JP2012053519A - Image processing apparatus and image processing system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing apparatus capable of confirming readability of a character string of an image which is optically read from a document.SOLUTION: An image processing apparatus comprises: an image acquisition unit; a storage unit; a character recognition unit; a comparison unit; and a readability determination unit. The image acquisition unit acquires an image of a document. The storage unit stores therein a character string candidate specific for the document, for each type of the document. The character recognition unit performs a character recognition process by using a character recognition dictionary set in advance for the image acquired by the image acquisition unit to obtain a character string. The comparison unit compares the character string obtained by the character recognition unit and the character string candidate for each type of the document in the storage unit. The readability determination unit determines readability of the document and a type of the document in which the image is acquired by the image acquisition unit, by whether or not a degree of accordance/discordance between the character string and the character string candidate for each type of the document, which are compared by the comparison unit, exceeds a reference value set in advance.

Description

  Embodiments described herein relate generally to an image processing apparatus and an image processing system.

  2. Description of the Related Art Conventionally, an image reading apparatus such as a flatbed scanner has been used to digitize a document such as a document.

  In recent years, with the improvement of camera performance (higher pixels) of mobile terminals such as digital cameras and camera-equipped mobile phones, mobile terminals and the like are being used for digitizing documents.

  In order for a person to read a document on which characters are written with a mobile terminal and read an image of the document, it is important that the image read with the mobile terminal has sufficient legibility. For this reason, it is necessary to construct a technique for more accurately checking the presence or absence of legibility.

  Although several techniques for determining the legibility of an image have already been disclosed, it is difficult to determine whether or not a person can actually read because the legibility is judged from the character size of the document.

JP 2005-26597 A

  Also, if the source document is a copy, for example, a copy document, or if the source document itself is crushed due to the effect of copying, the image read on the mobile terminal It is not clear whether the written characters can actually be read correctly.

  An object of the present invention is to provide an image processing apparatus and an image processing system capable of confirming the legibility of a character string of an image optically read from a document.

  The image processing apparatus according to the embodiment includes an image acquisition unit, a storage unit, a character recognition unit, a comparison unit, and a legibility determination unit. The image acquisition unit acquires an image of a document. The storage unit stores character string candidates specific to the document for each type of the document. The character recognition unit performs a character recognition process on the image acquired by the image acquisition unit using a preset character recognition dictionary to obtain a character string. The comparison unit compares the character string obtained by the character recognition unit with a character string candidate for each type of document in the storage unit. The readability determination unit is configured to determine whether or not the degree of matching / mismatching between the character string candidate and the character string for each document type compared by the comparison unit exceeds a preset reference value. The type of the document from which the image is acquired and the legibility of the document are determined.

1 is a diagram illustrating a schematic configuration of an image processing system according to a first embodiment. It is a figure which shows the structure of a portable terminal. It is a figure which shows the structure of a server. It is a flowchart which shows operation | movement of this image processing system. It is a figure which shows the procedure list screen of a portable terminal. It is a figure which shows the document photography screen of a portable terminal. It is a figure which shows the example of the document image determined with a legibility. It is a figure which shows the example of the document image determined with no legibility. It is a figure which shows the structure of 2nd Embodiment of an image processing apparatus. It is a figure which shows the QR code recognition screen of a portable terminal. It is a figure which shows the structure of 3rd Embodiment of an image processing apparatus. It is a figure which shows the sending screen of the confirmation document of a portable terminal. It is a figure which shows the transmission mail preparation screen of a portable terminal. It is a figure which shows the attached data selection menu screen of a portable terminal.

Hereinafter, embodiments will be described in detail with reference to the drawings.
(First embodiment)
FIG. 1 is a diagram illustrating the configuration of the image processing apparatus according to the first embodiment.
As shown in FIG. 1, the image processing system of the first embodiment is configured by connecting a mobile terminal 1 and a server 3 via a wireless base station 2a and a network 2 such as the Internet. The mobile terminal 1 is a mobile phone with a camera, for example, and is carried by an insurance contractor. The server 3 is arranged, for example, in an insurance company or an insurance contract examination company.

