Image forming apparatus

JP2025168469A5Pending Publication Date: 2025-12-23KYOCERA DOCUMENT SOLUTIONS INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025145719
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-09-02
Publication Date
2025-12-23

AI Technical Summary

Technical Problem

Existing image processing devices struggle to classify images of documents with multiple pages appropriately on a page-by-page basis.

Method used

An image processing device that recognizes character strings in documents with multiple pages and classifies them by grouping pages with the same topic words using an OCR function and control unit.

Benefits of technology

Enables accurate classification of images of documents with multiple pages by topic on a page-by-page basis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

To classify images of documents composed of a plurality of pages for every topic by the page.SOLUTION: In an image forming apparatus 10, when images of a plurality of pages of documents are read by an image reading unit 11, a control unit 31 recognizes, for every read image of each page of the document, character strings in the image of the document, determines whether a plurality of types of topic words input through a touch operation on a topic word setting screen displayed on a screen of a display 21 are included in the character strings in the image of the document, collects, for every topic word, the images of the pages of the documents determined to include the same topic word into one group to classify the images of the pages of the documents.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to an image processing apparatus, and more particularly to a technique for classifying images of a document having multiple pages. [Background technology]

[0002] An example of an image processing device is a multifunction peripheral (MFP). This MFP reads an image of a document using an image reading unit, or receives and inputs an image of a document from an external device, and prints the image of the document on recording paper. Furthermore, in a mail processing device described in Patent Document 1, multiple documents are transported on a conveyor belt, each document is read by a scanner, information about each document is acquired from the read document, and the documents are sorted into bins on a document-by-document basis based on the information acquired from each document. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] US7992853B2 Summary of the Invention [Problem to be solved by the invention]

[0004] In the image processing device described above, if the images of each page of a document can be appropriately classified when the images of the document have multiple pages, convenience will be improved. In the above-mentioned Patent Document 1, each document is sorted into a bin based on information acquired from the document, but when a document is composed of images of multiple pages of the document, the images of each page of the document are not appropriately classified.

[0005] The present invention has been made in view of the above circumstances, and has as its object to make it possible to classify images of a document consisting of multiple pages on a page-by-page basis by topic. [Means for solving the problem]

[0006] An image processing device according to one aspect of the present invention includes an input unit for inputting an image of a document; an operation unit for inputting instructions based on user operation; and a control unit that, when an image of a document having multiple pages is input by the input unit, recognizes character strings in the image of the document for each of the input pages, determines whether the character strings in the image of the document include multiple topic words input to the operation unit, and classifies the images of the document for each page by topic word by grouping together the images of the document for pages determined to include the same topic word. [Effects of the Invention]

[0007] According to the present invention, images of a document consisting of multiple pages can be classified by topic on a page-by-page basis. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a cross-sectional view showing an image forming apparatus to which an image processing apparatus according to an embodiment of the present invention is applied; [Figure 2] 1 is a functional block diagram showing a main internal configuration of an image forming apparatus according to an embodiment of the present invention; [Figure 3] 10A and 10B are diagrams showing an example in which images of a document containing multiple pages are classified in the classification mode of the present embodiment. [Figure 4] 10A and 10B are diagrams illustrating another example in which images of a document containing multiple pages are classified using the classification mode of the present embodiment. [Figure 5] 10A and 10B are diagrams illustrating another example in which images of a document containing multiple pages are classified using the classification mode of the present embodiment. [Figure 6] FIG. 10 is a diagram showing yet another example in which images of a document containing multiple pages are classified using the classification mode of the present embodiment. [Figure 7] 10 is a flowchart showing a control procedure in a classification mode for classifying images of a document containing multiple pages. [Figure 8] FIG. 2 is a diagram showing an initial screen displayed on a display unit. [Figure 9]FIG. 10 is a diagram showing a topic word setting screen displayed on a display unit. [Figure 10] 2 is a diagram conceptually showing a classification folder, a plurality of folders stored in the classification folder, and respective save flags associated with each folder. FIG. [Figure 11] 10A, 10B, and 10C are diagrams showing the on / off state changes of the respective save flags for a plurality of folders. [Figure 12] FIG. 4 is a diagram showing a print setting screen displayed on a display unit. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0010] 1 is a cross-sectional view showing an image forming apparatus to which an image processing apparatus according to one embodiment of the present invention is applied. The image forming apparatus 10 includes an image reading unit 11 and an image forming unit 12.

