received images, a plurality of OCR dictionaries stored in the OCR dictionary storage means are acquired from the control procedure of the facsimile communication to acquire transmission source related information for specifying the transmission source and based on the transmission source related information One OCR dictionary is selected from the above, a predetermined region of the received image is OCR processed using the selected OCR dictionary, and a management method of the received image is determined based on the OCR processing result. It is said.

  Further, the present invention provides the source-related information as a country code of a CSI signal of a facsimile control signal, number display information sent through the line, and the received dial-in number and a plurality of received dial-in numbers. Of the connected lines, at least one of the received line types may be acquired.

  Furthermore, the present invention may be characterized in that, among the received images, either a TTI region or an image region other than the TTI region is selected as an OCR processing target region, and the selected region is subjected to OCR processing.

  According to the present invention, information necessary for managing a received image by selecting an OCR dictionary based on transmission source related information for specifying a transmission source for facsimile reception is acquired from the received image by OCR processing, and the received image is received. Thus, the OCR dictionary suitable for the character type of the received facsimile image can be selected to improve the character recognition rate of the OCR processing, and the received image can be managed more appropriately.

  Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In addition, since the Example described below is a suitable Example of this invention, various technically preferable restrictions are attached | subjected, However, The range of this invention is unduly limited by the following description. However, not all the configurations described in the present embodiment are essential constituent elements of the present invention.

  1 to 11 are diagrams illustrating an embodiment of an image processing apparatus, an image processing method, an image processing program, and a recording medium according to the present invention. FIG. 1 illustrates an image processing apparatus, an image processing method, and an image according to the present invention. 1 is a block configuration diagram of a composite apparatus 1 to which an embodiment of a processing program and a recording medium is applied. FIG.

  In FIG. 1, a composite apparatus 1 includes a main control unit 2, a display / operation control unit 3, a job control unit 4, a communication control unit 5, a compression / decompression control unit 6, a plotter control unit 7, a scanner control unit 8, and a destination management unit. 9, internal switch / own terminal registration data unit 10, file management unit 11, network control unit 12, report control unit 13, counterpart CSI control unit 14, OCR control unit 15, number display control unit 16, OCR dictionary unit 17, A dial-in control unit 18, an image direction determination control unit 19, a multi-line exclusion control unit 20, a Tiff / PDF creation control unit 21, and the like are provided, and each main unit is connected to a bus 22.

  The main control unit 2 uses a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. An image processing program and necessary data are stored, and the CPU controls each part of the composite apparatus 1 using the RAM as a work memory based on the program in the ROM, and executes basic processing as the composite apparatus 1. At the same time, the OCR dictionary is appropriately switched based on the received information of facsimile reception described later to appropriately perform character recognition of the received facsimile image (document) and manage the output of the received image.

  That is, the composite apparatus 1 includes a ROM, an EEPROM (Electrically Erasable and Programmable Read Only Memory), an EPROM, a flash memory, a flexible disk, a CD-ROM (Compact Disc Read Only Memory), a CD-RW (Compact Disc Rewritable), a DVD ( Main control by reading an image processing program for executing the image processing method of the present invention recorded on a computer-readable recording medium such as a digital video disk (SD), a secure digital (SD) card, or an MO (Magneto-Optical Disc) By introducing the ROM 2 or the hard disk of the unit 2 to an image processing method for appropriately switching the OCR dictionary based on reception information of facsimile reception described later, appropriately performing character recognition of the received facsimile document, and outputting an image. It is constructed as a composite device 1 as a processing device. This image processing program is a computer-executable program written in a legacy programming language such as assembler, C, C ++, C #, Java (registered trademark) or an object-oriented programming language, and is stored in the recording medium. Can be distributed.

  The display / operation control unit (selection / setting unit, area selection unit) 3 is connected to a display unit and an operation unit (not shown). The operation unit includes a numeric keypad, a start key, a function key, a one-touch dial key, and an abbreviated dial. Various operation keys necessary for the operation of the Internet composite apparatus 1 such as keys are provided, and the display unit uses, for example, a liquid crystal display and the like, and exchanges data with the main control unit 2 to start operation from the operation unit. The contents of the input command and various information notified from the composite apparatus 1 to the operator are displayed. The display / operation control unit 3 controls the operation of each part of the display unit and the operation unit, exchanges various data with the main control unit 2, and displays the operation contents of the operation keys on the operation unit. 2 and display data is received from the main control unit 2 and displayed on the display unit. In particular, the operation unit and the display unit select the OCR dictionary selection setting to be selected as the OCR dictionary corresponding to the transmission source related information and the received image from either the TTI region or the image region other than the TTI region as the OCR processing target region. The display / operation control unit 3 performs control between this operation and the main control unit 2.

  The job control unit 4 performs main control when a job such as copying, scanning, facsimile reception, facsimile transmission, document organization, e-mail creation / transmission, etc., which is instructed by the operator to the multifunction device 1, occurs. When a job request is generated in the unit 2 and the main control unit 2 requests generation of control in response to the job generation request, the job generation request is accepted and job execution control is performed.

