Image processing device, control method for image processing device, and program

Abstract

To improve the usability by performing a predetermined process using OCR results in two or more different regions of a document image.SOLUTION: An image processing device includes acquisition means that performs OCR processing on a document image obtained by scanning a document and acquires a first character string that indicates the type of the document and a plurality of second character strings that indicate related destinations of the document, and generation means that generates a plurality of destination information for the document image using a plurality of combination character strings consisting of the first character string and any one of the plurality of second character strings.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present disclosure relates to processing using OCR results.

Background Art

[0002] It is possible to apply various techniques to the result of performing OCR processing (Optical Character Recognition processing) on a scanned image of a document. For example, Patent Document 1 discloses a technique of performing OCR processing on one area of a scanned image and sending a document to an email address corresponding to the OCR-processed result.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technique according to Patent Document 1, for example, in an image of a scanned postcard, OCR processing is performed only on the area where the recipient is described, and one character string extracted from the area is converted into an email address to send the document by email. However, it was not possible to send the document to a destination corresponding to a combination of a plurality of character strings. The present disclosure has been made in view of the above problems, and an object thereof is to improve the usability when generating destination information based on the OCR result of a document image.

Means for Solving the Problems

[0005] The image processing apparatus according to the present disclosure includes an acquisition unit that performs OCR processing on a document image obtained by scanning a document, and acquires a first character string representing the type of the document and a plurality of second character strings representing the destinations related to the document, and a generation unit that generates a plurality of destination information of the document image using a plurality of combination character strings each composed of the first character string and any one of the plurality of second character strings.

Effect of the Invention

[0006] According to the technology of the present disclosure, it is possible to improve the usability when generating destination information based on the OCR result of a document image.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the present disclosure, and not all combinations of features described in these embodiments are essential for the solution means of the present disclosure. Note that the same components will be denoted by the same reference numerals and described. Also, each step (step) in the flowchart will be denoted by a code starting with "S".

[0009] [First Embodiment] FIG. 1 is a diagram showing an example of the overall configuration of an image processing system. The MFP (Multi Function Peripheral) 110 is a multifunction device having a plurality of functions such as a scanner, a printer, and an SMTP client. The MFP 110 is an example of an image processing apparatus that performs image processing on a scanned document image and transmits an email via an SMTP server (not shown). The MFP 110 also has a function of performing character recognition processing on a scanned document image, obtaining a character string, and transmitting the document image by email or the like to a transmission destination based on information related to the obtained character string. Further, the MFP 110 has a function of presenting transmission destination candidates based on information related to the obtained character string and transmitting the image by email or the like to a transmission destination selected by the user from among the transmission destination candidates. The functions of performing character recognition processing on a scanned document image, obtaining a character string, extracting a transmission destination based on information related to the obtained character string, and extracting transmission destination candidates may be executed by other servers.

[0010] The PC 120 and the mobile terminal 130 are examples of terminal devices having an email client such as an IMAP client or a POP client that receives emails and receiving emails via an IMAP server (not shown) or a POP server (not shown). Here, IMAP is an abbreviation for Internet Message Access Protocol. POP is an abbreviation for Post Office Protocol. The MFP 110 exchanges emails with the PC 120 and the mobile terminal 130 via the Internet.

[0011] The image processing system of this embodiment has a configuration including an MFP 110, a PC 120, a mobile terminal 130, an SMTP server (not shown), an IMAP server (not shown), and a POP server (not shown), but is not limited thereto. For example, the MFP 110 may also have the function of an SMTP server. Further, the PC 120 or the mobile terminal 130 of the terminal device may also have the functions of an IMAP server and a POP server. Further, the PC 120 and the mobile terminal 130 do not have a mail client and may access the mail service from a browser. In this embodiment, mails are sent from the MFP 110 to the PC 120 and the mobile terminal 130 via the Internet, but mails may be sent and received on a LAN (Local Area Network) without using the Internet.

[0012] FIG. 2 is a diagram showing an example of the hardware configuration of the MFP 110. The MFP 110 includes a hardware control unit 210, an operation unit 220, a printer unit 221, a scanner unit 222, and a modem 223. The hardware control unit 210 includes the following units 211 to 219 and controls the operation of the entire MFP 110. The CPU 211 reads out the control program stored in the ROM 212 and executes various functions of the MFP 110 such as reading, printing, and communication to perform control. The RAM 213 is used as a main memory of the CPU 211 and a temporary storage area such as a work area. In this embodiment, it is assumed that one CPU 211 executes each process using one memory (RAM 213 or HDD 214), but it is not limited thereto. For example, a plurality of CPUs and a plurality of RAMs or HDDs may cooperate to execute each process.