[0011] The image reading unit 11 has an image pickup element (CCD sensor) that optically reads an image of a document, and the analog output of this image pickup element is converted into a digital signal to generate image data representing the image of the document.

[0012] The image forming unit 12 forms an image represented by the image data on recording paper and includes a magenta image forming unit 3M, a cyan image forming unit 3C, a yellow image forming unit 3Y, and a black image forming unit 3Bk. Each of the image forming units 3M, 3C, 3Y, and 3Bk uniformly charges the surface of the photosensitive drum 4, exposes the surface of the photosensitive drum 4 to light, forms an electrostatic latent image on the surface of the photosensitive drum 4, develops the electrostatic latent image on the surface of the photosensitive drum 4 into a toner image, and primarily transfers the toner image on the surface of the photosensitive drum 4 to the intermediate transfer belt 5. This forms a color toner image on the intermediate transfer belt 5. This color toner image is then secondarily transferred to the recording paper P, which has been transported from the paper feed unit 14 through the transport path 8, in a nip region N between the intermediate transfer belt 5 and the secondary transfer roller 6.

[0013] Thereafter, the recording paper P is heated and pressed in the fixing device 15, the toner image on the recording paper P is fixed by heat and pressure, and the recording paper P is then discharged onto a discharge tray 17 via discharge rollers 16.

[0014] Next, Fig. 2 is a block diagram showing the main internal configuration of the image forming apparatus 10 of this embodiment. As shown in Fig. 2, the image forming apparatus 10 of this embodiment includes an image reading unit 11, an image forming unit 12, a display unit 21, an operation unit 22, a touch panel 23, a network communication unit (NW communication unit) 24, an image memory 27, a storage unit 28, and a control unit 29. These components are capable of transmitting and receiving data or signals to and from each other via a bus.

[0015] The display unit 21 is configured by a liquid crystal display (LCD) or an organic light-emitting diode (OLED) display.

[0016] The operation unit 22 includes physical keys such as a numeric keypad, a decision key, a start key, etc. Various instructions are input to the operation unit 22 based on operations by the user.

[0017] A touch panel 23 is disposed on the screen of the display unit 21. The touch panel 23 is a so-called resistive or capacitive touch panel, which detects contact (touch) of a user's finger or the like with the touch panel 23 together with the contact position, and outputs a detection signal indicating the coordinates of the contact position to a control unit 31 (described later) of the control unit 29, etc.

[0018] The network communication unit 24 is a communication interface, and transmits and receives data to and from external terminal devices via a network (such as an intranet).

[0019] The image memory 27 stores image data representing an image of a document read by the image reading unit 11, or image data representing an image of a document transmitted from an external terminal device and received by the network communication unit 24.

[0020] The storage unit 28 is a large-capacity storage device such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive), and stores various application programs and various data.

[0021] The control unit 29 is composed of a processor, a RAM (Random Access Memory), a ROM (Read Only Memory), etc. The processor is, for example, a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or an MPU (Micro Processing Unit). The control unit 29 functions as a control unit 31 when a control program stored in the ROM or the storage unit 28 is executed by the processor.

[0022] The control unit 31 comprehensively controls the image forming apparatus 10. The control unit 29 is connected to the image reading unit 11, the image forming unit 12, the display unit 21, the operation unit 22, the touch panel 23, the network communication unit 24, the image memory 27, and the storage unit 28. The control unit 31 controls the operation of these components and transmits and receives signals or data to and from each of the components.