  The communication control unit (sender information acquisition means) 5 is composed of, for example, a G3 control unit and the like, and exchanges facsimile control signals with a partner facsimile apparatus connected via a public line network or the like. Data conversion is performed and a facsimile communication procedure is executed.

  The compression / decompression control unit 6 is for improving the efficiency of storing image data in an image memory (not shown) and shortening the transmission time. A predetermined encoding method, in particular, the composite apparatus 1 is a network facsimile apparatus. Therefore, the image data is encoded by the MH (Modified Huffman) encoding method, and the encoded image data is decoded.

  A plotter (not shown) is connected to the plotter control unit 7. As the plotter, for example, a printing apparatus such as an electrophotographic system or an ink ejection system is used. The plotter control unit 7 controls the plotter based on image data (write data) transferred from an image memory or the like, and causes the plotter to record and output an image corresponding to the image data on paper.

  The scanner control unit 8 is connected to a scanner (not shown). For example, an image scanner using a CCD (Charge Coupled Device) is used as the scanner. Is scanned to read the image of the document with a predetermined resolution. The scanner control unit 8 controls the operation of the scanner in accordance with a control signal from the main control unit 2, causes the scanner to read an image of the document, and transfers the image of the document read by the scanner to an image memory (not shown). .

  The destination management unit 9 creates a destination management table composed of destination information such as a destination ID, a user name, and the like for each destination of facsimile communication, and under the control of the main control unit 2 based on the destination management table. Perform destination management.

  The internal switch / own terminal registration data unit 10 stores the state of the switch for performing various operation settings of the multifunction apparatus 1 and data related to the multifunction apparatus 1 (model, machine number, own facsimile number, etc.).

  The file management unit 11 manages various files such as generating and deleting image files for transmission and reception under the control of the main control unit 2. In particular, the file management unit 11 determines a management method for the received facsimile image based on an OCR processing result by the OCR control unit 15 described later.

  A predetermined network, for example, a cable such as a LAN (Local Area Network) is connected to the network control unit 12, and an information processing apparatus such as a personal computer, a data server, and the like are connected to the network. The network control unit 12 converts compressed image data transmitted from an information processing device or data via the network into image data that can be processed by the composite device 1, and converts the image data in the image memory into the image data. When transferring to an information processing apparatus or the like, the image data is converted into image data that can be processed by the information processing apparatus or the like, and transmitted to the information processing apparatus or the like.

  The report control unit 13 manages various reports such as communication reports under the control of the main control unit 2, and causes the plotter to record and output the report on a sheet via the plotter control unit 7 as necessary.

  The counterpart CSI control unit (sender information acquisition means) 14 is called CSI (Called Subscriber Identification) which is partner identification information (sender information) sent from the sender at the time of facsimile communication, in particular, facsimile reception. Signal) The sender information such as the destination telephone number is acquired from the signal and notified to the job control unit 4.

  The OCR control unit (OCR processing unit) 15 performs OCR processing of the OCR target image and transmits from the job control unit 4 among a plurality of OCR dictionaries stored in the OCR dictionary unit (OCR dictionary storage unit) 17. Based on the original information, an OCR dictionary to be used in the OCR processing is selected, and a predetermined area of the received image is OCR processed using the selected OCR dictionary.

  The number display control unit (transmission source information acquisition means) 16 extracts the number display information (transmission source information) of the partner device (transmission source device) from the facsimile protocol when the communication control unit 5 performs facsimile reception, and performs job control. The number display information is notified to the unit 4.

  The OCR dictionary unit 17 stores a plurality of OCR dictionaries corresponding to languages of each country and the like, and the OA control unit 15 selects and uses them.

  The dial-in control unit (transmission source information acquisition means) 18 extracts dial-in number information (transmission source information) of the partner device from the protocol when the communication control unit 5 performs facsimile reception, and dials in the job control unit 4. Notify number information.

  An image direction determination control unit (OCR processing direction control unit, OCR processing result determination unit) 19 operates under the control of the main control unit 2 and performs OCR processing on the OCR control unit 15 from the vertical and horizontal directions of the facsimile received image. Accordingly, the image direction of the received image is determined based on the character recognition rate (hit rate) in the OCR processing by the OCR control unit 15 in each direction.

  The multiple line exclusive control unit (sender information acquisition means) 20 determines which line is currently receiving a facsimile when a plurality of lines are connected to the communication control unit 5; The job type is notified to the job control unit 4.

  The TIFF / PDF creation control unit 21 generates TIFF (Tag Image File Format) data and / or PDF (Portable Document Format) data from the received facsimile image, and passes it to the file management unit 11.

  Next, the operation of this embodiment will be described. When receiving the facsimile, the multifunction apparatus 1 according to the present embodiment selects an appropriate OCR dictionary for the received image, performs OCR processing, and manages the received image based on the OCR processing result.

  First, a case where received images are managed based on a country code (country information) analyzed based on a facsimile protocol CSI signal will be described with reference to FIGS.