[0013] The HDD214 is a large-capacity storage unit that stores image data and various programs. The HDD214 also includes a destination definition table that describes definitions for obtaining destination candidates from the character strings included in the image information when transmitting document images. The destination definition table is table information managed in a database format in the MFP110 or a file representing the table in CSV (Comma Separated Values) or the like. The destination definition table can be edited from the MFP110 by the CPU211 executing software for editing the table included in the HDD214. The destination definition table may also be edited from an information terminal such as a PC120 or a mobile terminal 130 via a network.

[0014] The operation unit I / F215 is an interface that connects the operation unit 220 and the hardware control unit 210. The operation unit 220 is equipped with a touch panel, a keyboard, etc., and accepts operations, inputs, instructions, etc. from the user. Also, the operation unit 220 displays information on the touch panel to the user. The printer I / F216 is an interface that connects the printer unit 221 and the hardware control unit 210. Print image data is transferred from the hardware control unit 210 to the printer unit 221 via the printer I / F216 and printed on a recording medium.

[0015] The scanner I / F217 is an interface that connects the scanner unit 222 and the hardware control unit 210. The scanner unit 222 reads a document set on a document table (not shown) or an ADF (Auto Document Feeder) to generate scanned image data and inputs it to the hardware control unit 210 via the scanner I / F217. The MFP110 not only prints out (copies) the image data generated by the scanner unit 222 from the printer unit 221, but also sends it as a file or by email.

[0016] The modem I / F 218 is an interface that connects the modem 223 and the hardware control unit 210. The modem 223 performs facsimile communication of image data with a facsimile device on the PSTN. The network I / F 219 is an interface that connects the hardware control unit 210 (MFP 110) to the LAN. The MFP 110 uses the network I / F 219 to send an email with a document image attached to a specified email address, or to send and receive image data or various information to and from each service on the Internet. The above-described hardware configuration of the MFP 110 is an example, and it may have other configurations as necessary, or may not have some configurations.

[0017] Figure 3 is a diagram showing an example of the hardware configuration of the PC 120. The PC 120 includes a CPU 311, a ROM 312, a RAM 313, an HDD 314, and a network I / F 315. The CPU 311 reads out a control program stored in the ROM 312, executes various processes, and controls the operation of the entire PC 120. The RAM 313 is used as a main memory of the CPU 311 and a temporary storage area such as a work area. The HDD 314 is a large-capacity storage unit that stores image data and various programs. The HDD 314 includes applications such as a mail client. The network I / F 315 is an interface that connects the PC 120 to the Internet. The PC 120 performs transmission and reception of various information with other devices via the network I / F 315. The mail client application also performs mail transmission and reception with other devices via the network I / F 315.

[0018] FIG. 4 is a diagram showing an example of the hardware configuration of the mobile terminal 130. The mobile terminal 130 includes a CPU 411, a ROM 412, a RAM 413, a flash memory 414, an operation panel 415, and a network I / F 416. The CPU 411 reads out a program stored in the ROM 412 or the flash memory 414, executes various processes, and controls the operation of the entire mobile terminal 130. The RAM 413 is used as a main memory of the CPU 411 and a temporary storage area such as a work area. The flash memory 414 is a non-volatile storage medium and stores programs and various data executed by the CPU 411. Note that various programs executed by the CPU 411 include a mail client application for sending and receiving mails.

[0019] The operation panel 415 displays the internal state of the mobile terminal 130 and the screens of applications installed in the mobile terminal 130. Also, when the user touches the touch panel when performing various operations, it receives operations, inputs, instructions, etc. from the user. The network I / F 416 is an interface for connecting the mobile terminal 130 to the Internet. The mobile terminal 130 transmits and receives various information to and from other devices via the network I / F 416. The mail client application also transmits and receives mails to and from other devices via the network I / F 416. Note that communication is performed via a LAN and the Internet by a wireless communication method such as a wireless LAN or a wired method. However, the present disclosure is not limited to communication according to a specific standard and can communicate according to any standard.

[0020] FIG. 5 is a diagram showing the functional blocks of the software of the MFP 110. The MFP 110 includes a character string acquisition unit 501, a destination information generation unit 502, a transmission unit 503, a display control unit 504, and a control unit 505. The character string acquisition unit 501 performs OCR processing on the scanned document image and acquires a character string from the scanned document image. The destination information generation unit 502 has a destination definition table such as an email address determined from the combined character string. The destination information generation unit 502 generates destination information such as an email address from the combined character string obtained from the OCR processing using the above destination definition table.

[0021] The transmission unit 503 transmits the scanned document image to a destination such as a specified destination email address. In the present embodiment, the destination is assumed to be an email address, but a folder path may be set as the destination and a folder including the scanned document image may be transmitted. The display control unit 504 controls the operation unit 220 and displays various screens on the touch panel or the like of the operation unit 220. The control unit 505 performs various processes of the "Scan and Send by Email" application and controls the MFP 110.