[0023] The control unit 31 serves as a processing unit that executes various processes required for image formation by the image forming apparatus 10.

[0024] Furthermore, the control unit 31 accepts operation instructions input by the user based on a detection signal output from the touch panel 23 or an operation of a physical key on the operation unit 22. For example, the control unit 31 accepts a touch operation on a GUI (Graphical User Interface) or the like displayed on the screen of the display unit 21 via the touch panel 23.

[0025] Furthermore, the control unit 31 has a function of controlling the display operation of the display unit 21 and a function of controlling the communication operation of the network communication unit 24 .

[0026] In image forming apparatus 10 configured as described above, for example, when a user places a document in image reading unit 11 and operates the start key on operation unit 22 to input a copy instruction to operation unit 22, control unit 31 accepts the copy instruction, causes image reading unit 11 to read the image of the document, stores image data representing the image of the document in image memory 27, inputs this image data to image forming unit 12, and causes image forming unit 12 to form the image of the document represented by this image data on recording paper.

[0027] In addition, when image data representing an image of a document transmitted from an external terminal device is received by the network communication unit 24, the control unit 31 stores the received image data in the image memory 27, inputs the image data to the image forming unit 12, and causes the image forming unit 12 to form the image of the document represented by the image data on recording paper.

[0028] Furthermore, the image forming apparatus 10 of this embodiment has a classification mode for classifying the images of each page of a document when the images of the document have multiple pages. A user inputs an instruction to set the classification mode via the touch panel 23 in response to, for example, an operation of a GUI displayed on the display unit 21, and also inputs multiple topic words to be used to classify the images of the document. In addition to the operation unit 22, the touch panel 23 is also an example of an operation unit within the scope of the claims.

[0029] Each time image data representing images of multiple pages of a document is sequentially stored in the image memory 27, the control unit 31 analyzes the document image using a known OCR (Optical Character Recognition) function based on the image data representing the document image to recognize character strings in the document image. The control unit 31 then determines whether the various input topic words are included in the character strings in the document image, and classifies the document images of each page determined to contain the same topic word into one group for each topic word.

[0030] For example, if three topic words WA, WB, and WC are input, as shown in FIG. 3, the control unit 31 classifies the manuscripts M1 to M3, pages 1 to 3, which contain the topic word WA, into one group Q1, the manuscripts M4 and M5, pages 4 and 5, which contain the topic word WB, into another group Q2, and the manuscript M6, page 6, which contains the topic word WC, into another group Q3.

[0031] Furthermore, if the control unit 31 determines that one of various topic words is included in a string of characters on one of the pages in the document image and classifies the document image of this page into one group, and then determines that none of the topic words are included in the string of characters in the document image of the next or subsequent pages, the control unit 31 classifies the document image of the next or subsequent pages together with the document image of the page that has already been determined to contain the above-mentioned one topic word into the same group as the document image of that page.

[0032] For example, as shown in FIG. 4, if the first page of manuscript M1 contains the topic word WA, the second to fourth pages of manuscript M2 to M4 do not contain any of the topic words WA, WB, or WC, and the fifth page of manuscript M5 contains the topic word WB, the control unit 31 classifies the first to fourth pages of manuscript M1 to M4 into one group Q1.

[0033] In addition, when the control unit 31 determines that two or more topic words among various topic words are included in the image of one page of the document, it classifies the image of the document of that page into groups corresponding to the two or more topic words.

[0034] 5, the control unit 31 classifies the first and second pages of manuscript M1 and M2, which contain the topic word WA and the topic word WB, into both group Q1 (the group of topic word WA) and group Q2 (the group of topic word WB). The control unit 31 also classifies the third page of manuscript M3, which contains the topic word WB, into group Q2 (the group of topic word WB), the fourth and fifth pages of manuscript M4 and M5, which contain the topic word WB and the topic word WC, into group Q2 (the group of topic word WB) and group Q3 (the group of topic word WC), and the sixth page of manuscript M6, which contains the topic word WC, into group Q3 (the group of topic word WC).