  As shown in FIG. 2, the multifunction device 1 includes a CSI country code and an OCR dictionary table used corresponding to the CSI country code (hereinafter referred to as a country code corresponding use OCR dictionary selection table). In this country code correspondence use OCR dictionary selection table, the country code corresponding to the CSI and the OCR dictionary are registered in advance in association with each other. The OCR dictionary used for the country code can be set or changed as appropriate.

  When the communication control unit 5 detects ringing in the state where the country code corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, as illustrated in FIG. 4 receives G3 reception permission and starts the facsimile reception protocol (step S101).

  When the communication control unit 5 starts the facsimile protocol, the multifunction device 1 recognizes the CSI signal sent from the transmission source, and extracts and extracts the country code from the CSI signal. The country code is notified to the job control unit 4 (step S102). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 finishes all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 is passed from the counterpart CSI control unit 14 to the OCR control unit 15. Notify the country code and request OCR processing. The OA control unit 15 refers to the country code corresponding use OCR dictionary selection table based on the country code passed from the job control unit 4, and converts the OCR dictionary corresponding to the country code to the OCR processing of the facsimile reception image. The dictionary to be used is switched from a preset dictionary (step S105).

  The OCR control unit 15 performs OCR processing of the facsimile reception image data stored in the file management unit 11 using the selected OCR dictionary (step S106). In this case, the OCR control unit 15 may perform OCR processing for all regions of all pages of the received image. However, if the OCR processing is to determine the output destination of the received image and organize and classify, Only a specific description area (for example, a TTI area portion) of information necessary for performing the sorting and classification in the image is subjected to OCR processing and character recognition is performed.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted character and image file ID to the job control unit 4, and the job control unit 4 transmits the received character and image file ID to TIFF / PDF. The creation control unit 21 is notified. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 to Tiff or PDF, and the image file together with the characters received from the job control unit 4 to the file management unit 11. To pass. The file management unit 11 manages the received image file based on the received OCR recognition character (step S108). As the data file management, for example, the output destination of the received image is determined based on the character recognition result, for example, storage in a folder, transmission to a computer, facsimile transfer, e-mail transmission, and the like are performed. That is, in this file management process, the file management unit 11 may classify and store the TIFF file or PDF file in the internal memory based on the character of the OCR process result as described above, or may be stored in another computer. It is also possible to output to an output destination associated with the analyzed character in advance, such as transmission to the e-mail or e-mail.

  As described above, the composite apparatus 1 according to the present embodiment performs facsimile reception according to a predetermined facsimile control procedure with a transmission source connected to a predetermined line, and receives a facsimile image transmitted from the transmission source. When managing the received image, the transmission source related information for specifying the transmission source is acquired from the control procedure of the facsimile communication, and based on the transmission source related information, the OCR dictionary unit 17 stores a plurality of OCR dictionaries. One OCR dictionary is selected, and the OCR control unit 15 performs OCR processing on a predetermined area of the received image using the selected OCR dictionary. Based on the OCR processing result, the file management unit 11 selects the received image. The management method is determined.

  Therefore, it is possible to improve the character recognition rate of the OCR process by selecting an OCR dictionary suitable for the characters of the facsimile received image, and to manage the received image more appropriately.

  Also, the composite apparatus 1 of the present embodiment acquires the country code of the CSI signal of the facsimile control signal as the transmission source related information, selects an OCR dictionary based on the country code, and selects the selected OCR dictionary The OCR control unit 15 performs OCR processing on a predetermined area of the received image, and the file management unit 11 determines the management method of the received image based on the OCR processing result.

  Therefore, it is possible to improve the character recognition rate of the OCR process by selecting an OCR dictionary suitable for the characters of the facsimile received image, and to manage the received image more appropriately.

  Furthermore, in the selection of the OCR dictionary, the composite apparatus 1 performs the OCR dictionary selection process based on the country code based on the CSI. As described above, the user can display the OCR dictionary selected by the country code based on the CSI. The setting of the country code corresponding use OCR dictionary selection table can be changed by operation of the operation control unit 3 or the like.

  Therefore, when a facsimile image written in Japanese from an overseas branch office is received, the OCR processing is set by using a Japanese dictionary instead of the foreign language OCR dictionary determined by the CSI. Recognition rate can be improved.

  In the above description, the OCR dictionary is selected, but the OCR dictionary is selected based on the country code based on CSI. However, the OCR dictionary is selected based on the country code based on CSI. For example, as shown in FIGS. 4 and 5, the OCR dictionary may be selected based on the number display information of the transmission source by the number display function. In FIG. 5, the same processing steps as those in FIG. 3 are denoted by the same step numbers, and the description thereof is simplified.

  When the composite apparatus 1 selects the OCR dictionary based on the transmission source number display information, as shown in FIG. 4, the OCR control unit 15 uses the number display information and the OCR dictionary to be used corresponding to the number display information. Table (hereinafter referred to as “number display information corresponding use OCR dictionary selection table”), and this number display information correspondence use OCR dictionary selection table includes number display information and OCR dictionary sent in advance from the station during communication. Although registered in association with each other, the OCR dictionary to be used corresponding to the number display information can be appropriately set or changed by the operation from the display / operation control unit 3 by the user.

