JP2016163141A - Image processing apparatus, image processing method and program - Google Patents

Abstract

An object of the present invention is to appropriately restore original images to the same size without generating and printing information other than images of a plurality of reduced original documents. An image processing apparatus according to the present invention includes a character information acquisition section, an aggregation number determination section, and a page order determination section. The character information acquisition unit acquires character information indicating characters included in image data read from a document. The aggregation number determination section determines an aggregation number indicating the number of a plurality of document images that are aggregated into image data, based on the character information acquired by the character information acquisition section. The page order determination unit determines the page order of the plurality of manuscript images based on character information included in each of the plurality of manuscript images. [Selection diagram] Figure 2

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program.

  2. Description of the Related Art Conventionally, an image forming apparatus having a function (aggregate printing) for reducing a plurality of originals and forming an image on the same recording paper is known. In such an image forming apparatus, when each original image reduced in the collective printing is returned to the original image size before the collective copy and scanned or printed (same size restoration), the user manually operates. Since it is necessary to perform trimming and enlargement, there is a problem that the burden on the user is heavy.

  In order to solve such a problem, at the time of aggregate printing, in addition to a plurality of reduced original images, a mark representing information necessary for restoring the same magnification such as an aggregation rate is printed on a recording sheet. A technique for restoring to a non-aggregated state (same size restoration) is known.

  However, with the technique disclosed in Patent Document 1, if a mark necessary for the normal magnification restoration cannot be recognized for some reason, the normal magnification restoration cannot be performed. That is, with the technique disclosed in Patent Document 1, there is a case where it is not possible to appropriately restore the same size. Further, in the technique disclosed in Patent Document 1, it is necessary to generate and print information other than the reduced plurality of document images (marks necessary for the normal magnification restoration), so that the processing becomes complicated.

  In order to solve the above-described problems and achieve the object, the present invention is obtained by a character information acquisition unit that acquires character information indicating characters included in image data read from a document, and the character information acquisition unit. Based on the character information, based on the character information included in each of the plurality of document images, an aggregation number determination unit that determines an aggregation number indicating the number of document images aggregated in the image data, And a page order determining unit that determines a page order of the plurality of document images.

  According to the present invention, it is possible to appropriately restore the same size without generating and printing information other than a plurality of reduced original images.

FIG. 1 is a diagram illustrating an example of a hardware configuration of an MFP. FIG. 2 is a diagram illustrating an example of functions of the image processing apparatus. FIG. 3 is a flowchart illustrating an example of processing performed by the image processing apparatus. FIG. 4 is a diagram illustrating an example of input image data. FIG. 5 is a diagram for explaining a first process of the aggregation number determination process. FIG. 6 is a diagram for explaining a second process of the aggregation number determination process. FIG. 7 is a diagram for explaining a third process of the aggregation number determination process. FIG. 8 is a diagram for explaining a fourth process of the aggregation number determination process. FIG. 9 is a flowchart showing the aggregation number determination process. FIG. 10 is a flowchart showing the aggregation number determination process. FIG. 11 is a flowchart showing the aggregation number determination process. FIG. 12 is an image diagram of input image data. FIG. 13 is a flowchart illustrating an example of the page number determination process. FIG. 14 is an image diagram of input image data. FIG. 15 is an image diagram of the table of contents determination process. FIG. 16 is a flowchart illustrating an example of a table of contents determination process. FIG. 17 is an image diagram of input image data. FIG. 18 is a flowchart illustrating an example of a table of contents reuse determination process. FIG. 19 is an image diagram showing image data read from the document of the last page. FIG. 20 is an image diagram of the page crossing character determination process.

  Hereinafter, embodiments of an image processing apparatus, an image processing method, and a program according to the present invention will be described in detail with reference to the accompanying drawings. Hereinafter, as an example of an image forming apparatus to which the present invention is applied, a multifunction peripheral (MFP) will be described as an example. However, the present invention is not limited to this. Note that a multifunction peripheral is a device having a plurality of different functions such as a copy function, a scanner function, a print function, and a fax function.

  FIG. 1 is a diagram illustrating an example of a hardware configuration of the MFP 1 according to the present embodiment. As illustrated in FIG. 1, the MFP 1 includes a document reading device 10, an image processing device 20, an operation unit 60, and a printing device 40.