  As shown in FIG. 2, the mobile terminal 1 includes a display unit 9, a memory 10, a key operation unit 11, an image acquisition unit 12, a procedure identifier assignment unit 13, an image file encryption unit 14, a wireless communication unit 15, an image discard unit. 16, a control unit 17 and the like.

  The display unit 9 is, for example, a liquid crystal display. The memory 10 is used as a work area for processing performed by each unit. The memory 10 stores an image acquired by the image acquisition unit 12. The key operation unit 11 is an operation button (switch) such as a numeric keypad, an arrow key, and an enter key, for example, and accepts a document type selected by the user from among a plurality of document types displayed on the display unit 9. The key operation unit 11 functions as a document designation unit that designates a document from which an image is acquired by the image acquisition unit 12.

  The image acquisition unit 12 is a CCD camera, for example, and images a document as a subject to acquire a document image. The performance (resolution) of the CCD camera is preferably 2 million pixels (65 dpi) or more, for example.

  When the document acquisition is performed by the image acquisition unit 12, the determination key of the key operation unit 11 functions as an imaging button. The procedure identifier assigning unit 13 assigns an identifier (identification information) indicating the type of document accepted by the key operation unit 11 to the image. That is, the procedure identifier giving unit 13 gives identification information indicating the type of document designated (selected) by the key operation unit 11 to the image acquired by the image acquisition unit 12.

  The image file encryption unit 14 encrypts an image to be transmitted to which an identifier indicating the type of document is assigned. The wireless communication unit 15 transmits the image encrypted by the image file encryption unit 14. That is, the wireless communication unit 15 functions as a transmission unit that transmits an image of a document with an identifier to the server 3. The image discard unit 16 deletes (discards) the image in the memory 10 after transmitting the image.

  As shown in FIG. 3, the server 3 includes a communication unit 31, an image decoding unit 32, a procedure specifying unit 33, a document name specifying unit 34, a document keyword extracting unit 35, a character recognizing unit 36, a recognition result keyword comparing unit 37, reading. And a document type determination unit 38, a document edge detection unit 39, a protrusion determination unit 40, a storage unit 42, a master DB 43, and the like.

  The master DB 43 is a database provided in the large-capacity storage device of the server 3 such as a hard disk device. The master DB 43 stores, for example, information on insurance procedures (for example, a list to be included in the procedure list), information on insurance contractors, and the like. Lists include, for example, “confirmation / change of contract”, “change of insurance premium transfer account”, “reissue of insurance deduction certificate”, “change of surname / name, contractor, change of recipient”, “request for hospitalization benefits” , "Death insurance claim". Of these, for example, for “Inpatient Benefit Claim”, the procedure name is “Request for Benefit”, detailed information on the claim for benefits (necessary documents: “Receipt of Medical Institution”, “Details of Medical Report” "... etc.) is stored.

  In addition, if the type of document is “Receipt of medical institution”, for example, “receipt”, “receipt”, “total” “Yen”, “¥”, and the like are stored. As described above, the master DB 43 functions as a storage unit that stores character string candidates specific to a document for each type of document.

  The master DB 43 stores insurance procedures in association with document identifiers added to images. For example, “contract details confirmation / change” is associated with identifier “0001”, “insurance fee transfer account change” is associated with identifier “0002”, and “insurance deduction certificate” is associated with identifier “0003”. "Reissue" is associated, and "Inpatient Benefit Claim" is associated with the identifier "0004".

  The communication unit 31 receives an image transmitted from the mobile terminal 1 through the network 2 and stores it in the storage unit 42. Further, the communication unit 31 functions as a determination result notification unit that sends the image readability determination result determined by the legibility and document type determination unit 38 to the mobile terminal 1 through the network 2. The image decoding unit 32 composites the image received by the communication unit 31.

  The procedure specifying unit 33 specifies the procedure from the identifier given to the image. The document name identification unit 34 identifies some candidate documents (for example, a medical institution receipt, a “medical report specification”, etc.) required in the procedure. The name specifying unit 44 specifies the name of the sender (contractor) from the source address of the received electronic mail. The contract information of the master DB 43 is used for specifying these.