  When the communication control unit 5 detects ringing in the state where the number display information corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, the multifunction device 1 permits the job control unit 4 to accept G3 reception. In response, the facsimile reception protocol is started (step S101).

  In the composite apparatus 1, when the communication control unit 5 starts the facsimile protocol, the number display control unit 16 extracts the number display information sent from the communication station of the line, and the extracted number display information is used as the job control unit 4. (Step S202). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 finishes all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 is passed from the number display control unit 16 to the OCR control unit 15. The number display information is notified and an OCR processing request is made. The OA control unit 15 refers to the number display information corresponding use OCR dictionary selection table based on the number display information passed from the job control unit 4, and sets the OCR dictionary corresponding to the number display information to the OCR of the received facsimile image. Switching from a dictionary preset as a dictionary to be used for processing (step S202).

  The OCR control unit 15 performs OCR processing of the facsimile reception image data stored in the file management unit 11 using the selected OCR dictionary (step S106). In this case, as described above, the OCR control unit 15 may perform OCR processing for all areas of all pages of the received image. However, in the OCR processing for determining the output destination of the received image and organizing and classifying it. If there is, the OCR process is performed only on the description area of the information necessary for organizing and classifying the received image, character recognition is performed, and the output destination of the received image based on the result of the character recognition, for example, folder, computer Determine facsimile transfer, e-mail transmission, etc.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted characters (OCR extracted characters) and the image file ID to the job control unit 4, and the job control unit 4 receives the received characters and image file. The ID is notified to the TIFF / PDF creation control unit 21. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 into a Tiff or PDF, along with the characters recognized by the OCR processing received from the job control unit 4 The file is transferred to the file management unit 11. The file management unit 11 manages the data file based on the received OCR recognition result character for the received image file (step S108).

  As described above, the composite apparatus 1 according to the present embodiment acquires number display information as transmission source related information, selects an OCR dictionary based on the number display information, and uses the selected OCR dictionary. The OCR control unit 15 performs OCR processing on a predetermined area of the received image, and the file management unit 11 determines the management method of the received image based on the OCR processing result.

  Therefore, it is possible to improve the character recognition rate of the OCR process by selecting an OCR dictionary suitable for the characters of the facsimile received image, and to manage the received image more appropriately.

  The method for selecting the OCR dictionary is not limited to the method based on the country code and the number display information by the CSI. For example, as shown in FIG. 6 and FIG. When a plurality of numbers are subscribed, a dial-in number may be acquired as source-related information, and an OCR dictionary may be selected based on the dial-in number. In FIG. 7, the same processing steps as those in FIG. 3 are denoted by the same step numbers, and the description thereof is simplified.

  When the multifunction device 1 selects the OCR dictionary based on the transmission source dial-in caller number, the OCR control unit 15 uses the dial-in number and the OCR corresponding to the dial-in number as shown in FIG. An OCR dictionary table (hereinafter referred to as a dial-in number corresponding use OCR dictionary selection table) of the dictionary unit 17 is held, and this dial-in number corresponding use OCR dictionary selection table is dialed in advance from a station during communication. The in number and the OCR dictionary are associated with each other. The dial-in number corresponding use OCR dictionary selection table of the OCR dictionary unit 17 can be set and registered as appropriate or the contents of the table can be changed according to the operation from the display / operation control unit 3 by the user.

  When the communication control unit 5 detects ringing in the state where the dial-in number corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, the job control unit 4 permits the job control unit 4 to accept G3 reception. In response, the facsimile reception protocol is started (step S101).

  In the multifunction apparatus 1, when the communication control unit 5 starts the facsimile protocol, the dial-in control unit 18 extracts the dial-in number sent from the communication station of the line, and the extracted dial-in number is used as the job control unit 4. (Step S301). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 finishes all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 is passed from the dial-in control unit 18 to the OCR control unit 15. Notify the dial-in number and request OCR processing. The OA control unit 15 refers to the dial-in number corresponding use OCR dictionary selection table based on the dial-in number passed from the job control unit 4, and obtains the OCR dictionary corresponding to the dial-in number from the OCR of the facsimile received image. Switching from a dictionary preset as a dictionary to be used for processing (step S302).

  The OCR control unit 15 performs OCR processing of the facsimile reception image data stored in the file management unit 11 using the selected OCR dictionary (step S106). In this case, as described above, the OCR control unit 15 may perform OCR processing for all areas of all pages of the received image. However, in the OCR processing for determining the output destination of the received image and organizing and classifying it. If there is, the OCR process is performed only on the description area of the information necessary for organizing and classifying the received image, character recognition is performed, and the output destination of the received image based on the result of the character recognition, for example, folder, computer Determine facsimile transfer, e-mail transmission, etc.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted characters (OCR extracted characters) and the image file ID to the job control unit 4, and the job control unit 4 receives the received characters and image file. The ID is notified to the TIFF / PDF creation control unit 21. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 into a Tiff or PDF, along with the characters recognized by the OCR processing received from the job control unit 4 The file is transferred to the file management unit 11. The file management unit 11 manages the data file based on the received OCR recognition result character for the received image file (step S108).