[0022] 《Main Processing of the Application》 FIG. 6 is a flowchart showing the main processing of the "Scan and Send by Email" application executed in the MFP 110. By the CPU 211 of the MFP 110 reading and executing the program stored in the ROM 212 or the HDD 214 into the RAM 213, the processing of the flowchart shown in FIG. 6 is executed by the display control unit 504 and the control unit 505 of the MFP 110. The processing flow in FIG. 6 is started by activating an application that transmits the scanned image of the MFP 110 by email. In the present embodiment, the application that transmits the scanned image by email is referred to as the "Scan and Send by Email" application.

[0023] In S601, the display control unit 504 of the MFP 110 controls the operation unit 220 and, when the "Scan and Send by Email" application is launched, displays on the operation unit 220 a screen for selecting a method for setting an email address. When the selection screen is displayed on the operation unit 220, the process proceeds to S602.

[0024] FIG. 7 is a diagram showing an example of a screen for selecting a method for setting an email address of the "Scan and Send by Email" application, which is displayed on the operation unit 220. The "Enter New Email Address" button 701 is a button for transitioning to a screen for entering and setting a new email address. When the "Enter New Email Address" button 701 is selected, a screen for displaying an input character string is displayed. The CPU 211 of the MFP 110 receives an input from the touch panel or the keyboard (operation unit 220), sets the email address, and then executes scanning and sends an email.

[0025] The "Select from Address Book" button 702 is a button for transitioning to the address book screen. When the "Select from Address Book" button 702 is selected, the display control unit 504 of the MFP 110 displays a list of pre-registered email addresses via the operation unit 220. When a desired email address is selected by a user operation, the control unit 505 of the MFP 110 sets the email address and then executes scanning and sends an email.

[0026] The "Select Recipient from Image" button 703 is a button for extracting an email address based on the scanned document image and transitioning to a screen for setting the recipient's email address. Details will be described later. The "Select Recipient from Image and Auto-Send" button 704 is a button for extracting an email address based on the scanned document image and executing the transmission of the scanned document image to the extracted email address. Details will be described later. Also, buttons for setting an email address, etc., may include other buttons such as selecting an email address from the history, in addition to buttons 701 to 704.

[0027] The scan setting item 710 is a setting item when performing a scan. The color setting button 711 is a button for changing the color setting during scanning. By selecting the color setting button 711, it is possible to select a color setting for saving, such as identifying the scanned image as color, grayscale, black and white binary, or "automatic" according to the scanned image. The resolution setting button 712 is a button for changing the resolution setting during scanning. By selecting the resolution setting button 712, it is possible to select a resolution setting for saving the scanned image, such as 150×150 dpi, 300×300 dpi, 600×600 dpi, etc. The reading size setting button 713 is a button for changing the reading size during scanning. By selecting the reading size setting button 713, it is possible to set the size to be read during scanning, such as A4, A3, B4, automatic identification, etc. The output file format setting button 714 is a button for changing the file format generated after scanning. By selecting the output file format setting button 714, it is possible to change the file format to be generated, such as PDF, JPEG, TIFF, etc. The double-sided original setting button 715 is a button for changing the orientation setting for double-sided originals. By selecting the double-sided original setting button 715, it is possible to set whether the double-sided printed original is opened left and right or up and down and correct the orientation of the original. In addition to the setting buttons 711 to 715, the scan setting item 710 may display other scan-related settings.

[0028] In S602, the control unit 505 of the MFP 110 determines whether any of the buttons 701 to 704 has been pressed. If the control unit 505 of the MFP 110 determines that any of the buttons 701 to 704 has been pressed, the process proceeds to S603. If the control unit 505 of the MFP 110 determines that none of the buttons 701 to 704 has been pressed, the process returns to S602. In S603, the control unit 505 of the MFP 110 executes the processes defined for the buttons 701 to 704, and the process flow of the flowchart shown in FIG. 6 ends.

[0029] Automatically Sending Document Images to the Destination FIG. 8 is a flowchart showing the processing when the "Select Destination from Image and Automatically Send" button 704 is pressed. It is assumed that a document to be sent to the platen or ADF is set. By the CPU 211 of the MFP 110 reading out and executing the program stored in the ROM 212 or HDD 214 into the RAM 213, the processing of the flowchart shown in FIG. 8 is executed by each part 501 to 505 of the MFP 110.

[0030] FIG. 9 is a diagram showing an example of a document to be sent. In this embodiment, a document in the form of an application form is described as an example. The document title 901 is an item indicating the type of the document. The approver 902 is an item in which the position, department name (related party), etc. that approves the application are described. The frame 903 is a frame indicating the position where the person who approves stamps or signs.