  The document reading device 10 is a device that reads image data from a document placed on a document table, and can be realized in various known configurations. Image data read by the document reading device 10 is input to the image processing device 20.

  The image processing device 20 is a device that performs image processing on image data (image data read from a document) input from the document reading device 10. As shown in FIG. 1, the image processing apparatus 20 includes a CPU 201, a ROM 202, a RAM 203, a blank sheet detection processing circuit 204, a rotation processing circuit 205, a scaling processing circuit 206, a trimming processing circuit 207, and a network I. / F circuit 208 and output image processing circuit 209.

  The CPU 201 comprehensively controls the operation of the image processing apparatus 20. The CPU 201 controls the overall operation of the image processing apparatus 20 by executing a program stored in the ROM 202 or the like using the RAM 203 as a work area (work area).

  The blank sheet detection processing circuit 204 is a circuit that detects a blank area of a document. The rotation processing circuit 205 is a circuit that performs rotation processing for rotating image data. The scaling processing circuit 206 is a circuit that performs processing such as reduction and enlargement of image data. The trimming processing circuit 207 is a circuit that performs processing for cutting out (extracting) a partial region of image data. The network I / F circuit 208 is an interface circuit for transmitting / receiving data to / from the external device 50. The output image processing circuit 209 is a circuit that processes image data (output image) output to the printing apparatus 40.

  The operation unit 60 is a device that receives an operation by a user, and may be configured with a touch panel, for example. The printing device 40 is a device that performs printing based on the image data output from the image processing device 20, and can be realized with various known configurations.

  Next, functions of the image processing apparatus 20 will be described. FIG. 2 is a block diagram illustrating an example of functions that the image processing apparatus 20 has. As shown in FIG. 2, the image processing apparatus 20 includes a character information acquisition unit 21, a rotation processing unit 22, an aggregation number determination unit 23, a page order determination unit 24, a trimming processing unit 25, and a storage unit 26. The enlargement unit 27, the page order change unit 28, the network I / F unit 29, the output image processing unit 30, and the output unit 31. In the present embodiment, functions of each unit of the image processing apparatus 20 (character information acquisition unit 21, rotation processing unit 22, aggregation number determination unit 23, page order determination unit 24, trimming processing unit 25, enlargement unit 27, page order change unit 28, the network I / F unit 29, the output image processing unit 30, and the output unit 31) are realized by the CPU 201 executing a program stored in the ROM 202 or the like. At least a part of the functions of the respective units may be realized by a dedicated hardware circuit.

  The character information acquisition unit 21 acquires character information indicating characters included in image data read from a document (hereinafter also referred to as “input image data”). For example, the character information acquisition unit 21 performs processing (OCR processing or the like) for identifying characters included in the input image data, thereby acquiring character information and determining the character printing direction (character progression direction). The rotation processing unit 22 performs a process of rotating (for example, rotating 90 degrees) the input image data according to the printing direction determined by the character information acquisition unit 21.

  Based on the character information acquired by the character information acquisition unit 21, the aggregation number determination unit 23 determines an aggregation number indicating the number of a plurality of document images aggregated in the input image data. Although detailed contents will be described later, in the present embodiment, the aggregation number determination unit 23 is a non-blank area including character information or includes character information for each of a plurality of unit areas obtained by dividing the input image data. The unit area is a non-blank area, and the main scanning direction (paper direction) is half the position of the input image data in the sub-scanning direction (direction perpendicular to the paper feeding direction). When the first symmetric unit region indicating the unit region corresponding to the unit region with the first reference line extending in the (feed direction) as the symmetry axis is a blank region, the first symmetric unit region is a non-blank region. Judge that there is. If the unit area is a blank area and the first symmetric unit area is a non-blank area, it is determined that the unit area is a non-blank area. The unit area is a non-blank area, and the unit area corresponding to the unit area is defined with a second reference line extending in the sub-scanning direction at a half position in the main scanning direction of the input image data as an axis of symmetry. When the second symmetric unit area shown is a blank area, it is determined that the second symmetric unit area is a non-blank area. Furthermore, when the unit area is a blank area and the second symmetric unit area is a non-blank area, it is determined that the unit area is a non-blank area. The aggregation number determination unit 23 determines that an area in which a plurality of unit areas determined to be non-blank areas is a document image area. Further, the aggregation number determination unit 23 can also variably set the size of the unit area in accordance with an operation by the user (in response to an operation received by the operation unit 60).