  As described above, the composite apparatus 1 according to the present embodiment acquires a dial-in number as transmission source related information, selects an OCR dictionary based on the dial-in number, and uses the selected OCR dictionary. The OCR control unit 15 performs OCR processing on a predetermined area of the received image, and the file management unit 11 determines the management method of the received image based on the OCR processing result.

  Therefore, it is possible to improve the character recognition rate of the OCR process by selecting an OCR dictionary suitable for the characters of the facsimile received image, and to manage the received image more appropriately.

  Further, the selection method of the OCR dictionary is not limited to the method based on the country code, the number display information, and the dial-in number by the CSI. When a plurality of lines are connected to the composite apparatus 1, for example, FIG. As shown in FIG. 9, the OCR dictionary may be selected based on the line type in which facsimile reception has occurred. In FIG. 9, processing steps similar to those in FIG. 3 are denoted by the same step numbers, and the description thereof is simplified.

  When the composite apparatus 1 selects the OCR dictionary based on the line type in which the facsimile reception has occurred, the OCR control unit 15 selects the line type and the OCR dictionary used corresponding to the line type as shown in FIG. A table (hereinafter referred to as a line type corresponding use OCR dictionary selection table) is held, and this line type corresponding use OCR dictionary selection table includes a plurality of line types (for example, as shown in FIG. 8) connected to the composite apparatus 1. As shown, the line 1 to the line n) and the OCR dictionary are associated with each other, and a table for setting or changing the contents as appropriate according to the operation from the display / operation control unit 3 by the user is registered.

  When the communication control unit 5 detects ringing in the state where the line type corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, the multifunction device 1 permits the job control unit 4 to accept G3 reception. In response, the facsimile reception protocol is started (step S101).

  When the communication control unit 5 starts the facsimile protocol, the multi-line exclusive control unit 20 recognizes the line type indicating which line is the current facsimile reception line, and determines the recognized line type. The job control unit 4 is notified (step S401). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 ends all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 sends the line passed from the communication control unit 5 to the OCR control unit 15. The type is notified and a request for OCR processing is made. The OA control unit 15 refers to the line type corresponding use OCR dictionary selection table based on the line type passed from the job control unit 4 and uses the OCR dictionary corresponding to the line type for the OCR processing of the facsimile received image. The dictionary preset as the dictionary to be switched is switched (step S402).

  The OCR control unit 15 performs OCR processing of the facsimile reception image data stored in the file management unit 11 using the selected OCR dictionary (step S106). In this case, as described above, the OCR control unit 15 may perform OCR processing for all areas of all pages of the received image. However, in the OCR processing for determining the output destination of the received image and organizing and classifying it. If there is, the OCR process is performed only on the description area of the information necessary for organizing and classifying the received image, character recognition is performed, and the output destination of the received image based on the result of the character recognition, for example, folder, computer Determine facsimile transfer, e-mail transmission, etc.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted characters (OCR extracted characters) and the image file ID to the job control unit 4, and the job control unit 4 receives the received characters and image file. The ID is notified to the TIFF / PDF creation control unit 21. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 into a Tiff or PDF, along with the characters recognized by the OCR processing received from the job control unit 4 The file is transferred to the file management unit 11. The file management unit 11 manages the data file based on the received OCR recognition result character for the received image file (step S108).

  As described above, the composite apparatus 1 according to the present embodiment acquires the line type of the line that received the facsimile as the transmission source related information, selects the OCR dictionary based on the line type, and selects the selected line. A predetermined area of the received image is OCR processed by the OCR control unit 15 using the OCR dictionary, and the file management unit 11 determines a management method of the received image based on the OCR processing result.

  Therefore, it is possible to improve the character recognition rate of the OCR process by selecting an OCR dictionary suitable for the characters of the facsimile received image, and to manage the received image more appropriately.

  The received image area to be subjected to the OCR process includes a case in which only a specific image area in which transmission source information such as TTI (Transmitter Terminal Identification) such as transmission date / time, transmission source, and number of pages is described is subjected to OCR processing, and reception As shown in FIG. 10, as in the case of performing the OCR processing on the entire region of the image and the case of performing the OCR processing on only other image regions excluding the specific image region in which the transmission source information such as TTI is described, The area for OCR processing may be set by the transmission source (destination) of facsimile reception to perform OCR processing. In this case, in association with the transmission source information, as described above, the OCR processing range is registered for each transmission source information in the transmission source information corresponding use dictionary selection table for registering the OCR processing dictionary. That is, in facsimile communication, on the transmission side, TTI information such as the transmission date and time, the transmission source, and the number of pages is added to the front end area of the image information of the transmission original and transmitted, and the reception side (the composite apparatus 1 of this embodiment). ) Records the image information to which the TTI information is added on the sheet, so that the TTI information is recorded in the leading end area of the received document. An area to which the TTI information added to the received image is added is set as a specific image area. In FIG. 10, processing steps similar to those in FIG. 3 are denoted by the same step numbers, and the description thereof is simplified. Further, FIG. 10 is applied to the case where the OCR dictionary is selected based on the line type, as in FIGS. 8 and 9, but the method based on the country code, the number display information, and the dial-in number based on the CSI. The same can be applied to such cases.