[0035] In addition, when the control unit 31 determines that any one of a plurality of topic words is included in a string of characters in an image of a document on one page and classifies the image of the document on that page into one group, if it determines that none of the topic words are included in the string of characters in an image of a document on the next or subsequent pages, it groups the image of the document on the next or subsequent pages into the same group together with the image of the document that has been determined to contain the one topic word.

[0036] For example, as shown in Figure 6, if the first page of manuscript M1 contains the topic word WA, the second to fourth pages of manuscript M2 to M4 contain neither the topic word WA nor WB, the fifth page of manuscript M5 contains the topic word WB, and the sixth to eighth pages of manuscript M6 to M8 contain neither the topic word WA nor WB, then the first to fourth pages of manuscript M1 to M4 are classified into one group Q1 (the group of topic word WA), and the fifth to eighth pages of manuscript M5 to M8 are classified into their respective groups Q2 (the group of topic word WB).

[0037] Next, a process performed by the image forming apparatus 10 in a classification mode for classifying images of a document having multiple pages will be described in detail with reference to the flowchart shown in FIG.

[0038] It is assumed that the control unit 31 causes the display unit 21 to display an initial screen G1 as shown in Fig. 8. A plurality of function keys 41a to 41h, etc., each associated with a different function, are displayed on the initial screen G1 shown in Fig. 8. At this time, the user touches the function key 41h for setting the classification mode.

[0039] The control unit 31 sets the classification mode in accordance with a classification mode setting instruction corresponding to the function key 41h, which is input via the touch panel 23 (S101). The control unit 31 creates a classification folder FD (S102), stores it in the storage unit 28, and displays a topic word setting screen G2, an example of which is shown in Fig. 9, on the display unit 21 (S103). The topic word setting screen G2 shown in Fig. 9 displays a message M1 prompting the user to input a topic word, text boxes TB1, TB2, and TB3 into which the topic word is entered, an add key K11, an OK key K12, and a cancel key K13.

[0040] When the user touches and selects one of the text boxes TB1, TB2, and TB3, the control unit 31 receives an instruction corresponding to the touched text box through the touch panel 23, and in accordance with this instruction, stores the text box selected by the touch operation and displays a soft keyboard (not shown) on the screen of the display unit 21. When the user touches the soft keyboard to input an arbitrary topic word, the control unit 31 receives the topic word corresponding to the touch operation on the soft keyboard through the touch panel 23 and displays the received topic word in the selected and stored text box. The control unit 31 receives each topic word corresponding to the displayed text boxes TB1, TB2, and TB3, and displays each topic word in the corresponding text box.

[0041] Furthermore, when the user touches the add key K11, the control unit 31 receives an instruction to add a text box corresponding to the add key K11 via the touch panel 23, and causes a further text box to be additionally displayed on the topic word setting screen G2. Based on the user's touch operation on the added text box, the control unit 31 receives a topic word corresponding to the added text box in the same manner as described above, and displays the received topic word in the added text box.

[0042] When the user checks the topic words displayed in the text boxes and touches the OK key K12, the control unit 31 receives a topic word setting instruction corresponding to the OK key K12 through the touch panel 23, obtains each topic word displayed in each text box at this time, and sets them as topic words to be used for classification (S104).

[0043] Furthermore, for each topic word set in S104, the control unit 31 creates a folder corresponding to the topic word in the classification folder FD created in S102 (S105). The control unit 31 generates and stores a save flag for each folder, and initializes each save flag to off (S106).

[0044] For example, if three topic words WA, WB, and WC are set, the control unit 31 creates a folder FA corresponding to the topic word WA, a folder FB corresponding to the topic word WB, and a folder FC corresponding to the topic word WC, and stores each of the folders FA, FB, and FC in the classification folder FD, as shown in Fig. 10. The control unit 31 generates and stores save flags GA, GB, and GC for each of the folders FA, FB, and FC, and keeps each of the save flags GA, GB, and GC turned off.