  The page order determination unit 24 determines the page order of the plurality of document images based on the character information included in each of the plurality of document images collected in the input image data. In the present embodiment, the page order determination unit 24 includes a page number determination unit 101, a table of contents determination unit 102, a table of contents reuse determination unit 103, a missing page determination unit 104, and a page crossing character string determination unit 105. Including.

  The page number determination unit 101 determines the page order of the plurality of document images based on the order character information, which is character information representing the number, among the character information included in each of the plurality of document images collected in the input image data. judge. Although detailed contents will be described later, the page number determination unit 101 identifies target order character information indicating the order character information included in the target document image indicating any one of the plurality of document images, and sets the target Based on the relationship between the order character information and the order character information existing at the position corresponding to the target order character information in the next page candidate document image indicating the document image that is a candidate for the next page of the target document image, the target document The page order of the image and the next page candidate document image is determined.

  The table of contents determination unit 102 determines the first document image from the shape of each of the plurality of document images collected in the input image data and the print direction of the characters, and determines the first document image and the first document image. A table of contents page is determined based on character information included in each of the next page candidate document images indicating document images that are candidates for the next page or each layout. Although the detailed contents will be described later, the table of contents determination unit 102 generates table of contents information in which a plurality of character strings included in the table of contents page are associated with the appearance order based on the character information included in the determined page of the table of contents. The order of the plurality of pages is determined based on the table of contents information and the character information included in the document image other than the table of contents page.

  The table of contents reuse determination unit 103 determines the table of contents page in the same manner as the table of contents determination unit 102, and based on the character information included in the determined table of contents page, the plurality of character strings included in the table of contents page and the appearance order Is generated, and it is determined whether or not there is a document image whose type and appearance order of the plurality of character strings included in the document image other than the table of contents page match the table of contents information. judge. Although the detailed contents will be described later, the table of contents reuse determination unit 103 matches the table of contents information with the types and appearance order of a plurality of character strings included in the document images other than the table of contents page. If there is a document image in which the size or color of any one of the plurality of character strings included in the information has changed or has not changed, based on the appearance order of the one character string, The page order of the document image is determined.

  The missing page determination unit 104 includes a plurality of document image areas corresponding one-to-one with the number of document images indicated by the aggregation number determined by the aggregation number determination unit 23 in the image data read from the document of the last page. When at least one of the document image areas is a blank area, the page order of the plurality of document images is determined according to the position of the blank area. Detailed contents will be described later.

  The page-crossing character string determination unit 105 includes a part of a page-crossing candidate character string indicating a character string represented by a predetermined number of characters or more in a plurality of document images collected in the input image data. There is a document image included at the rear end, and the remaining portion of the page-strand candidate character string is at the leading end of the next page candidate document image indicating a document image that is a candidate for the next page of the document image. If it is included, it is determined that the next page of the document image is a next page candidate document image. Detailed contents will be described later.

  The trimming processing unit 25 extracts (cuts out) each of a plurality of document images from the input image data. The storage unit 26 (first storage unit) stores a plurality of document images extracted by the trimming processing unit 25.

  The enlargement unit 27 enlarges each of the plurality of document images extracted by the trimming processing unit 25 to the original image size before aggregation. In the present embodiment, the enlargement unit 27 enlarges the plurality of document images stored in the storage unit 26 to the original image size before aggregation. In this example, since the enlargement unit 27 is arranged at the subsequent stage of the storage unit 26, the storage unit 26 stores a reduced image. As a result, the storage capacity of the storage unit 26 can be reduced (saved).

  The page order changing unit 28 rearranges the plurality of document images enlarged by the enlargement unit 27 according to the page order determined by the page order determination unit 24.

  The network I / F unit 29 has a function of transferring a plurality of document images obtained by the image processing of the present embodiment to the external device 50.

  The output image processing unit 30 has a function of processing a plurality of document images obtained by the image processing of the present embodiment. The output unit 31 has a function of outputting the image processed by the output image processing unit 30 to the printing apparatus 40 as print data.