  When the composite apparatus 1 selects the OCR dictionary and the OCR processing area based on the line type in which facsimile reception has occurred, the OCR control unit 15 uses the OCR dictionary and the OCR processing area corresponding to the line type and the line type. Is stored (hereinafter referred to as a line type corresponding OCR area-used OCR dictionary selection table), and this line type corresponding OCR area-used OCR dictionary selection table is stored in a plurality of devices connected to the composite apparatus 1. The line type, the OCR dictionary, and the OCR processing area are associated with each other, and according to the operation from the display / operation control unit 3 by the user, the settings are registered as appropriate, or a table of changed contents is registered. As described above, this OCR processing area excludes the specific image area in which the transmission source information such as TTI is described, the entire area of the received image, and the specific image area in which the transmission source information such as TTI is described. The area is designated as in the image area of FIG.

  When the communication control unit 5 detects ringing in the state where the line type corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, the multifunction device 1 permits the job control unit 4 to accept G3 reception. In response, the facsimile reception protocol is started (step S101).

  In the composite apparatus 1, when the communication control unit 5 starts the facsimile protocol, the multi-line exclusion control unit 20 recognizes the line type indicating which line is the reception line, and sets the recognized line type to the job control unit. 4 is notified (step S501). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 ends all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 sends the line passed from the communication control unit 5 to the OCR control unit 15. The type is notified and a request for OCR processing is made. The OA control unit 15 refers to the line type corresponding OCR area-used OCR dictionary selection table based on the line type passed from the job control unit 4, and sets the OCR dictionary corresponding to the line type to the OCR of the facsimile received image. A dictionary preset as a dictionary to be used for processing is switched (step S502).

  The OCR control unit (OCR area selecting means) 15 further refers to the line type corresponding OCR area-used OCR dictionary selection table based on the line type passed from the job control unit 4 and corresponds to the OCR corresponding to the line type. A processing area (OCR processing range) is determined (step S503), and the determined image area (OCR processing range) of the facsimile reception image data stored in the file management unit 11 using the selected OCR dictionary is used. ) Is subjected to OCR processing (step S504).

  The OCR control unit 15 performs output of the received image, for example, folder, computer, facsimile transfer, e-mail transmission, etc. based on the result of character recognition by performing OCR processing on the determined OCR processing area of the received image. To decide.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted characters (OCR extracted characters) and the image file ID to the job control unit 4, and the job control unit 4 receives the received characters and image file. The ID is notified to the TIFF / PDF creation control unit 21. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 into a Tiff or PDF, along with the characters recognized by the OCR processing received from the job control unit 4 The file is transferred to the file management unit 11. The file management unit 11 manages the data file based on the received OCR recognition result character for the received image file (step S108).

  As described above, the composite apparatus 1 according to the present embodiment uses one or both of the entire received image and the TTI area as the OCR processing target area by the OCR control unit 15 based on the transmission source related information recognized by the OCR process. Selected.

  Accordingly, it is possible to appropriately determine a management method for received images, and to improve the usability of character information subjected to OCR processing.

  In this case, in the composite apparatus 1, the OCR processing control unit 15 performs OCR processing on the entire area of the received image, and converts the OCR processing data of the entire received image into the OCR processing data in the TTI area and the CR processing data other than the TTI area. The separated OCR processing data may be used as appropriate.

  In this way, it is possible to further improve the usability of the processing data for the OCR processing.

  Further, in the OCR processing of the received image, as shown in FIG. 11, the recognition rate may be improved by changing the orientation of the image and performing OCR processing in each direction. In FIG. 11, processing steps similar to those in FIGS. 3 and 10 are given the same step numbers to simplify the description. Further, FIG. 11 is applied to the case where the OCR dictionary is selected based on the line type and the OCR range is selected and the OCR processing is performed as in FIG. The present invention can be similarly applied to a method based on information and a dial-in number.

  When the composite apparatus 1 selects the OCR dictionary and the OCR processing area based on the line type in which facsimile reception has occurred, the OCR control unit 15 uses the OCR dictionary and the OCR processing area corresponding to the line type and the line type. Is stored (hereinafter referred to as a line type corresponding OCR area-used OCR dictionary selection table), and this line type corresponding OCR area-used OCR dictionary selection table is stored in a plurality of devices connected to the composite apparatus 1. The line type, the OCR dictionary, and the OCR processing area are associated with each other, and according to the operation from the display / operation control unit 3 by the user, the settings are registered as appropriate, or a table of changed contents is registered. As described above, this OCR processing area excludes the specific image area in which the transmission source information such as TTI is described, the entire area of the received image, and the specific image area in which the transmission source information such as TTI is described. The area is designated as in the image area of FIG.