[0045] As described below, the control unit 31 stores image data in folder FA showing images of original documents containing the topic word WA corresponding to the folder FA, stores image data in folder FB showing images of original documents containing the topic word WB corresponding to the folder FB, and further stores image data in folder FC showing images of original documents containing the topic word WC corresponding to the folder FC.

[0046] Furthermore, as will be described later, the control unit 31 initially sets all of the save flags GA, GB, and GC for folders FA, FB, and FC to off, and when an image of a document containing a topic word is saved in one of folders FA, FB, or FC, the control unit 31 turns on the save flag for the folder in which the document image is saved. Therefore, when an image of a document containing a topic word is saved in a folder, only the save flag for this folder is turned on, and this on save flag indicates the folder in which the document image containing the topic word was most recently saved.

[0047] For example, when the control unit 31 saves an image of a document in folder FA and turns on the save flag GA corresponding to folder FA as shown in Fig. 11(A), and then saves an image of another document in another folder FB, the save flag GA corresponding to folder FA is turned off and the save flag GB corresponding to the other folder is turned on as shown in Fig. 11(B). Also, when the control unit 31 saves an image of a document in folder FA and turns on the save flag GA corresponding to folder FA as shown in Fig. 11(A), and then saves an image of another document in the same folder FA and another folder FB, the save flag GA corresponding to folder FA is turned on and the save flag GB corresponding to the other folder FB is turned on as shown in Fig. 11(C).

[0048] If the user touches the cancel key K13, the control unit 31 receives a cancel instruction corresponding to the cancel key K13 through the touch panel 23, cancels the classification mode in accordance with the cancel instruction, and causes the initial screen G1 to be displayed again on the display unit 21. After this, the process returns to S101.

[0049] As described above, the topic words WA, WB, and WC are set, folders FA, FB, and FC corresponding to the topic words WA, WB, and WC are created and stored in classification folder FD, and the save flags GA, GB, and GC associated with folders FA, FB, and FC are saved and initialized to off. After this, the user inputs images of multiple pages of original documents into image forming apparatus 10. For example, under the control of control unit 31 in accordance with instructions from the user, image reading unit 11 sequentially reads images of the multiple pages of original documents, and the images of each page of the original documents are sequentially stored in image memory 27, or images of the multiple pages of original documents transmitted from an external terminal device are received by network communication unit 24, and the received images of each original document are sequentially stored in image memory 27, thereby inputting images of the multiple pages of original documents into image forming apparatus 10 (S107).

[0050] The control unit 31 uses the OCR function to recognize a character string in the image of the first page of the document stored in the image memory 27 (S108). Furthermore, the control unit 31 determines whether any of the topic words WA, WB, and WC set in S104 is included in the recognized character string in the image of the document (S109).

[0051] If the control unit 31 determines that the topic word WA is included in the character string in the document image (S109 "Yes"), it saves the document image of that page in the folder FA corresponding to the topic word WA (S110).Then, the control unit 31 turns on the save flag GA associated with the folder FA corresponding to the topic word WA (S111).

[0052] Similarly, if the control unit 31 determines that the topic word WB is included in a character string in the image of the document (S109 "Yes"), it saves the image of the document of that page in the folder FB corresponding to the topic word WB (S110) and turns on the save flag GB associated with the folder FB corresponding to the topic word WB (S111).

[0053] Alternatively, if the control unit 31 determines that the two topic words WB and WC are included in the character string in the image of the document (S109 "Yes"), it saves the image of the document of that page in both folders FB and FC corresponding to the two topic words WB and WC (S110), and turns on the save flags GB and GC associated with the folders FB and FC corresponding to the two topic words WB and WC (S111).

[0054] The control section 31 determines whether the image of the next page of the document is stored in the image memory 27 (S113).