  FIG. 3 is a flowchart illustrating an example of processing performed by the image processing apparatus 20 according to the present embodiment. First, the character information acquisition unit 21 performs OCR processing or the like on input image data (image data read from a document), and acquires character information included in the input image data (step S1). Next, the aggregation number determination unit 23 performs an aggregation number determination process for determining the aggregation number based on the character information acquired in step S1 (step S2). Specific contents of the aggregation number determination process will be described later.

  Next, the page number determination unit 101 performs a page number determination process (step S3). Specific contents of the page number determination process will be described later. If the page order is determined by the page number determination process (step S4: Yes), the process proceeds to step S12. If the page order is not determined (step S4: No), the table of contents determination unit 102 performs the table of contents determination process. This is performed (step S5). Specific contents of the table of contents determination process will be described later.

  If the page order is determined by the table of contents determination process (step S6: Yes), the process proceeds to step S12. If the page order is not determined (step S6: No), the table of contents reuse determination unit 103 determines the table of contents reuse. Processing is performed (step S7). Specific contents of the table of contents reuse determination process will be described later.

  When the page order is determined by the table of contents reuse determination process (step S8: Yes), the process proceeds to step S12. When the page order is not determined (step S8: No), the missing page determination unit 104 performs the missing page determination process. Is performed (step S9). Specific contents of the missing page determination process will be described later.

  If the page order is determined by the missing page determination process (step S10: Yes), the process proceeds to step S12. If the page order is not determined (step S10: No), the page-crossing character string determination unit 105 determines the page-crossing character. A determination process is performed (step S11). Specific contents of the page-crossing character determination process will be described later. After the page crossing character determination process, the process proceeds to step S12. The order of the table of contents determination process, the table of contents reuse determination process, the missing page determination process, and the page crossing character determination process is arbitrary, and can be performed in parallel.

  In step S12, the trimming processing unit 25 performs a trimming process for extracting each of a plurality of document images from the input image data. Next, the enlarging unit 27 performs an enlarging process for enlarging each of the plurality of document images extracted by the trimming process to the original image size before aggregation (step S13).

  Next, specific contents of the aggregation number determination process will be described. FIG. 4 is a diagram illustrating an example of target input image data. An area surrounded by a dotted line in FIG. 4 represents an area (aggregated area) where the aggregated document images are arranged, and an area displayed in gray represents an area including character information (non-blank area). Yes. In the example of FIG. 4, the aggregation number to be correctly determined is “6”.

  FIG. 5 is a diagram for explaining a first process of the aggregation number determination process. In the first process, the aggregation number determination unit 23 divides the main scanning direction at a certain interval Δy (this interval can be arbitrarily set). Then, the divided areas in the main scanning direction are obtained by using the character information acquisition result by the character information acquisition unit 21, an area including character information (non-blank area), and an area not including character information (blank area). Classify into:

  FIG. 6 is a diagram for explaining the second process after the first process. In the second step, the aggregation number determination unit 23 divides the sub-scanning direction at a certain interval Δx (this interval can be arbitrarily set). Then, the divided areas in the sub-scanning direction are divided into an area including character information (non-blank area) and an area not including character information (blank area) using the character information acquisition result by the character information acquisition unit 21. Classify into:

  FIG. 7 is a diagram for explaining a third process of the aggregation number determination process. In general, the arrangement of original images on an integrated original is symmetrical with respect to the top, bottom, left and right. Using this, in the third process, the result of the second process is folded back at the sub-scanning center, and the sum of the non-blank areas is obtained.

  That is, the aggregation number determination unit 23 determines, for each of a plurality of unit areas obtained by dividing the input image data, whether it is a non-blank area including character information or a blank area not including character information, A first unit area that is a non-blank area and indicates a unit area corresponding to the unit area with a first reference line extending in the main scanning direction at a half position in the sub-scanning direction of the input image data. When the symmetric unit area is a blank area, it is determined that the first symmetric unit area is a non-blank area. If the unit area is a blank area and the first symmetric unit area is a non-blank area, it is determined that the unit area is a non-blank area. As a result, even if a unit area that happens to be a blank area in the aggregated area is a non-blank area when the first symmetric unit area corresponding to the first reference line as a symmetry axis is a non-blank area, Can also be determined to be an area to be aggregated (area where document images are arranged), in which a plurality of unit areas determined to be non-blank areas are collected. .