[0031] In S801, the control unit 505 of the MFP 110 controls the scanner unit 222, and based on the scan settings of the above-described scan setting items 710, the MFP 110 executes scanning. When the scanned document image is generated, the process proceeds to S802. In S802, the character string acquisition unit 501 and the destination information generation unit 502 of the MFP 110 execute a process of generating email address information for automatically sending the scanned document image by executing the sequence shown in FIG. 10.

[0032] Figure 10 is a sequence chart showing an example of a sequence in which the MFP 110 analyzes a scanned image and generates a destination email address. In S1001, the character string acquisition unit 501 performs character recognition processing (OCR processing) on the scanned document image and acquires a character string from the scanned document image. Also, image processing such as rotation or inclination correction of the scanned document image may be performed before the OCR processing. In S1002, the destination information generation unit 502 determines whether the combination of the acquired character strings corresponds to the combination in the destination definition table, and generates an email address for automatically transmitting the scanned document image. When the email address information for automatically transmitting the scanned document image is generated, the process of the flowchart in FIG. 8 proceeds to S803.

[0033] Figure 11 is a diagram showing an example of the configuration of the destination definition table. The destination definition table is stored in the HDD 214 of the MFP 110. The combination string 1101 is a column in which a character string for determining the destination is described. The destination 1102 is a column in which the destination information is described. The destination information generation unit 502 determines whether the character string described in the combination string 1101 is included in the result of the OCR processing. If the content of the combination string 1101 is included in the result of the OCR processing, the destination 1102 in the same row is selected as a destination candidate.

[0034] Also, the destination definition table pre-sets the destination corresponding to the combination string 1101 before S801 is executed. In FIG. 9 which is an example of a document scanned by the MFP110, the document title 901 and the approver 902 are pre-set to the combination string 1101 of the destination definition table, and the email address of the destination corresponding to the approver 902 is set to the destination 1102. The scanned document image shown in FIG. 9 includes the "Borrowing Permission Application Form" of the combination string 1101, as well as "Section Chief", "Department Head", and "General Affairs Department". Therefore, the destinations "aaa.aaaa@example.com", "bbb.bbbb@example.com", and "ccc.cccc@example.com" are generated from the destination 1102. Also, when a document with the document title 901 being the "Business Trip Application Form" and the approver 902 being the "General Affairs Department" is scanned in another document, the destination "ddd.dddd@example.com" is generated. In this embodiment, the combination string 1101 is set in two columns, but it may also be in two or more columns. Also, in this embodiment, the document title 901 and the approver 902 are pre-set as the combination string 1101. It is not limited to these when the destination can be specified from other strings included in the document. As described above, since the email address which is the destination can be generated from the combination string obtained from the scanned document image using the destination definition table, the usability is improved.

[0035] In S803, the transmission unit 503 transmits to the email address specified by the email address information generated based on the scanned document image. When the scanned document image is transmitted to the specified email address, the process proceeds to S804. In S804, the display control unit 504 displays the transmission result on the operation unit 220 and ends the "Scan and Send by Email" application.

[0036] 《Send the Document Image to the Selected Destination》 Next, the processing when the "Select Destination from Image" button 703 is pressed will be described. The items described in the above-mentioned "Automatic Transmission to Destination" will be omitted from the description. FIG. 11 is a flowchart showing the processing when the "Select Destination from Image" button 703 is pressed. It is assumed that a document to be sent to the platen or ADF is set. By the CPU 211 of the MFP 110 reading and executing the program stored in the ROM 212 or HDD 214 into the RAM 213, the processing of the flowchart shown in FIG. 12 is executed in each part 501 to 505 of the MFP 110.

[0037] In S1201, the control unit 505 of the MFP 110 controls the scanner unit 222, and based on the scan settings of the above-described scan setting items 710, the MFP 110 performs a scan. When the scanned document image is generated, the process proceeds to S1202. In S1202, the character string acquisition unit 501 and the destination information generation unit 502 of the MFP 110 execute the sequence shown in FIG. 10 to perform the process of generating the email address information for transmitting the scanned document image. When candidates for the email address to be transmitted are generated, the process proceeds to S1203.

[0038] In S1203, the display control unit 504 of the MFP 110 controls the operation unit 220 to display a screen for setting the destination email address. On this screen, a list of the character strings of the email addresses generated in S1202, a check box for selecting the destination email address, a button for adding the destination email address, a button for canceling the email transmission, and a send button for executing the email transmission are displayed. When the screen for setting the destination email address is displayed, the process proceeds to S1204.

