Image processing apparatus

Abstract

To select, when a plurality of documents to be read have the same page number, from document images obtained through reading of the documents, one of document images having the same page number, and arrange the selected document image and the document images having the other page numbers in the order of pages.SOLUTION: A control unit 29 of an image forming apparatus 10 recognizes page numbers provided in margin areas of document images read by an image reading unit 11, arranges the document images in order of the recognized page numbers of the document images, when the recognized page numbers of the document images include the plurality of same page numbers, selects one of the document images provided with the same numbers, arranges the selected one document image and the document images provided with the other page numbers in the order of the page numbers, and stores the arranged document images in a storage unit 27.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an image processing apparatus that reads and processes a plurality of document images, and more particularly to a technique for arranging the document images in page order. [Background technology]

[0002] In an image processing apparatus, a plurality of original images are read and each original image is formed on a respective recording sheet, or each original image is stored in a storage unit.

[0003] The image forming device described in Patent Document 1 reads multiple document images, detects the page number from each document image data, and rearranges each document image according to its page number. This makes it possible to arrange multiple documents in the correct order and display or output them in the correct order, even if the multiple documents are not in the correct order.

[0004] Furthermore, the document sorting device described in Patent Document 2 inputs a stack of recording papers to which document sorting information has been added in one go, reads the document sorting information (page number, etc.) of each recording paper, and performs processing such as rearranging the pages of each recording paper based on the document sorting information of each recording paper. Also, if a page is missing from the stack of recording papers, an error is displayed, processing is interrupted, and an alternative transport material (paper of a different color from the recording paper) is inserted. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2007-142631 A [Patent Document 2] Japanese Patent Application Publication No. 10-316302 Summary of the Invention [Problem to be solved by the invention]

[0006] As described above, in Patent Document 1, the page number is detected from each document image data, and each document image is rearranged according to its page number. In addition, in Patent Document 2, the document sorting information (page number, etc.) of each recording sheet is read, and a page rearrangement process is performed for each recording sheet, and missing pages are also dealt with.

[0007] Here, there are cases where other documents that are completely unrelated to the multiple documents are mixed in and the multiple documents have the same page numbers. In this case, it becomes difficult to accurately arrange the document images obtained by document reading according to the page numbers. However, in such a case, neither the technology described in Patent Document 1 nor the technology described in Patent Document 2 can accurately arrange the document images obtained by document reading according to the page numbers.

[0008] The present invention has been made in consideration of the above-mentioned circumstances, and aims to select one of the document images with the same page number from among the document images obtained by reading each document when the page numbers of multiple documents to be read are the same, and to arrange the selected document image and the document images with the other page numbers in page order. [Means for solving the problem]

[0009] An image processing device according to one aspect of the present invention includes a reading unit that reads multiple original images, a memory unit, and a control unit that recognizes page numbers assigned to marginal areas of each original image obtained by reading multiple originals by the reading unit, arranges each original image according to the page numbers recognized for each original image, and if there are multiple identical page numbers among the page numbers recognized for each original image, selects one of the original images assigned with the same page number, arranges the selected one original image and each original image assigned with a different page number according to their respective page numbers, and stores each of the arranged original images in the memory unit. Effect of the Invention

[0010] According to the present invention, when the page numbers of multiple documents to be read are the same, one of the document images obtained by reading each document can be selected that has the same page number, and the selected document image and the document images with the other page numbers can be arranged in page order. [Brief description of the drawings]