  The document keyword extraction unit 35 uses characters (yen, ¥, etc.) set in advance for candidate documents (“receipt of medical institution”, “medical report specification”, etc.) necessary for the specified procedure and Character strings (total, receipt, receipt, etc.) are read from the master DB 43.

  The character recognition unit 36 performs character recognition on the image and generates a pair of an image of each character and text. The character recognizing unit 36 generates a character or a character string obtained by dividing a line of continuous text of each character of the recognition result into a unit of a phrase or a word. That is, the character recognition unit 36 performs a character recognition process on the image received by the communication unit 31 using a preset character recognition dictionary (not shown) to obtain a character or a character string.

  The recognition result keyword comparing unit 37 compares the character string obtained as a result of character recognition by the character recognizing unit 36 with the character string extracted by the document keyword extracting unit 35, and determines a match / mismatch. . That is, the recognition result keyword comparison unit 37 compares the character string obtained by the character recognition unit 36 with the character string candidates for each document type in the master DB 43.

  The legibility and document type determination unit 38 obtains the gradation change rate of the image, determines the focus state (whether it is in focus) by comparing it with a preset threshold value, and reads the document image. Judgment (readability) is determined.

  Further, the legibility and document type determination unit 38, as a result of the comparison by the recognition result keyword comparison unit 37, is a candidate having a large number of matching character strings (document keywords) (for example, medical report specifications and medical institution receipts). Among them, for example, the receipt of the medical institution) is specified by referring to the master DB 43. That is, the legibility and document type determination unit 38 determines whether or not the degree of match / mismatch between the character string candidate and the character string for each document type compared by the recognition result keyword comparison unit 37 exceeds a preset reference value. The type of document and the readability of the document are determined based on the above.

  The document edge detection unit 39 detects a document edge line in the image. The protrusion determination unit 40 determines whether or not the document edge line protrudes from the photographing range of the CCD camera of the mobile terminal 1.

  The determination result notification unit 41 reads a fixed message according to the protrusion determination result from the protrusion determination unit 40 from the storage unit 42 and notifies the mobile terminal 1 from the communication unit 31. That is, the determination result notification unit 41 notifies the portable terminal 1 of the document readability determination result determined by the readability and document type determination unit 38.

  The storage unit 42 is a memory, for example, and stores an image received by the communication unit 31. The storage unit 42 stores a standard message corresponding to the determination result of the protrusion determination unit 40.

  When the determination result is “pass”, as the notification information indicating that the document image has been normally received, a fixed message such as “The certificate image you received has been successfully received” is stored in the storage unit 42. Is remembered.

  In addition, if the judgment result is “Fail”, the notice information that cannot be read is “[Important] Please re-shoot / send the official certificate. The photo you sent earlier was not accepted. Reason: Text The column could not be read. Please note: Sorry for your inconvenience, but please re-shoot and send. "

Next, the operation of the image processing system according to the first embodiment will be described with reference to FIGS.
In the case of the first embodiment, when a user operates a key of the mobile terminal 1 and starts up procedure application software (hereinafter referred to as “procedure application”) that is installed in the mobile terminal 1 in advance (FIG. 4). Step S101), a screen 51 as shown in FIG. It is assumed that the procedure application is activated by operating a predetermined key (such as an application key) of the mobile terminal 1.

  In this screen 51, as the “procedure list”, the master DB 43 list (“contract details confirmation / change”, “insurance transfer account change”, “insurance deduction certificate reissue”, “rename / name, contractor” Change, payee change, hospitalization benefit claim, death insurance claim)) are displayed as selection menus.

  When the user selects “hospital benefit claim” from the key operation unit 11 (step S102), the image acquisition unit 12 captures a document for displaying an imaging frame 52 (camera field of view) as shown in FIG. The screen 53 is displayed (step S103), and the image of the document is photographed by the image acquisition unit 12 when the user presses the image capture button so that the document is placed in the image capture frame 52 (step S104). An identifier indicating the type of the document that has been assigned is assigned to the image file name by the procedure identifier assigning unit 13 (step S105) and stored in the memory 10.