[0039] FIG. 13 is a diagram showing an example of a screen for setting a destination email address. In the destination candidate 1301, the email address acquired in S1202 is displayed. The destination selection checkbox 1302 is a checkbox for selecting the email address to be sent. The destination candidate 1301 selected by the checkbox is set as the email destination. The "Enter Email Address" button 1311 is a button for transitioning to a screen for newly entering an email address and adding it to the destination candidates. When the "Enter Email Address" button 1311 is selected, a screen (not shown) for displaying the input string is displayed, the operation unit 220 accepts input from the touch panel or the keyboard, and the email address is added to the destination candidate 1301.

[0040] The "Select from Address Book" button 1312 is a button for transitioning to the address book screen. When the "Select from Address Book" button 1312 is selected, a list of pre-registered email addresses (not shown) is displayed. By selecting an email address from the list of email addresses, the email address is added to the destination candidate 1301. Additionally, it may include buttons for selecting an email address from the history and adding the email address to the destination candidate 1301. The "Enter Email Address" button 1311 and the "Select from Address Book" button 1312 may not be present. The cancel button 1321 is a button for ending the email sending process. When the cancel button 1321 is pressed, the email sending of the scanned document image is not performed, and the "Scan and Send by Email" application ends. The send button 1322 is a button for performing a process of sending the scanned document image to the set email address by email.

[0041] In S1204, the control unit 505 of the MFP 110 determines whether the settings have been changed. If there is no change in the setting of the destination selection checkbox 1302, the process proceeds to S1206. If there is a change in the setting of the destination selection checkbox 1302, the process proceeds to S1205. In S1205, the control unit 505 of the MFP 110 updates the destination setting, and the process returns to S1204. Specifically, the email address marked with a checkmark in the destination selection checkbox 1302 is set as the destination, and the email address without a checkbox is excluded from the destination setting.

[0042] In S1206, the display control unit 504 of the MFP 110 determines whether the cancel button 1321 has been pressed. If the display control unit 504 of the MFP 110 determines that the cancel button 1321 has been pressed, the control unit 505 of the MFP 110 terminates the "Scan and Send by Email" application. If the control unit 505 of the MFP 110 determines that the cancel button 1321 has not been pressed, the process proceeds to S1207.

[0043] In S1207, the display control unit 504 of the MFP 110 determines whether the send button 1322 has been pressed. If the display control unit 504 of the MFP 110 determines that the send button 1322 has been pressed, the process proceeds to S1208. If the CPU 211 of the MFP 110 determines that the send button 1322 has not been pressed, the process returns to S1204.

[0044] In S1208, the control unit 505 of the MFP 110 determines whether at least one destination email address is set. If there is at least one checkmark in the destination selection checkbox 1302 and it is set as the destination, the process proceeds to S1210. If there is no checkmark in the destination selection checkbox 1302, the process proceeds to S1209.

[0045] In S1209, the display control unit 504 of the MFP 110 controls the operation unit 220, displays an error message indicating that the destination has not been set on the screen for setting the destination in FIG. 13, and the process returns to S1204. In S1210, the transmission unit 503 of the MFP 110 controls the network I / F 219, performs mail transmission, and the process proceeds to S1211. The transmission unit 503 of the MFP 110 scans the document image attached with the mail address of the destination candidate 1301 with a check mark in the destination selection check box 1302 as the destination and transmits the mail.

[0046] In S1211, the display control unit 504 of the MFP 110 controls the operation unit 220, displays the transmission result on the operation unit 220, and ends the "Scan and Send by Mail" application. In this embodiment, although it has been transmitted to multiple people as the destination (TO), a screen for setting CC (Carbon Copy) or BCC (Blind Carbon Copy) may be provided so that it can be transmitted by CC or BCC.

[0047] As described above, according to this embodiment, it is possible to automatically send the scanned image to the generated destination using the OCR results in two or more different regions of the document image, or display the destination candidates of the scanned image. Therefore, it is possible to improve the usability when generating destination information based on the OCR result of the document image.

[0048] [Second Embodiment] For the scanned document image, even if it is the same document, the destination may be different for each user or for each organization to which the user belongs. For example, when you want to get an approval stamp or signature from the section chief of the relevant department in an application form, the recipient to be sent differs depending on the section to which you belong. Therefore, in this embodiment, the destination is determined from the combination of the user information for transmission and the character string included in the document.

[0049] FIG. 14 is a sequence chart showing an example of a sequence for analyzing a document image scanned by the MFP 110 and selecting a list of candidate email addresses for the destination. The sequence chart shown in FIG. 14 corresponds to the sequence chart of FIG. 10 in the first embodiment. In S1401, the character string acquisition unit 501 executes OCR processing on the scanned document image and acquires a character string from the scanned document image. Image processing such as rotation or inclination correction of the scanned document image may be performed before the OCR processing.