[0011] [Figure 1] 1 is a cross-sectional view showing an image forming apparatus which is an embodiment of an image processing apparatus according to the present invention. [Diagram 2] 1 is a block diagram showing an internal configuration of an image forming apparatus; [Figure 3A] 10 is a flowchart showing a process of arranging document images obtained by reading a plurality of documents in page order and storing them in a storage unit. [Figure 3B] 3B is a flowchart showing the control procedure following FIG. 3A. [Figure 4] FIG. 4 is a diagram showing a function selection screen displayed on a display unit. [Diagram 5] FIG. 13 is a diagram illustrating an example of a document with a folded corner. [Figure 6] FIG. 13 is a diagram showing a warning screen displayed on the display unit. [Figure 7] FIG. 13 is a diagram showing a warning screen displayed on the display unit. [Figure 8] FIG. 13 is a diagram showing a state in which a plurality of document images are arranged in page order. [Figure 9] FIG. 13 is a diagram showing a state in which a plurality of original images arranged in page order include original images to which the same plurality of page numbers are assigned. [Figure 10] FIG. 13 is a diagram used to explain a process of selecting and leaving one original image among original images to which the same page number is assigned, and deleting the other original images not selected. [Figure 11] FIG. 13 is a diagram showing a notification screen displayed on a display unit. [Figure 12] 13A to 13C are diagrams illustrating a process of deleting an original image having the same page number from among the original images having the same page number, while leaving an original image having the same format as an original image having a different page number. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The image processing device of the present invention will be described below with reference to the drawings. Fig. 1 is a cross-sectional view showing an image forming device which is an embodiment of the image processing device of the present invention. As shown in Fig. 1, the image forming device 10 of this embodiment is an MFP (multi-function peripheral) having multiple functions such as a copy function and a printer function. The image forming device 10 includes an image reading unit 11 and an image forming unit 12.

[0013] The image reading unit 11 has an imaging element (CCD sensor, CIS) that optically reads an image of an original document, and image data showing the image of the original document is generated from the analog output of the imaging element. In addition, the image reading unit 11 reads an image of an original document placed on an original table (platen glass) with the imaging element, or causes an ADF (automatic document feeder) to pull out and transport a plurality of original documents set on an original document tray one by one, and reads the image of the original document being transported with the imaging element.

[0014] The image forming unit 12 is an image forming mechanism that forms an image represented by the image data on a recording sheet. The image forming unit 12 includes an image forming unit 3M for magenta, an image forming unit 3C for cyan, an image forming unit 3Y for yellow, and an image forming unit 3Bk for black. In each of the image forming units 3M, 3C, 3Y, and 3Bk, the surface of the photosensitive drum 4 is uniformly charged, the surface of the photosensitive drum 4 is exposed to light, an electrostatic latent image is formed on the surface of the photosensitive drum 4, the electrostatic latent image on the surface of the photosensitive drum 4 is developed into a toner image, and the toner image on the surface of the photosensitive drum 4 is primarily transferred to the intermediate transfer belt 5. As a result, a color toner image is formed on the intermediate transfer belt 5. This color toner image is secondarily transferred to the recording sheet P that has been transported from the paper feed unit 14 through the transport path 8 in the nip area N between the intermediate transfer belt 5 and the secondary transfer roller 6.

[0015] Thereafter, the recording paper P is heated and pressed in the fixing device 15 so that the toner image on the recording paper P is fixed by thermocompression, and the recording paper P is then discharged onto a discharge tray 17 via discharge rollers 16 .

[0016] 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, an image memory 26, a storage unit 27, and a control unit 28. These components are capable of transmitting and receiving data or signals to and from each other via a bus.

[0017] The display unit 21 is configured with a liquid crystal display (LCD) or an organic light-emitting diode (OLED) display.

[0018] 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 by the user operating each of the above keys.

[0019] A touch panel 23 is disposed on the screen of the display section 21. The touch panel 23 is a so-called resistive film type or capacitive type touch panel, which detects a contact (touch) made by a user's finger or the like on the touch panel 23 together with the contact position, and outputs a detection signal indicating the coordinates of the contact position to a control section 29 (described later) of the control unit 28, etc.

[0020] In the image memory 26, image data indicating the image of the original M read by the image reading unit 11 is stored.

[0021] The storage unit 27 is a large-capacity storage device such as a solid state drive (SSD) or a hard disk drive (HDD), and stores various application programs and various data.

[0022] The control unit 28 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), etc. The control unit 28 functions as a control unit 29 by the processor executing a control program stored in the ROM or the storage unit 27.

[0023] The control unit 29 comprehensively controls the image forming apparatus 10. The control unit 28 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 image memory 26, and the storage unit 27. The control unit 29 controls the operation of these components and transmits and receives signals or data between these components.

[0024] The control unit 29 serves as a processing unit that executes various processes required for image formation by the image forming apparatus 10. The control unit 29 also accepts instructions input by the user based on a detection signal output from the touch panel 23 or an operation of a physical key of the operation unit 22. For example, the control unit 29 accepts instructions associated with a touch operation on a GUI (Graphical User Interface) or the like displayed on the screen of the display unit 21 through the touch panel 23. Furthermore, the control unit 29 controls the display operation of the display unit 21. The control unit 29 also processes image data stored in the image memory 26.