  FIG. 8 is a diagram for explaining a fourth process of the aggregation number determination process. In the fourth process, the result of the second process is folded back at the main scanning center, and the sum of the non-blank areas is obtained. That is, the aggregation number determination unit 23 determines, for each of a plurality of unit areas obtained by dividing the input image data, whether it is a non-blank area including character information or a blank area not including character information, A second unit area that is a non-blank area and that indicates a unit area corresponding to the unit area with a second reference line extending in the sub-scanning direction at a half position in the main scanning direction of the input image data as an axis of symmetry; If the symmetric unit area is a blank area, it is determined that the second symmetric unit area is a non-blank area. If the unit area is a blank area and the second symmetric unit area is a non-blank area, the unit area is determined to be a non-blank area. In the processing so far, when the shape of the aggregated region is not a rectangle (when there is a dent), the shape is corrected to a rectangle. Further, paying attention to the fact that the shape of each aggregated region is usually the same, the region shape is corrected using the maximum repair length of all regions. For areas that are too thin, further processing such as merging with surrounding areas or correction by comparison with a general arrangement pattern may be performed.

  9 to 11 are flowcharts of the aggregation determination process. As shown in FIG. 9, first, the aggregation number determination unit 23 sets a determination line interval Δy (step S20). Next, the aggregation number determination unit 23 pays attention to a region Δy from the top in the sub-scanning direction (region for the main scanning length) in the input image data (step S21), and the character information acquisition unit 21 performs character information Using the obtained result, it is determined whether or not the focused area (focused area) includes character information (step S22). When the attention area includes character information (step S22: Yes), it is determined that the attention area is a non-blank area (step S23). If the region of interest does not include character information (step S22: No), it is determined that the region of interest is a blank region (step S24).

  Then, the aggregation number determination unit 23 determines whether or not attention has been paid to the entire document (input image data) (step S25). If the entire document has not been focused (step S25: No), the focused area is shifted downward by Δy (step S26), and the processing from step S22 onward is repeated.

  When attention has been paid to the entire document (step S25: Yes), the aggregation number determination unit 23 sets the determination column interval Δx (step S27). Next, the aggregation number determination unit 23 pays attention to a region corresponding to Δx from the head in the main scanning direction (region corresponding to the sub-scanning length) in the input image data (step S28), and character information obtained by the character information acquisition unit 21 is displayed. Using the obtained result, it is determined whether or not the region of interest includes character information (step S29). When the attention area includes character information (step S29: Yes), it is determined that the attention area is a non-blank area (step S30). If the region of interest does not include character information (step S29: No), it is determined that the region of interest is a blank region (step S31).

  Then, the aggregation number determination unit 23 determines whether or not attention has been paid to the entire document (step S32). If the entire document has not been focused (step S32: No), the focused area is shifted to the right by Δx (step S33), and the processing from step S29 is repeated. If attention has been paid to the entire document (step S32: Yes), the flow proceeds to the flow of FIG.

  As shown in FIG. 10, the aggregation number determination unit 23 sets a region (unit region) of Δx from the top in the main scanning direction and Δy from the top in the sub-scanning direction of the input image data as a region of interest (Step S40). . Next, the aggregation number determination unit 23 determines whether or not the region of interest is a non-blank region (step S41). When the attention area is a non-blank area (step S41: Yes), the aggregation number determination unit 23 uses the first reference line (a reference line extending in the main scanning direction at a half position in the sub-scanning direction) as the symmetry area. It is determined whether or not the first symmetrical unit area corresponding to is a blank area (step S42). When the first symmetric unit region corresponding to the region of interest is a blank region (step S42: Yes), the first symmetric unit region is set as a non-blank region (step S43).

  On the other hand, in the above-described step S41, when the attention area is a blank area (step S41: No), the aggregation number determination unit 23 determines whether or not the first symmetric unit area corresponding to the attention area is a non-blank area. Is determined (step S44). When the first symmetrical unit area corresponding to the attention area is a non-blank area (step S44: Yes), the attention area is set as a non-blank area (step S45).