[0050] FIG. 15 is a diagram showing an example of the configuration of a destination definition table using user information and a combined character string. The affiliated group 1501 is a column in which affiliated group information for determining the destination is described. The user 1502 is a column in which user information for determining the destination is described. The combined character string 1503 is a column in which a character string for determining the destination is described. Note that the combined character string 1503 has two columns in this embodiment, but may have two or more columns. The destination 1504 is a column in which destination information is described.

[0051] In S1402, the destination information generation unit 502 extracts, from the destination definition table based on the user information, the destination mail address group corresponding to the account operating the MFP 110. Specifically, the destination information generation unit 502 determines whether the user information corresponds to the affiliated group 1501 or the user 1502, and extracts the corresponding row. For example, when the user information is the user name: "User 1", the row with "User 1" described in the user 1502 is extracted. When the user information is the affiliated group information: "Personnel Section" and the user name is not described in the user 1502, the row with "Personnel Section" described in the affiliated group 1501 is extracted. When the acquired user information is the affiliated group information: "Personnel Section" and the user name: "User 1", the row with "User 1" described in the user 1502 is preferentially extracted. If the acquired affiliated group information and user name do not exist in the affiliated group 1501 and the user 1502, a default destination mail address group may be defined and the row may be extracted. For example, the default destination mail address group may be used for the row where both the affiliated group 1501 and the user 1502 are blank, "-", or "ALL" etc. At this time, the characters or character strings that can be used for the default destination mail address group need to be characters that cannot be used as the affiliated group name and the user name.

[0052] In S1403, the destination information generation unit 502 determines whether the combination of character strings acquired in S1401 matches the combination character string of the destination mail address group extracted in S1402. When the combination character string 1503 exists in the same row of the destination mail address group extracted in S1402, the destination 1504 in the same row is generated as a destination candidate.

[0053] For example, assume that the document shown in FIG. 9, which is an example of a document to be transmitted, is scanned using an account with the user name: "User 1". In S1402, the lines of the destination 1504 such as "aaa.aaaa@example.com", "bbb.bbbb@example.com", "ccc.cccc@example.com", and "ddd.dddd@example.com" are extracted. In S1403, the combined string 1503 of the lines extracted in S1403 and included in the OCR processing result in S1402 is "Request for Borrowing Permission", "Section Chief", "Department Head", and "General Affairs Department". Therefore, "aaa.aaaa@example.com", "bbb.bbbb@example.com", and "ccc.cccc@example.com" are generated as destination candidates from the destination 1504. Similarly, assume that the scanned account has the affiliated group information: "Personnel Section" and the user name: "User 3". In this case, "www.wwww@example.com", "xxx.xxxx@example.com", and "yyy.yyyy@example.com" are generated as destination candidates. The subsequent processing is the same as the processing after S803 (automatically transmit to the generated destination candidates) or S1204 (select a destination from the generated destination candidates) in the first embodiment.

[0054] As described above, in this embodiment, since the destinations can be collectively defined according to the affiliated group, the burden of creating the destination definition in advance is reduced, and since the definition for each user is also possible, a highly flexible setting becomes possible. Also in this embodiment, it is possible to improve the usability when generating destination information based on the OCR result of the document image.

[0055] [Third Embodiment] When approving documents such as applications, there may be cases where it is not necessary to select a destination for transmission to a business partner who has already been approved. In this embodiment, the destination is determined based on the combination of character strings and the presence or absence of a stamped impression image or signature. Here, the impression image may be image data with an actual seal stamped, or it may be an electronic impression. The signature is signature image data obtained when scanning a document.

[0056] FIG. 16 is a sequence chart showing an example of a sequence in which, in S801 or S1201, the MFP 110 analyzes a scanned document image acquired by scanning and selects a list of email addresses of destination candidates. In S801 or S1201, when the MFP 110 acquires a scanned document image, the sequence shown in FIG. 16 starts. By the CPU 211 of the MFP 110 reading a program stored in the ROM 212 or the HDD 214 into the RAM 213 and executing it, the processing of the sequence chart shown in FIG. 16 is executed in each part 501 to 505 of the MFP 110.

[0057] In S1601, the character string acquisition unit 501 of the MFP 110 executes OCR processing on the scanned document image. Also, image processing such as rotation and inclination correction of the image may be performed before performing the OCR processing.

[0058] FIG. 17 is a diagram showing an example of the configuration of a destination definition table using the combination of character strings and the presence or absence of an impression image or signature image. The character string 1701 is a column in which character strings for determining the destination are described. Note that there may be multiple columns of character strings 1701. The approver 1702 is a column indicating an approver such as a position or department name (affiliation name). The destination 1703 is a column in which destination information is described.