[0025] In the image forming device 10 having such a configuration, for example, when a user sets an original M in the image reading unit 11 and operates the start key on the operation unit 22, an instruction to perform a copy operation is input to the operation unit 22, and the control unit 29, in accordance with the instruction to perform the copy operation, causes the image reading unit 11 to read the image of the original M, temporarily stores image data representing the image of the original M in the image memory 26, inputs this image data to the image forming unit 12, and causes the image forming unit 12 to form the image represented by this image data on recording paper.

[0026] The image forming apparatus 10 is also provided with a page order editing function that arranges the document images obtained by reading the multiple documents M by the image reading unit 11 in page order and stores them in the storage unit 27. When the page order editing function is executed, the control unit 29 causes the image reading unit 11 to read the images of the multiple documents M, and the control unit 29 recognizes the page numbers present in the marginal areas of each document image obtained by the document reading, and arranges the document images in order according to the page numbers recognized in each document image and stores them in the storage unit 27. Note that arranging the document images in order means either (i) creating one file (e.g., PDF format, etc.) in which the document images are arranged in page number order by assigning a page number corresponding to each document image, or (ii) creating a separate file for each document image by assigning a page number corresponding to each document image, and assigning the corresponding page number to each created file as the name of each created file.

[0027] Furthermore, the control unit 29 determines, for each original image, whether the original image includes a folded image portion indicating a folded original, and if it determines that only one original image does not include the folded image portion and the page number is not recognized, it determines a missing page number from the page numbers recognized for the other original images for the original image that includes the folded image portion and assigns the missing page number to the original image, arranges each original image according to the recognized page number and the assigned page number of each original image, and stores each arranged original image in the memory unit 27.

[0028] Furthermore, when there are a plurality of identical page numbers among the page numbers recognized in each of the read original images, the control unit 29 selects one of the original images to which the same page number has been assigned, and arranges this selected original image and the original images to which different page numbers have been assigned according to their respective page numbers and stores them in the memory unit 27.

[0029] In this manner, in this embodiment, all document images obtained by reading each document M are arranged in the order of page numbers.

[0030] Next, a process of arranging the document images obtained by reading a plurality of documents in the order of pages and storing them in the storage unit in the image forming apparatus 10 will be described. Figures 3A and 3B are flowcharts showing the process of arranging the document images obtained by reading a plurality of documents in the order of pages and storing them in the storage unit.

[0031] The control unit 29 causes the display unit 21 to display a function selection screen GS as shown in Fig. 4, for example. On this function selection screen GS, a plurality of function keys 41a to 41h, each associated with a different function, are displayed. When the user touches the function key 41h associated with the page order editing function, the control unit 29 receives an instruction to execute the page order editing function associated with the function key 41h through the touch panel 23, and sets the page order editing function according to the execution instruction (S101).

[0032] After setting the page order editing function, the user sets a plurality of documents M on the document tray of the image reading unit 11. The document tray of the image reading unit 11 is provided with a sensor that detects each document M set on the document tray.

[0033] When the sensor detects each document M set on the document tray, the control unit 29 causes the ADF of the image reading unit 11 to sequentially pull out each document M from the document tray one by one and transport it, and each time a document M is transported, the image sensor of the image reading unit 11 reads an image of the document M being transported (S102), and stores each document image obtained by reading the multiple documents M in, for example, an image memory built into the control unit 28. The control unit 29 causes the image reading unit 11 to read each document M with an area corresponding to a document size to be read (for example, a standard paper size) input by the user to the operation unit 22, or with a document size to be read detected by a known document size detection sensor provided in the image reading unit 11.

[0034] Based on each document image showing an image of each document M stored in the storage unit 27, the control unit 29 judges whether or not the document image im has an image portion showing a folded corner of the document M as shown in Fig. 5 (S103). For example, the control unit 29 detects the contour of the entire circumference of the document image in each document image by, for example, edge detection. The control unit 29 judges whether or not images showing corners (corner portions) are present at the four corners of the image portion showing the contour of each document image, and judges that a document image in which images showing corners (corner portions) are not present at all four corners includes a folded image portion showing a folded document.