[0055] If the control unit 31 determines that the image of the next page of the document is stored in the image memory 27 (S113 "Yes"), it returns to S108, recognizes the character string in the image of the next page of the document, and determines whether any of the topic words WA, WB, and WC is included in the character string in the image of the next page of the document (S109). If the control unit 31 determines that any of the topic words is included in the character string in the image of the next page of the document (S109 "Yes"), it saves the image of the next page of the document stored in the image memory 27 in a folder corresponding to the topic word in the classification folder FD (S110). Furthermore, the control unit 31 turns on the save flag for the folder corresponding to the topic word (S111). The control unit 31 repeats the processes of S108 to S111 as long as there are further images of the next page of the document.

[0056] As a result, for example, as shown in Figure 3, the first to third pages of manuscripts M1 to M3 containing the topic word WA are classified into one group Q1 (saved in folder FA), the fourth and fifth pages of manuscripts M4 and M5 containing the topic word WB are classified into another group Q2 (saved in folder FB), and the sixth page of manuscript M6 containing the topic word WC is classified into another group Q3 (saved in folder FC).

[0057] Alternatively, as shown in Figure 5, the first and second pages of manuscripts M1 and M2 containing the topic word WA and the topic word WB are classified into groups Q1 and Q2 (stored in folders FA and FB, respectively), the third page of manuscript M3 containing the topic word WB is classified into group Q2 (stored in folder FB), the fourth and fifth pages of manuscripts M4 and M5 containing the topic word WB and the topic word WC are classified into groups Q2 and Q3 (stored in folders FB and FC, respectively), and the sixth page of manuscript M6 containing the topic word WC is classified into group Q3 (stored in folder FC).

[0058] On the other hand, in S109, if the control unit 31 determines that none of the topic words WA, WB, and WC is included in the character string in the image of the document on the page to be processed (S109 "No"), it determines whether any of the save flags GA, GB, and GC is turned on (S114).

[0059] Here, when the control unit 31 determines that all of the storage flags GA, GB, and GC are off (S114 "No"), the process proceeds to S113, and the process from S108 is performed on the image of the next page of the document.

[0060] If the control unit 31 determines that any one of the save flags GA, GB, and GC is on (S114 "Yes"), it adds and saves the image of the document of that page in the folder whose save flag is on (S116). If the control unit 31 determines that the image of the document of the next page exists (S113 "Yes"), the process returns to S108.

[0061] Similarly, if none of the topic words WA, WB, or WC is included in the character string in the image of the document on that page (S109 "No") and any of the save flags GA, GB, or GC is on (S113 "Yes"), the image of the document on that page is added and saved in the folder whose save flag is on (S116). Processing proceeds to S113, and the process from S108 is repeated for the image of the document on the next page.

[0062] Furthermore, if the image of the next page of the document is stored in image memory 27 (S113 "Yes"), the character string in the image of the next page of the document is recognized (S108), and any one of the topic words WA, WB, and WC is included in the character string in the image of the next page of the document (S109 "Yes"), S110 to S113 are repeated, and if none of the topic words WA, WB, and WC is included in the character string in the image of the next page of the document (S109 "No"), S114, S116, and S113 are repeated.

[0063] As a result, for example, as shown in FIG. 4, the first to fourth pages of manuscripts M1 to M4 having a common topic word are classified into one group Q1 (saved in folder FA).

[0064] Alternatively, for example, as shown in FIG. 6, the first to fourth pages of the originals M1 to M4 are classified into one group Q1 (saved in folder FA), and the fifth to eighth pages of the originals M5 to M8 are classified into their respective groups Q2 (saved in folder FB).

[0065] Furthermore, in S113, when the control unit 31 determines that there are no further images of the next page of the document in the image memory 27 (S113 "No"), this means that classification of the images of all pages of the document has been completed, and so the control unit 31 causes the display unit 21 to display a print setting screen G3, an example of which is shown in Fig. 12 (S117). For example, the control unit 31 causes the print setting screen G3 to display a message M2 prompting the user to print the folder, check boxes CB1, CB2, CB3 associated with each of the topic words WA, WB, and WC, and an OK key K21.