[0059] In S1602, the destination information generation unit 502 of the MFP 110 determines whether the result of the OCR process in S1601 includes the character string 1701 and the character strings described in the approver 1702. If both the character string 1701 and the approver 1702 exist in the result of the OCR process in the same line, the destination 1703 in the same line is generated as a destination candidate.

[0060] Assume that the setting of the destination definition table is completed before scanning the document shown in FIG. 9. It is possible to update the destination definition table after the scanning is completed. When scanning the document shown in FIG. 9, in S1601 and S1602, the character string "Borrowing Permission Application Form" of the character string 1701 and the approvers 1702 of "Section Chief", "Department Head", and "General Affairs Department" are obtained. Using the destination definition table shown in FIG. 17, "aaa.aaaa@example.com", "bbb.bbbb@example.com", and "ccc.cccc@example.com" are selected as destination candidates from the destination 1703.

[0061] In S1603, the destination information generation unit 502 of the MFP 110 generates, as the destination email address information, the email address of the approver in which there is no stamped image or signature image within a predetermined range among the destination candidates selected in S1602. In FIG. 9, as an example of a method for determining whether there is a stamped image near the approver 902, the control unit 505 of the MFP 110 determines, for example, whether a red circle is drawn above and below a certain range of the approver 902. An example of a method for determining whether there is a signature near the approver 902 is described below. The signature image data of the approver 902 is stored in the HDD 214 in advance. By collating the signature image obtained when scanning the document shown in FIG. 9 with the signature image data stored in the HDD 214 by a known method, the control unit 505 of the MFP 110 determines whether there is a signature near the approver 902.

[0062] In FIG. 9, if there is already a stamped impression or signature associated with the frames 903 related to the section chief and department head in the approver 902, then “ccc.cccc@example.com” of the General Affairs Department where no stamping or signature has been made is selected as the transmission destination candidate.

[0063] As described above, in this embodiment, the transmission destination candidates can be narrowed down based on the presence or absence of a stamped image or signature image, making it easier for the user to select the transmission destination. Also, in this embodiment, although the transmission destination candidates are narrowed down based on the presence or absence of a stamped image or signature image, the transmission destination candidates may be ranked. Then, in S1203, the transmission destination candidates without a stamped image or signature image are displayed at the top, and the transmission destination candidates with a stamped image or signature image are rearranged and displayed at the bottom to assign priorities. Also, in this embodiment as well, similar to the second embodiment, the transmission destination candidates may be narrowed down using user information and then the transmission destination may be selected based on the presence or absence of a stamped image or signature image.

[0064] [Other Embodiments] In the first, second, and third embodiments, the transmission destination is acquired only by the MFP 110, but a configuration having the MFP 110 and other servers may be adopted. That is, communication is performed between the MFP 110 and other servers, transmission destination candidates are generated in other servers, and the transmission destination candidates generated by other servers are transmitted to the MFP 110. Then, the MFP 110 automatically transmits the scanned document image to the generated transmission destination candidates, or displays the generated transmission destination candidates on the operation unit 220.

[0065] Also, although the MFP 110 has been sending emails, the server 120 may send emails. In that case, the server 120 holds the scanned document image acquired from the MFP 110, and in S1207, instead of the MFP 110 sending an email, the server 120 is sent the selected email address information. The server 120 attaches the scanned document image based on the received email address information and sends an email to the target email address.

[0066] In the above-described embodiment, a mail address is specified as the destination, but a folder path may be specified as the destination. The MFP 110 may transmit a folder including the scanned document image to the specified folder path.

[0067] The present disclosure can also be realized by supplying a program that realizes one or more functions of the above-described embodiment to a system or apparatus via a network or a storage medium, and causing one or more processors in a computer of the system or apparatus to read and execute the program. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

[0068] The disclosure of the above-described embodiment includes the following configurations.

[0069] (Configuration 1) Acquisition means for performing OCR processing on a document image obtained by scanning a document, and acquiring a first character string representing the type of the document and a plurality of second character strings representing the destinations related to the document; and using a plurality of combination character strings composed of the first character string and any one of the plurality of second character strings, generation means for generating a plurality of destination information of the document image. An image processing apparatus characterized by comprising the above.

[0070] (Configuration 2) The image processing apparatus according to Configuration 1, further comprising transmission means for transmitting the document image to a destination based on the plurality of destination information generated by the generation means.

[0071] (Configuration 3) The image processing apparatus according to Configuration 2, further comprising display control means for causing a display means to display destination candidates based on the plurality of destination information.

[0072] (Configuration 4) The display control means receives a selection of a destination by a user from among the destination candidates displayed on the display means, and the transmission means transmits the document image to the selected destination. The image processing apparatus according to Configuration 3, characterized by the above.

[0073] Configuration 5: The image processing apparatus according to Configuration 1, wherein when there is a predetermined mark in a predetermined area associated with the second character string, the generation means does not generate transmission destination information corresponding to the combined character string of the first character string and the second character string.