[0035] When the control unit 29 determines that at least one of the original images includes a folded image portion (S103 "Yes"), it determines whether or not there are two or more original images including a folded image portion (S104). When the control unit 29 determines that there are two or more original images including a folded image portion (S104 "Yes"), it causes the display unit 21 to display a warning screen G1 as shown in FIG. 6 (S105). After this, the process ends. The warning screen G1 displays a message E1 that urges the user to re-read each original M because the reading of each original M was not performed normally. In other words, because multiple originals M were not read normally, the user is prompted to re-read the originals in order to obtain the existing or original images by reading all the originals normally.

[0036] When the control unit 29 determines that there is no document image including a folded image portion (S103 "No"), the process proceeds to S107.

[0037] Even if the control unit 29 determines that there is an original image including a folded image portion (S103 "Yes"), if it determines that there is only one original image including a folded image portion (S104 "No"), the process proceeds to S107.

[0038] In S107, the control unit 29 determines character strings in the text area, image area, margin area, and blank margin area of ​​the document image for each document image obtained by reading multiple documents, for example, by using a known OCR (Optical Character Reader) function or AI (artificial intelligence)-OCR function (S107). Furthermore, the control unit 29 recognizes character strings included in the margin area (S108). The margin area is a so-called header, and an author's name, title, date, page number, etc. are written therein. Alternatively, the margin area is a so-called footer, and like the header, an author's name, title, date, page number, etc. are written therein.

[0039] The control unit 29 extracts a character or a character string indicating a page number from a character string included in a marginal area of ​​the document image for each document image (S109). For example, the control unit 29 uses a Named Entity Recognition (NER) function to extract and exclude an author name, a title, and a date from a character string included in a marginal area recognized by an OCR function or an AI-OCR function, and identifies and extracts a number indicating a page number. Alternatively, the control unit 29 may detect a predetermined combination of characters and numbers, such as page n or -n- (n is a number), from a character string included in a marginal area, and extract a value indicated by a number included in the detected combination as a page number.

[0040] Furthermore, the control unit 29 judges the position of the page number in each document image (S110), and judges whether the deviation between the positions of the page numbers in each document image is within a preset error range (S111). If the deviation between the positions of the page numbers in each document image is not within the error range (S111 "No"), the control unit 29 displays a warning screen G11, an example of which is shown in FIG. 7, on the display unit 21 (S105). After this, the process ends. This is because there is a possibility that an error in reading the document has occurred. For example, the control unit 29 judges the average center position of the positions of the page numbers in each document image, calculates the deviation of the positions of the page numbers from this center position, and if the deviation of the positions of the page numbers is equal to or less than a preset threshold, it judges that the deviation of the positions of the page numbers is within the error range, and if the deviation of the positions of the page numbers is not within the error range, it judges that the deviation is not within the error range.

[0041] Furthermore, if the deviation in the position of each page number falls within the error range (S111 "Yes"), the control unit 29 judges whether or not there is a missing page number among the page numbers extracted from each document image (S112). For example, the control unit 29 determines whether the page numbers are complete from the first page to the last page, taking the value indicating the number of documents read as the page number of the last page, and if not, judges that a page number is missing.

[0042] When the control unit 29 determines that there is a missing page number for each document image (S112 "Yes"), it determines whether there are multiple missing page numbers (S113). When the control unit 29 determines that there are multiple missing page numbers (S113 "Yes"), it causes the display unit 21 to display a warning screen G11, an example of which is shown in Fig. 7 (S105). After this, the process ends.

[0043] Furthermore, when the control unit 29 determines that there is only one missing page number and not multiple missing pages (S113 "No"), it identifies the values ​​of the page numbers that are not complete from the first page to the final page (S115). For example, when the number of pages of the scanned document is 10, the control unit 29 determines the page numbers indicating the pages from the first page to the final page, page 10, as the missing page numbers (missing page numbers).

[0044] Then, the control unit 29 assigns the specified page number to the document image from which the page number has not been extracted, generates and synthesizes an image showing the specified page number Pn at the average central position of the page number determined in S110 in the document image from which the page number has not been extracted, and further, if the document image from which the page number has not been extracted includes the folded image portion, synthesizes a contour image showing a shape similar to the contour at the position corresponding to the folded image portion in another document image to the folded image portion in the document image from which the page number has not been extracted, thereby correcting the document image from which the page number has not been extracted to a rectangular shape (S115). For example, the control unit 29 identifies two sets (four) of parallel straight-line contours that form the rectangle of the document M, corrects the document image to a rectangular shape based on these straight-line contours, and fills in a triangular portion missing due to a corner fold with a plurality of white pixels.