  Further, the image in the memory 10 is encrypted by the image file encryption unit 14 (step S106), and then transmitted to the server 3 by the wireless communication unit 15 (step S107).

  After the image is transmitted to the server 3 by the wireless communication unit 15, the image discarding unit 16 discards the image held in the memory 10 (step S108).

  On the other hand, in the server 3, the encrypted image transmitted from the mobile terminal 1 through the network 2 is received by the communication unit 31 and stored in the storage unit 42.

  Then, the image decryption unit 32 reads and decrypts the encrypted image in the storage unit 42 (step S201), and stores the image in the storage unit 42.

  Subsequently, the procedure specifying unit 33 specifies the contents of the procedure by searching the master DB 43 using the identifier given to the file name of the decrypted image as a keyword (step S202).

  When the contents of the procedure are specified, the document name specifying unit 34 searches the master DB 43 by the procedure (step S203), and specifies a document necessary for the procedure.

  As in this example, if the procedure is, for example, payment of hospitalization benefits, the required document is “medical institution receipt” or “medical remuneration statement” based on the identifier added to the image file name.

  When the document is specified, the document keyword extraction unit 35 reads the document keyword (character string) of the specified document from the master DB 43 (step S204), and passes it to the recognition result keyword comparison unit 37. In the case of “Receipt of medical institution”, “Receipt”, “Receipt”, “Total”, “Yen”, “¥”, etc. are registered in the master DB 43 in advance as master keywords. Read from DB43.

  Further, the character recognition unit 36 reads an image from the storage unit 42, recognizes the character (step S205), and passes the character string obtained as the recognition result to the recognition result keyword comparison unit 37.

  The recognition result keyword comparison unit 37 compares the character string (character string candidate) passed from the document keyword extraction unit 35 with the character string of the character recognition result passed from the character recognition unit 36 (step S206). The degree of matching / mismatching between the column candidate and the character string, that is, the matching degree between the character strings is determined.

  When the character string matching degree is higher than a preset threshold value as a result of comparison by the recognition result keyword comparison unit 37, the legibility and document type determination unit 38 has image legibility and document type ( For example, a medical institution's receipt ") is specified (step S207). The threshold is set to 80%, for example.

In addition, the legibility and document type determination unit 38 obtains the gradation change rate of the image, determines whether or not the image is in focus based on whether or not the gradation change rate of the obtained image exceeds a preset threshold. The focus pass / fail judgment result is included in one of the legibility judgment results.
Subsequently, the document edge detection unit 39 detects a document edge line (outer edge of the document) in the image (step S208).

  When the document edge line is detected, the protrusion determination unit 40, as shown in FIG. 7, the document edge line 72 of the detected original image 71 is set to a predetermined document image interpretation allowable range (inside and Whether or not it protrudes from the interpretation range due to the inclination of the document is determined depending on whether or not it is in contact with the two outer reference lines 73 and 74) (step S209).

  For example, as shown in FIG. 7, if the document edge line 72 is not in contact with the two reference lines 73 and 74 on the inner side and the outer side, the protrusion determination unit 40 can read the image of the document, that is, there is a problem in legibility. It is determined that there is no “pass”. As shown in FIG. 8, if the document edge line 72 is in contact with at least one of the two reference lines 73 and 74 on the inner side and the outer side, the protrusion determination unit 40 cannot read the image of the document. That is, it is determined as “Fail” which has a problem in legibility.

  The protrusion determination unit 40 determines whether the outer edge of the document detected by the document edge detection unit 39 protrudes from the image, and includes the protrusion determination result in one of the legibility determination results.

  The determination result notification unit 41 reads a fixed message corresponding to the determination result by the protrusion determination unit 40 from the storage unit 42 and notifies the portable terminal 1 from the communication unit 31 (step S210). The image after the determination is transferred from the storage unit 42 to a non-volatile storage unit such as a hard disk device and stored by the control unit 30 (step S211).