[0074] Configuration 6: The image processing apparatus according to Configuration 1, wherein when there is no predetermined mark in a predetermined area associated with the second character string, the generation means generates transmission destination information corresponding to the combined character string of the first character string and the second character string.

[0075] Configuration 7: The image processing apparatus according to Configuration 5 or 6, wherein the predetermined mark is a stamped image or a signature image.

[0076] Configuration 8: The image processing apparatus further includes storage means for storing user information of a user who uses the image processing apparatus, a third character string based on the user information, a plurality of fourth character strings, and a plurality of second transmission destination information associated with a plurality of second combined character strings each composed of the third character string and any one of the plurality of fourth character strings. When each combined character string composed of the first character string and the plurality of second character strings matches any one of the plurality of second combined character strings, the generation means generates, as one of the plurality of transmission destination information of the document image, each second transmission destination information associated with the second combined character string that matches the combined character string composed of the first character string and the plurality of second character strings.

[0077] Configuration 9: The image processing apparatus according to any one of Configurations 1 to 8, wherein the plurality of transmission destination information is an email address.

[0078] Configuration 10: The image processing apparatus according to any one of Configurations 1 to 8, wherein the plurality of transmission destination information is a folder path.

[0079] (Configuration 11) A step of performing OCR processing on a document image obtained by scanning a document to acquire a first string representing the type of the document and a plurality of second strings representing the destinations related to the document; and a step of generating a plurality of destination information of the document image using a plurality of combined strings each consisting of the first string and any one of the plurality of second strings. A control method for an image processing apparatus, characterized by comprising the above steps.

[0080] (Configuration 12) A program for causing a computer to function as the image processing apparatus according to any one of Configurations 1 to 10.

[0081] (Configuration 13) An image processing apparatus, comprising: an acquisition unit that performs OCR processing on a document image obtained by scanning a document to acquire a plurality of strings; and a generation unit that generates destination information of the document image using an email address corresponding to a combination of the plurality of strings.

Claims

1. An acquisition means for performing OCR processing on a document image obtained by scanning a document, and acquiring a first character string representing the type of the document and a plurality of second character strings representing the destinations related to the document; A generation means for generating a plurality of destination information of the document image using a plurality of combined character strings composed of the first character string and any one of the plurality of second character strings; An image processing apparatus, characterized by comprising the above.

2. The image processing apparatus according to claim 1, further comprising a transmission means for transmitting the document image to a destination based on the plurality of destination information generated by the generation means.

3. The image processing apparatus according to claim 2, further comprising a display control means for causing a display means to display a destination candidate based on the plurality of destination information.

4. The display control means receives a selection of a destination by a user from among the destination candidates displayed on the display means, The transmission means transmits the document image to the selected destination. The image processing apparatus according to claim 3, characterized by this.

5. The generation means does not generate destination information corresponding to a combined character string of the first character string and the second character string when there is a predetermined mark in a predetermined area associated with the second character string. The image processing apparatus according to claim 1, characterized by this.

6. The generation means generates destination information corresponding to a combined character string of the first character string and the second character string when there is no predetermined mark in a predetermined area associated with the second character string. The image processing apparatus according to claim 1, characterized by this.

7. The predetermined mark is a stamped image or a signature image. The image processing apparatus according to claim 5, characterized by this.

8. The image processing apparatus further comprises a storage means for storing user information of a user using the image processing apparatus, a third character string based on the user information, a plurality of fourth character strings, and a plurality of second combined character strings composed of the third character string and any one of the plurality of fourth character strings, and a plurality of second destination information associated therewith. When any of the combined strings formed from the first string and the plurality of second strings matches any of the plurality of second combined strings, the generation means generates, as one of the plurality of destination information of the document image, the respective second destination information associated with the second combined string that matches the combined string formed from the first string and the plurality of second strings. The image processing apparatus according to claim 1.

9. The image processing apparatus according to claim 1, wherein the plurality of destination information is an email address.

10. The image processing apparatus according to claim 1, wherein the plurality of destination information is a folder path.

11. A step of performing OCR processing on a document image obtained by scanning a document, and acquiring a first string representing the type of the document and a plurality of second strings representing the related parties of the document; A step of generating a plurality of destination information of the document image using a plurality of combined strings formed from the first string and any one of the plurality of second strings; A control method for an image processing apparatus, characterized by comprising:

12. A program for causing a computer to function as the image processing apparatus according to any one of claims 1 to 10.

13. An acquisition means for performing OCR processing on a document image obtained by scanning a document and acquiring a plurality of strings; A generation means for generating destination information of the document image using an email address corresponding to a combination formed from the plurality of strings; An image processing apparatus, characterized by comprising:

Images