[0045] Therefore, even if one of the original images is missing a page number, the page number that should be the page number of that original image is assigned to that original image.

[0046] Next, the control unit 29 judges whether there are multiple identical page numbers among the page numbers of each document image (S116). Note that, when the control unit 29 judges that there is no missing page number among the page numbers of each document image (S112 "No"), it judges whether there are multiple identical page numbers among the page numbers of each document image (S116) without performing S113 to S115.

[0047] For example, when the control unit 29 determines that there are no identical page numbers (S116 "No"), since the page numbers of each original image are complete with no missing pages, the control unit 29 arranges each original image in the order of their page numbers as shown in FIG. 8 and stores them in the memory unit 27 (S117).

[0048] In addition, when the control unit 29 determines that there are multiple document images with the same page number (page 3 in FIG. 9) as shown in FIG. 9 (S116 "Yes"), it determines whether the multiple document images with the same page number are identical (S118).

[0049] For example, the control unit 29 recognizes the text contained in each original image having the same page number using the OCR function or AI-OCR function, and further determines whether the text contained in each original image matches each other. If the texts match each other, it determines that the original images are the same (S118 "Yes"), and if the texts do not match each other, it determines that the original images are not the same (S118 "No").

[0050] When the control unit 29 determines that the document images having the same page number Pn are the same as shown in Fig. 10 (S118 "Yes"), it deletes the other document images while leaving one of the document images (S119). The control unit 29 causes the display unit 21 to display a notification screen G2 as shown in Fig. 11 (S120). The notification screen G2 displays a message E2 indicating that one of the document images having the same page number has been deleted while leaving the other. After this, the process returns to S116.

[0051] In S116, the control unit 29 again determines whether there are multiple identical page numbers among the page numbers of each document image (S116). If the control unit 29 determines that there are no multiple identical page numbers (S116 "No"), since the page numbers of each document image are complete without any missing pages, the control unit 29 arranges each document image in the order of page numbers as shown in FIG. 8 and stores each document image in the storage unit 27 (S117).

[0052] On the other hand, in S118, if the control unit 29 determines that the document images assigned the same page number are not the same (S118 "No"), it determines the format of each document image obtained in this document reading (S121).

[0053] 12, the format of each document image is compared, and among the document images with the same page number Pn, the image of document M having the same format as the document image with a different page number Pn is left and the other is deleted (S122). Since the document image that is not selected and deleted does not have the same format as the document image with the different page number Pn, it is highly likely that another document was read in by the process of S122 when document M was read, and the other document is deleted.

[0054] As a method of the above-mentioned determination, for example, the control unit 29 recognizes the text area and margin area as the format of each original image using a known method with the OCR function or AI-OCR function, and determines the shape consisting of the vertical and horizontal width of the margin area in each original image (S121), and if the shape of the margin area of ​​any of the original images assigned the same page number matches the shape of the margin area in an original image having a different page number, the original image having the matching shape of the margin area is retained and the other original image is deleted (S122).

[0055] Alternatively, the control unit 29 determines whether the color type of each original image is monochrome or color as the format of each original image (S121), and when the color type of any of the multiple original images with the same page number matches the color type of the original image with another page number, among the multiple original images with the same page number, the original image with the same page number that matches the color type of the original image with the other page number is retained and the other is deleted (S122). The determination of whether the original image is monochrome or color is performed, for example, by a known method such as ACS (Auto Color Selection).

[0056] The control unit 29 also determines the font type of the page number or the font type of the text in each document image as the format of each document image (S121), and when the font type of the page number (or the font type of the text) of a plurality of document images having the same page number matches the font type of the page number (or the font type of the text) of a document image having a different page number, the control unit 29 deletes the other document images having the same page number while leaving the document images having the matching font type (S122).The control unit 29 determines the font type of the page number or the font type of the text in each document image by a known method, for example, by using font data indicating the fonts of a plurality of characters for each font type to search for a font matching the font of the page number or the font of the text in the document image.

[0057] As shown in Fig. 12, among the multiple original images to which the same page number is assigned, the control unit 29 leaves the original image having the same format as the format of the original image having the other page number and deletes the other original image (S122). The control unit 29 causes the display unit 21 to display the notification screen G2 shown in Fig. 11 (S120), and again determines whether there are multiple identical page numbers among the page numbers for each original image (S116).