  When the communication control unit 5 detects ringing in the state where the line type corresponding use OCR dictionary selection table is registered in the OCR control unit 15 as described above, the multifunction device 1 permits the job control unit 4 to accept G3 reception. In response, the facsimile reception protocol is started (step S101).

  In the composite apparatus 1, when the communication control unit 5 starts the facsimile protocol, the multiple line exclusive control unit 20 recognizes the line type indicating which line is the reception line, and performs job control on the recognized line type. Notification is made to the unit 4 (step S501). In addition, when the communication control unit 5 performs the facsimile procedure and receives the facsimile image data from the transmission source, the communication control unit 5 passes the received image data to the file management unit 11, which temporarily stores the received image data. The job control unit 4 is notified of the image file ID of the image data file of the data (step S103).

  When the communication control unit 5 ends all the facsimile reception protocols, the job control unit 4 notifies the job control unit 4 of the end (step S104), and the job control unit 4 sends the line passed from the communication control unit 5 to the OCR control unit 15. The type is notified and a request for OCR processing is made. The OA control unit 15 refers to the line type corresponding OCR area-used OCR dictionary selection table based on the line type passed from the job control unit 4, and sets the OCR dictionary corresponding to the line type to the OCR of the facsimile received image. A dictionary preset as a dictionary to be used for processing is switched (step S502).

  Further, the OCR control unit 15 refers to the line type corresponding OCR area-used OCR dictionary selection table based on the line type passed from the job control unit 4 and refers to the OCR processing area (OCR processing range corresponding to the line type). ) (Step S503), and using the selected OCR dictionary, OCR processing is performed on the determined image area in the facsimile reception image data stored in the file management unit 11 (step S504). ).

  When the OCR process is performed, the OCR control unit 15 calculates a character recognition rate in the OCR process (step S601), and checks whether the calculated character recognition rate is improved from the previous time. The improved character recognition rate is stored in an internal memory or the like, and the image in the direction is transferred to the file management unit 11 (step S602). Since the first OCR processing has just been performed, the previous character recognition rate is not stored in the internal memory and cannot be compared. Therefore, the current character recognition rate and the recognized character and number of characters are stored in the internal memory. Then, the image data in the received direction is transferred to the file management unit 11.

  When the OCR control unit 15 saves the character recognition rate and the recognized characters and the number of characters in the internal memory, the OCR control unit 15 sets the number of times the OCR processing is set in advance (in this embodiment, character recognition rates for all the vertical and horizontal directions). It is checked whether it has been performed four times (step S603). When the OCR processing is not performed four times, the image is rotated by 90 degrees (step S604), and the process returns to step S504, and the image rotated by 90 degrees is performed. Then, the next OCR process is performed to compare the character recognition rate with the previous character recognition rate, the necessary character recognition rate, the number of characters and the number of characters are stored, and the necessary rotated image data is passed to the protocol management unit 11 The process is repeatedly executed in the same manner as described above until the OCR process is performed four times in step S603 (steps S504, S601 to S604).

  When the OCR process is completed four times in step S603, the OCR control unit 15 displays the character and the number of characters with the highest character recognition rate stored in the internal memory and the image in the direction with the highest character recognition rate. The specified character recognition rate is the highest by passing the specified information to the file management unit 11 or by reducing the processing that the file management unit 11 always updates the previous image data with the image data passed from the OCR control unit 15. Only the image data is left in the file management unit 11.

  Then, the OCR control unit 15 performs OCR processing on the determined OCR processing area of the received image, and based on the character recognition result of the OCR processing having the highest character recognition rate, the output destination of the received image, for example, Folder, computer, facsimile transfer, e-mail transmission, etc.

  The OCR control unit 15 performs OCR processing to extract characters, notifies the extracted characters (OCR extracted characters) and the image file ID to the job control unit 4, and the job control unit 4 receives the received characters and image file. The ID is notified to the TIFF / PDF creation control unit 21. The Tiff / PDF creation control unit 21 converts the received image corresponding to the image file ID received from the job control unit 4 into a Tiff or PDF, along with the characters recognized by the OCR processing received from the job control unit 4 The file is transferred to the file management unit 11. The file management unit 11 manages the data file based on the received OCR recognition result character for the received image file (step S108).

  As described above, the composite apparatus 1 according to the present embodiment changes the OCR processing direction of the received image up, down, left, and right, performs the OCR processing by the OCR control unit 15, determines the OCR processing result in each direction, and performs the OCR processing. The received image output management method is determined based on the result determination result.

  Therefore, it is possible to manage the received image and use the received image by using the OCR processing result with the best OCR recognition rate, and it is possible to further improve the usability.

  The invention made by the present inventor has been specifically described based on the preferred embodiments. However, the present invention is not limited to that described in the above embodiments, and various modifications can be made without departing from the scope of the invention. It goes without saying that it is possible.

  The present invention can be used for an image processing apparatus, an image processing method, an image processing program, and a recording medium for managing received images by performing OCR processing on images received by facsimile.