  As described above, according to the first embodiment, the file name of the document image taken by the portable terminal 1 is attached to the identifier indicating the document type and transmitted to the server 3, and the server 3 receives the document from the portable terminal 1. The type of document is determined by checking the degree of coincidence between the character string obtained by performing character recognition on the image and the character string candidates for identifying the document indicated by the file name identifier of the image. Has the legibility as a document, and at the same time, it can be confirmed that the image is an image of a document necessary for the procedure, and a highly reliable confirmation result can be obtained.

  In addition, by detecting the outer edge shape of the subject (document) in the acquired image, determining whether the ratio of the document to the subject area is acceptable, and whether or not it is protruding from the subject area, and notifying the result, shooting failure It can contribute to the efficiency of time recovery and prevention of backtracking work.

  Furthermore, by confirming whether or not the entire subject is in focus by confirming the gradation change rate in the image, it is possible to confirm not only the character string but also the portion of the picture or photograph (readability).

  In the above embodiment, the case where the user selects a desired “procedure” on the screen 51 of the mobile terminal 1 has been described. However, depending on the “procedure”, a plurality of documents may be required. A process is required in which candidates are given and narrowed down from them.

Therefore, after the user selects a desired “procedure” on the screen 51 of the portable terminal 1, the necessary document candidates are enumerated, and the user selects a document to be sent in the enumerated list. The document to be imaged is fixed, and the processing for narrowing down the document type on the server 3 side becomes unnecessary.
(Second Embodiment)
Next, a second embodiment will be described with reference to FIGS. FIG. 9 is a diagram illustrating a configuration of a portable terminal of the image processing system according to the second embodiment. In addition, the same code | symbol is attached | subjected to the structure similar to 1st Embodiment, and the description is abbreviate | omitted.

  As shown in FIG. 9, the mobile terminal 1 of the second embodiment includes a QR code recognition unit 18. The QR code recognizing unit 18 recognizes a QR code including identification information (identifier) of a document or procedure to be transmitted from the user. That is, the QR code recognizing unit 18 obtains information on the document from which the image is acquired by the image acquiring unit 12 from the QR code.

  In the case of the second embodiment, a QR code for each procedure or each document is printed on paper or the like in advance, and the QR code recognition unit 18 displays a QR code recognition screen 81 as shown in FIG. By capturing and recognizing a QR code 82 indicating a desired document or procedure printed on the document, identification information (identifier) for identifying the document or procedure is acquired and added as a part of the file name of the document image. .

  As for the file name of the document image, the default name of the portable terminal 1 is automatically renamed or manually renamed by “title editing”.

  After obtaining the document image file, the document image file is encrypted by the image file encryption unit 14 and uploaded to the server 3 from the wireless communication unit 15 through the network 2 by a transmission operation by the user. Then, after uploading to the server 3, the image file held in the memory 10 is discarded by the image discarding unit 16.

  In the server 3, the image decryption unit 32 decrypts the encrypted file received from the network 2. The document type is derived from the decrypted image file name, the document keyword (character string candidate) included in the document is read from the master DB 43, the image file is recognized, the result of the character recognition and the document keyword ( Check for match / mismatch with (candidate character string).

  When a character string of a character recognition result that matches a document keyword (character string candidate) is detected, the image is readable and the image file is a document indicated by the identifier assigned to the name. I can confirm that.

  On the other hand, if the character string of the character recognition result that matches the document keyword (character string candidate) is not detected, the image is not readable or the received image file has the name. It can be confirmed that it is not the document indicated by the identifier.

In addition to this judgment of legibility, processing to detect the edge of the document paper in the image and check whether the whole document is included in the image (whether the document does not protrude from the image) (extrusion judgment) May be included)
As described above, according to the second embodiment, by providing the QR code recognition unit 18 and recognizing the QR code 82 indicating the document or procedure, in addition to the effects of the first embodiment, the designation of the document or procedure ( Input) can be performed easily and reliably.
That is, by acquiring the character string information included in the image to be held together with the photographed image from the QR code, it is possible to reduce labor and mistakes due to key input.
(Third embodiment)
Next, a third embodiment will be described with reference to FIGS. FIG. 11 is a diagram illustrating a configuration of the mobile terminal 1 of the image processing system according to the third embodiment. In addition, the same code | symbol is attached | subjected to the structure similar to 1st Embodiment and 2nd Embodiment, and the description is abbreviate | omitted.