[0058] Then, when the control unit 29 determines that there are no multiple identical page numbers (S116 "No"), since the page numbers of each original image are complete without any missing pages, it arranges the remaining original images and original images to which different page numbers have been assigned in the order of the page numbers of each original image, as shown in FIG. 8, and stores each original image in the memory unit 27 in page order (S117).

[0059] In this embodiment, the page number attached to each document image is recognized, and the document images are arranged according to the page number recognized in each document image. If some document images do not include a page number and one page number is missing among the recognized page numbers of each document image, the missing page number is assigned to the document image that does not include the page number, and the document images are arranged according to the page numbers of each document image. Furthermore, one of the document images with recognized page numbers is left and the other is deleted, and the remaining document image and the document image with the different page number are arranged according to their page numbers. As a result, according to the above embodiment, when the page numbers of multiple documents to be read are the same, one of the document images obtained by reading the documents with the same page number is selected, and the selected document image and the document images with the other page numbers can be arranged in page order.

[0060] In the above embodiment, in S119 and S122, one of the original images having the same page number is selected and retained, and the other original images not selected are deleted. However, the control unit 29 may store the original images selected for deletion in the memory unit 27.

[0061] Moreover, the configurations and processes of the above-described embodiment described with reference to FIGS. 1 to 12 are merely examples of the present invention, and the present invention is not limited to these configurations. [Explanation of symbols]

[0062] 10 Image forming device 11 Image reading unit 12 Image forming section 21 Display section 22 Control section 23 Touch Panel 26 Image Memory 27 Memory section 28 Control Unit 29 Control Unit

Claims

1. A reading unit that reads a plurality of document images; A storage unit; a control unit that recognizes page numbers assigned to marginal areas of each original image obtained by reading a plurality of original documents by the reading unit, arranges each original image according to the recognized page number for each original image, and when there are a plurality of identical page numbers among the page numbers recognized for each original image, selects one of the original images assigned with the same page number, arranges the selected one original image and each original image assigned with a different page number according to their respective page numbers, and stores each of the arranged original images in the memory unit.

2. 2. The image processing device according to claim 1, wherein when there are multiple identical page numbers among the page numbers recognized for each of the original images, the control unit determines whether the original images assigned the same page number are identical, and when it determines that the original images are identical, selects one of the original images assigned the same page number, arranges the selected one original image and an original image assigned a different page number according to their respective page numbers, and stores each of the arranged original images in the memory unit.

3. 2. The image processing device according to claim 1, wherein, when there are multiple identical page numbers among the page numbers recognized for each of the original images, the control unit compares the format of each original image to which the same page number has been assigned with the format of an original image to which a different page number has been assigned, selects from among the original images to which the same page number has been assigned an original image having the same format as the original image to which the different page number has been assigned, arranges the selected original images to which the same format has been assigned and the original images to which the different page number has been assigned according to their respective page numbers, and stores each of the arranged original images in the memory unit.

4. 4. The image processing device according to claim 3, wherein the format of the original image is at least one of the size of the margin area, whether the original image is monochrome or color, the font type of the page number, or the font type of the text contained in the original image.

5. Further comprising a display unit, The image processing apparatus according to claim 1 , wherein the control unit causes the display unit to display a message indicating that a plurality of identical page numbers are present among the page numbers recognized for each of the document images.

6. 2. The image processing device according to claim 1, wherein the control unit determines, for each of the original images read by the reading unit, whether the original image includes a folded image portion indicating an original fold, and if it determines that multiple original images include the folded image portion, does not perform a process of arranging each of the original images according to the page number recognized for each of the original images and a process of storing each of the arranged original images in the memory unit.

7. 2. The image processing device according to claim 1, wherein the control unit determines, for each of the original images, whether the original image includes a folded image portion indicating a folded original, and if it determines that only one original image does not include the folded image portion and the page number is not recognized, determines a missing page number from the page numbers recognized for the other original images for the original image including the folded image portion and assigns the missing page number, arranges the original images according to the recognized page numbers and the assigned page numbers of each of the original images, and stores each of the arranged original images in the memory unit.

8. Further comprising a display unit, 8. The image processing device according to claim 6, wherein when the control unit determines that the document image includes a folded image portion indicating a document fold, the control unit causes the display unit to display information indicating that the document image includes the folded image portion.

Images