1 is a block configuration diagram of a composite apparatus to which an embodiment of the present invention is applied. The figure which shows an example of a country code corresponding | compatible use OCR dictionary selection table. The flowchart which shows the facsimile reception image management process accompanied by the OCR dictionary selection process based on a country code. The figure which shows an example of the use OCR dictionary selection table corresponding to number display information. The flowchart which shows the facsimile reception image management process accompanied by the OCR dictionary selection process based on number display information. The figure which shows an example of the use OCR dictionary selection table corresponding to a dial-in number. 6 is a flowchart showing facsimile received image management processing with OCR dictionary selection processing based on dial-in numbers. The figure which shows an example of a line classification corresponding use OCR dictionary selection table. 9 is a flowchart showing facsimile reception image management processing accompanied by OCR dictionary selection processing based on line type. The flowchart which shows the facsimile reception image management process accompanied by the OCR dictionary and OCR range selection process based on a line classification. 9 is a flowchart showing facsimile reception image management processing accompanied by character recognition rate determination processing by image direction change.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Composite apparatus 2 Main control part 3 Display / operation control part 4 Job control part 5 Communication control part 6 Compression / decompression control part 7 Plotter control part 8 Scanner control part 9 Destination management part 10 Internal switch and own terminal registration data part 11 File management Unit 12 network control unit 13 report control unit 14 partner CSI control unit 15 OCR control unit 16 number display control unit 17 OCR dictionary unit 18 dial-in control unit 19 image direction determination control unit 20 multi-line exclusive control unit 21 Tiff / PDF creation Control unit 22 bus

Claims (10)

  In an image processing apparatus connected to a predetermined line, receiving an image by facsimile according to at least a transmission source and a predetermined facsimile control procedure, and managing the received image, the transmission source specifying the transmission source from the communication procedure of the facsimile communication Transmission source information acquisition means for acquiring related information, OCR dictionary storage means for storing a plurality of OCR dictionaries, and OCR dictionary selection means for selecting one OCR dictionary from the plurality of OCR dictionaries based on the transmission source related information And OCR processing means for OCR processing a predetermined area of the received image using the selected OCR dictionary, and received image management means for determining a management method for the received image based on the OCR processing result. An image processing apparatus comprising:   The transmission source information acquisition means includes, as the transmission source related information, a country code of a CSI signal that is a facsimile control signal, number display information sent through the line, and a received dial-in number among a plurality of stored dial-in numbers. The image processing apparatus according to claim 1, wherein at least one of the number and the received line type of a plurality of connected lines is acquired.   3. The image processing apparatus according to claim 1, further comprising selection setting means for selecting and setting an OCR dictionary that is selected by the OCR dictionary selection means in correspondence with the transmission source related information. Image processing device.   The image processing apparatus includes an OCR region selection unit that selects one or both of the entire received image and the TTI region as an OCR processing target region by the OCR processing unit based on the transmission source related information. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus.   The image processing apparatus determines an OCR processing direction control unit that causes the OCR processing unit to perform OCR processing by changing the OCR processing direction of the received image up, down, left, and right, and an OCR processing result by the OCR processing unit in each direction. 5. The OCR processing result determination unit and the received image management unit that determine the output management method of the received image based on the OCR processing result determination result in each direction. An image processing apparatus according to any one of the above.   This is an image processing method for performing facsimile reception in accordance with a predetermined facsimile control procedure with a transmission source connected to a predetermined line, receiving a facsimile image sent from the transmission source, and managing the received image received. A transmission source information acquisition processing step for acquiring transmission source related information for specifying the transmission source from the control procedure of the facsimile communication, and a plurality of OCR dictionaries stored in the OCR dictionary storage means based on the transmission source related information. An OCR dictionary selection processing step for selecting one OCR dictionary, an OCR processing step for OCR processing of a predetermined area of the received image using the selected OCR dictionary, and the received image based on the OCR processing result. And a received image management processing step for determining a management method.   In the transmission source information acquisition processing step, as the transmission source related information, the country code of the CSI signal of the facsimile control signal, the number display information transmitted through the line, and the received dial-in number among the stored dial-in numbers. The image processing method according to claim 6, wherein at least one of the received line type is acquired from the number and a plurality of connected lines.   The image processing method includes an area selection processing step of selecting either a TTI area or an image area other than the TTI area as an OCR processing target area in the received image, and the OCR processing step includes the area selection processing step. 8. The image processing method according to claim 6, wherein the region selected in the step is subjected to OCR processing.   Facsimile reception processing for receiving a facsimile image sent from the transmission source by performing facsimile reception according to a predetermined facsimile control procedure with a transmission source connected to a computer via a predetermined line, and the processing procedure of the facsimile reception processing Source information acquisition processing for acquiring source-related information for specifying the source, and OCR dictionary selection for selecting one OCR dictionary from a plurality of OCR dictionaries stored in the OCR dictionary storage unit based on the source-related information Processing, OCR processing for performing OCR processing on a predetermined area of the received image using the selected OCR dictionary, and received image management processing for determining a management method for the received image based on the OCR processing result. An image processing program that is executed.   A computer-readable recording medium on which the image processing program according to claim 9 is recorded.

Images