  The mobile terminal 1 according to the third embodiment includes an address link input unit 19 as shown in FIG. This address link input unit 19 sets a mail address link different for each document type as a selection item of the procedure, and when the selection item is selected, displays the outgoing mail creation screen and displays the destination address on the outgoing mail creation screen. Enter the linked email address in the field.

  As shown in FIG. 12, when the user selects a selection item such as confirmation / change of contract contents from the procedure list screen 51 shown in FIG. 5, the address link input unit 19, as shown in FIG. 12, A screen 83 titled “Send Identity Verification Document” (hereinafter referred to as “Send Confirmation Document Screen 83”) is displayed.

  The confirmation document sending screen 83 is provided with two selection items such as “confirm contract contents” and “change contract contents”, a check box for consent, and link buttons for “return”, “input”, and “menu”. It has been. Different selection destination email addresses are linked to the two selection items.

  In the master DB 43, for example, xx0@xxxx.co.jp is stored as a reception address of the server 3 for the selection item “contract content confirmation”, for example, and for the selection item “contract content change”. As the reception address of the server 3, for example, a procedure-email address correspondence table storing xx1@xxxx.co.jp and the like is provided. The server 3 has a received mail account for each procedure, and the contents of the procedure can be determined based on the received mail account from which the e-mail is received.

  Here, for example, when the selection item “contract contents change” is selected, the check box of “agreement ...” is checked, and the link button of “input” is operated, the address link input unit 19 is as shown in FIG. Then, a send mail creation screen 84 with xx1@xxxx.co.jp inserted in the destination is displayed.

  When the item “Attachment” is selected on the outgoing mail creation screen 84, the address link input unit 19 displays an attached data selection menu screen 85 as shown in FIG.

  Here, when the user selects the “photo shooting” item 86, the document shooting screen 53 provided with the imaging frame 52 shown in FIG. 6 is displayed, and the imaging button is set so that the user puts the document in the imaging frame 52. By pressing, an image of the document is photographed, and an e-mail attached with the image file of the photographed document is transmitted to the server 3.

  In this case, the communication unit 31 of the server 3 is set with the receiving address of the server 3 set for each document, and the communication unit 31 is attached to the e-mail according to the receiving address at which the e-mail is received. Can identify the type of document image. In the case of this example, in the master DB 43, an identifier (such as a contractor number) for specifying the name or individual of the user (contractor) and the user's e-mail address (source address) are stored in advance in association with each other. Keep it.

  Hereinafter, the operation of the third embodiment will be described. First, the outline operation will be described. In the case of the second embodiment, when transmitting an image of a document necessary for the procedure from the mobile terminal 1, the user selects the document to be transmitted, and the electronic server of the transmission destination server set for each document type is selected. A transmission mail creation screen (screen for electronic mail transmission) with the mail address as the destination is displayed, and an electronic mail attached with an image file acquired by a normal captured image attachment operation is transmitted to the server 3.

  In the server 3, when the communication unit 31 receives the e-mail and acquires the attached image file, the master DB 43 is searched using the transmission source address of the received e-mail as a key, and the sender ( Retrieves the identifier (identity of the contractor) or individual (contractor number, etc.), and obtains the identifier identifying the sender's name or individual from the result of character recognition of the image file attached to the email, Compare and match each other.

  If a character string that matches the name and identifier read from the master DB 43 is found from the character recognition result, it can be confirmed that the image has readability and is a document related to the sender of the e-mail.

  On the other hand, if no matching character string is found from the character recognition result, it can be confirmed that the image is not readable or is not a document related to the sender of the e-mail.