[0066] When the user touches a check box on the print setting screen G3, the control unit 31 receives an instruction to select the topic word corresponding to that check box through the touch panel 23, causes a check image to appear in the check box, and selects the folder corresponding to the selected topic word from among the folders FA, FB, and FC in the classification folder FD stored in the storage unit 28 (S118). Then, when the user touches the OK key K21, the control unit 31 receives a print instruction corresponding to the OK key K21 through the touch panel 23, and causes the image forming unit 12 to form images of the original documents of each page stored in the folder selected in S118 onto recording paper (S119).

[0067] Furthermore, when the user touches check boxes indicating multiple topic words, the control unit 31 receives an instruction to select the topic words corresponding to those check boxes through the touch panel 23, causes those check boxes to display checked images, and selects folders corresponding to all of the selected topic words from among the folders FA, FB, and FC in the classification folder FD stored in the storage unit 28 (S118). When the user touches the OK key K21, the control unit 31 receives a print instruction corresponding to that OK key K21 through the touch panel 23, and causes the image forming unit 12 to form images of the originals of each page stored in all of the folders selected in S118 onto recording paper (S119).

[0068] As described above, in this embodiment, each time an image of a document with multiple pages is sequentially input, character strings in the document image are recognized, and it is determined whether the character strings in the document image contain multiple topic words. The document images of pages determined to contain the same topic words are classified into a single group for each topic word. Furthermore, after classifying a document image of one page into a single group, if the character strings in the document images of subsequent pages do not contain any topic words, the document images of subsequent pages are classified (saved) into the same single group. Furthermore, if the document image contains two or more topic words among the various topic words, the document image is classified (saved) into both of the groups associated with the two or more topic words. This allows the document images of multiple pages to be classified (saved) appropriately for each topic word.

[0069] The present invention is not limited to the image forming apparatus of the above embodiment, but can also be applied to a copier or facsimile machine equipped with an image reading unit, or a system that combines a PC, a scanner, etc.

[0070] Furthermore, the configurations and processes of the above-described embodiment explained using FIGS. 1 to 12 are merely examples of the present invention, and the present invention is not limited to these configurations and processes. [Explanation of symbols]

[0071] 10 Image forming device 11 Image reading unit 12 Image forming unit 21 Display section 22 Control section 23 Touch Panel 24 Network Communications Department 27 Image Memory 28 Memory section 29 Control Unit 31 Control Unit

Claims

1. an input unit for inputting image data; an operation unit into which instructions are input based on operations by a user; a control unit that, when image data of a plurality of pages is input by the input unit, recognizes character strings in the image data for each of the input pages of image data, determines whether or not the character strings in the image data include the plurality of topic items input to the operation unit, and classifies the image data of each of the pages by grouping the image data of the pages that are determined to include the same topic item into one group, When the control unit determines that two or more types of topic items out of the plurality of types of topic items are included in one piece of image data, the control unit classifies the determined image data into groups each of the two or more types of topic items.

2. 2. The image processing device of claim 1, wherein the control unit determines that one of the plurality of topic items is included in a character string in the image data of one of the pages, classifies the image data of the page into one group, and then, if it determines that none of the topic items are included in the character string in the image data of the next or subsequent pages, groups the image data of the next or subsequent pages into the one group together with the image data determined to include the one topic item.

3. 3. The image processing device according to claim 1, wherein the control unit generates a folder for each of the various topic items, and stores image data including the same topic item in a single group in the folder of the topic item.

4. an image forming unit that forms the image data on a recording sheet; 4. The image processing device according to claim 1, wherein when an instruction to select one of the topic items and an instruction to print the folder of the selected topic item are input to the operation unit, the control unit causes the image forming unit to form image data of each page stored in the folder onto recording paper.