  In addition to the determination of legibility as described above, as described in the first embodiment, the gradation change rate of the document image is obtained, the document edge line (edge) is detected from the image, and the protrusion determination process is performed. This makes it possible to determine the legibility more reliably.

Next, the detailed operation of the third embodiment will be described.
From the “procedure” selected on the procedure list screen 51 of the portable terminal 1, the confirmation document sending screen 83 (see FIG. 12) is displayed, and the image acquisition unit 12 shoots the type of document, and the image is displayed. The image file encryption unit 14 encrypts it and transmits it to the server 3 as an attached file of an electronic mail. After sending the e-mail to the server 3, the image discarding unit 16 discards (erases) the document image held in the memory 10.

  In the server 3, when the e-mail transmitted from the mobile terminal 1 is received by the communication unit 31, the image decryption unit 32 decrypts the encrypted file attached to the e-mail, and the decrypted image Is stored in the storage unit 42.

  Then, the procedure specifying unit 33 specifies the procedure from the transmission destination address of the e-mail attached with the image. The name specifying unit 44 extracts the source address from the received e-mail, specifies the name of the policyholder corresponding to the source address with reference to the master DB 43, and stores it in the storage unit 42.

  Subsequently, the character recognition unit 36 reads the image in the storage unit 42 and performs character recognition, and stores the character string obtained as a result of character recognition in the storage unit 42.

  The recognition result keyword comparison unit 37 reads the character recognition result character string stored in the storage unit 42 and the name of the policyholder, compares them, and passes the comparison result to the legibility and document type determination unit 38.

  The legibility and document type determination unit 38 reads the image as a document based on the comparison result passed from the recognition result keyword comparison unit 37 and whether the sender of the received e-mail is an insurance policyholder. Determine whether or not. For example, if a name that matches the name of the policyholder and the character recognition result string is detected, it is determined that the image is legible and the image is a document related to the policyholder who is the sender of the e-mail. Can be confirmed.

  Further, the document edge detection unit 39 detects a document edge line from the image, and the protrusion determination unit 40 determines whether or not the document edge line protrudes from the photographing range.

  The determination result notification unit 41 notifies the portable terminal 1 of these determination results (the determination result of the legibility determination result and the protrusion). After the notification, the server 3 displays the image determined to be legible in the master DB 43 of the hard disk device. Save it in association with the contractor information.

  According to the third embodiment, by providing the mobile terminal 1 with the address link input unit 19 for inputting an address link of a different transmission destination for each document, the server 3 can receive the e-mail transmitted from the mobile terminal 1. The document can be specified by the reception address, and the legibility of the document image attached to the e-mail can be confirmed without performing an identifier extraction process from the file name for specifying the procedure or the document.

  When the document image is transmitted from the portable terminal 1 to the server 3 by e-mail, if the portable terminal 1 is, for example, a cellular phone, a communication fee (packet fee) is borne by the user.

  Therefore, in order to compensate the packet fee for the user, a mail address mechanism is used in which the recipient pays the packet fee, such as toll-free. Specifically, a mechanism is adopted in which a packet transmission fee to a specific mail address is charged to the recipient side through service cooperation between carriers, or if the procedure is an insurance claim, for example, the packet equivalent is insured It is preferable to add money when paying money.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  In the above-described embodiment, the camera-equipped mobile phone is illustrated as an example of the mobile terminal 1, but other than this, for example, a PDA, a tablet terminal, an electronic book terminal, and the like equipped with an Internet connection function and a camera function may be used.

  By providing the tablet terminal with the function of the portable terminal 1 and the function of the server 3, the tablet terminal stores an image acquisition unit that acquires an image of the document and a character string candidate that is unique to the document for each type of document. A character recognition unit that performs character recognition processing using a character recognition dictionary set in advance for the image acquired by the image acquisition unit, and a character string obtained by the character recognition unit And a comparison unit that compares the character string candidates for each document type in the storage unit, and a reference in which the degree of match / mismatch between the character string candidate and the character string for each document type compared by the comparison unit is set in advance It functions as an image processing apparatus including a document type from which the image is acquired by the image acquisition unit and a legibility determination unit that determines the legibility of the document depending on whether or not the value is exceeded.

  In the above embodiment, identification information for identifying the type of document is included in a part of the image file name. However, for example, the identification information may be embedded in the image itself as a digital watermark. In this case, since the identification information of the document can be concealed, there is an effect that unauthorized use of the document image can be suppressed.

  Further, each component shown in the above embodiment may be realized by a program installed in a storage such as a hard disk device of a computer, and the program is stored in a computer-readable electronic medium: electronic media, The computer may realize the functions of the present invention by causing a computer to read a program from an electronic medium. Examples of the electronic medium include a recording medium such as a CD-ROM, flash memory, and removable media. Further, the configuration may be realized by distributing and storing components in different computers connected via a network, and communicating between computers in which the components are functioning.

  DESCRIPTION OF SYMBOLS 1 ... Portable terminal, 2 ... Network, 2a ... Wireless base station, 3 ... Server, 9 ... Display part, 10 ... Memory, 11 ... Key operation part, 12 ... Image acquisition part, 13 ... Procedure identifier provision part, 14 ... Image File encryption unit, 15 ... wireless communication unit, 16 ... image discarding unit, 17 ... control unit, 18 ... QR code recognition unit, 19 ... address link input unit, 30 ... control unit, 31 ... communication unit, 32 ... image decryption , 33 ... Procedure specifying unit, 34 ... Document name specifying unit, 35 ... Document keyword extracting unit, 36 ... Character recognition unit, 37 ... Recognition result keyword comparing unit, 38 ... Document type determining unit, 39 ... Document edge detecting unit, 40 ... a protrusion determination unit, 41 ... a determination result notification unit, 42 ... a storage unit, 44 ... a name identification unit.

Claims (5)

An image acquisition unit for acquiring an image of the document;
A storage unit that stores character string candidates specific to the document for each type of the document;
A character recognition unit that performs character recognition processing using a character recognition dictionary set in advance for the image acquired by the image acquisition unit, and obtains a character string;
A comparison unit that compares a character string obtained by the character recognition unit with a character string candidate for each document type in the storage unit, and a character string candidate and a character string for each document type compared by the comparison unit. A readability determination unit that determines the type of the document from which the image has been acquired by the image acquisition unit and the readability of the document, depending on whether the degree of match / mismatch exceeds a preset reference value; An image processing apparatus. The legibility determination unit
The gradation change rate of the image is obtained, and whether the obtained gradation change rate exceeds a preset threshold value is determined as to whether or not the image is in focus. The image processing apparatus according to claim 1, further comprising: An edge detection unit for detecting an outer edge of the document included in the image;
It further includes a protrusion determination unit that determines whether or not an outer edge of the document detected by the edge line detection unit protrudes from the image, and includes the protrusion determination result in one of the legibility determination results. The image processing apparatus according to claim 1 or 2.   The image processing apparatus according to claim 1, further comprising a QR code recognition unit that obtains information of a document from which an image is acquired by the image acquisition unit from a QR code. In an image processing system in which a mobile terminal and a server are connected via a network,
The portable terminal is
An image acquisition unit for acquiring an image of the document;
A document designating unit for designating a document for obtaining an image in the image obtaining unit;
An assigning unit that assigns identification information indicating the type of document designated by the document designating unit to the image obtained by the image obtaining unit;
A transmission unit that transmits the image to which the identification information is attached to the server,
The server
A receiving unit for receiving the image;
A storage unit that stores character string candidates specific to the document for each type of the document;
A character recognition unit that performs character recognition processing using a preset character recognition dictionary for the image received by the receiving unit, and obtains a character string;
A comparison unit that compares a character string obtained by the character recognition unit with a character string candidate for each document type in the storage unit, and a character string candidate and a character string for each document type compared by the comparison unit. A readability determination unit that determines the type of the document from which the image is acquired by the image acquisition unit and the readability of the document, depending on whether the degree of match / mismatch exceeds a preset reference value;
An image processing system comprising: a notification unit that notifies the portable terminal of a result of document legibility determination determined by the legibility determination unit.

Images