  Then, the aggregation number determining unit 23 determines whether or not the region of interest is the rear end (the rear end of the row) in the main scanning direction (step S46). If the region of interest is not the rear end in the main scanning direction (step S46: No), the aggregation number determination unit 23 shifts the region of interest by Δx to the right (step S47), and repeats the processing after step S41. When the region of interest is the rear end in the main scanning direction (step S46: Yes), the aggregation number determination unit 23 determines whether or not the region of interest is the rear end in the sub-scanning direction (the rear end of the column) ( Step S48). If the region of interest is not the rear end in the sub-scanning direction (step S48: No), the aggregation number determination unit 23 shifts the region of interest to the left by the main scanning length and downward by Δy (step S49), and after step S41 Repeat the process.

  When the region of interest is the rear end in the sub-scanning direction (step S48: Yes), the aggregation number determination unit 23 again performs Δx from the head of the input image data in the main scanning direction and Δy from the head in the sub-scanning direction. A region (unit region) is set as a region of interest (step S50). Next, the aggregation number determination unit 23 determines whether or not the region of interest is a non-blank region (step S51). When the attention area is a non-blank area (step S51: Yes), the aggregation number determination unit 23 uses the second reference line (a reference line extending in the sub-scanning direction at a half position in the main scanning direction) as the symmetry area. It is determined whether or not the second symmetric unit area corresponding to is a blank area (step S52). If the second symmetric unit region corresponding to the region of interest is a blank region (step S52: Yes), the second symmetric unit region is set as a non-blank region (step S53).

  On the other hand, in the above-described step S51, when the target area is a blank area (step S51: No), the aggregation number determination unit 23 determines whether the second symmetric unit area corresponding to the target area is a non-blank area. Is determined (step S54). When the second symmetrical unit region corresponding to the region of interest is a non-blank region (step S54: Yes), the region of interest is set as a non-blank region (step S55).

  Then, the aggregation number determination unit 23 determines whether or not the region of interest is the rear end in the main scanning direction (step S56). If the region of interest is not the rear end in the main scanning direction (step S56: No), the aggregation number determination unit 23 shifts the region of interest to the right by Δx (step S57), and repeats the processing after step S51. When the region of interest is the rear end in the main scanning direction (step S56: Yes), the aggregation number determination unit 23 determines whether the region of interest is the rear end in the sub-scanning direction (step S58). If the region of interest is not the rear end in the sub-scanning direction (step S58: No), the aggregation number determination unit 23 shifts the region of interest to the left by the main scanning length and downward by Δy (step S59), and after step S51 Repeat the process. When the region of interest is the rear end in the sub-scanning direction (step S58: Yes), the flow proceeds to the flow in FIG. The aggregation number determination unit 23 can determine that a set of unit areas determined to be a non-blank area is an area to be aggregated (original image area). Note that the order of the series of processes from step S40 to step S49 and the series of processes from step S50 to step S59 may be reversed.

  As illustrated in FIG. 11, the aggregation number determination unit 23 determines whether or not the interval between the areas determined as the aggregated areas is narrower than a specified value (step S61). If the interval between the regions is narrower than the specified value (step S61: Yes), the regions are combined with each other as a non-blank region (step S62).

  Next, the aggregation number determination unit 23 determines whether or not each area (aggregated area) has a dent (step S63). When there is a dent in each area (step S63: Yes), the dent is made a non-blank area and the area shape is corrected to a rectangle (step S64). Next, the aggregation number determination unit 23 determines whether or not each region has a convex portion (step S65). When there is a convex portion in each region (step S65: Yes), the aggregation number determination unit 23 corrects the region to a rectangle according to the convex portion (step S66).

  Next, the aggregation number determination unit 23 performs correction to match the main scanning width of each region with the maximum region (step S67). Next, the aggregation number determination unit 23 performs correction to match the sub-scanning width of each area with the maximum area (step S68).

  Next, specific contents of the page number determination process will be described. FIG. 12 is an image diagram of image data (input image data) read from six originals arranged side by side. Each collected document image includes order character information, which is character information representing a number, such as a chapter number of a title, an itemized number, and a page number.

  The page number determination unit 101 determines the first (first) document image from the shape of each of the plurality of document images determined by the aggregation determination process (the shape of each aggregated area) and the character printing direction. For example, if the shape of each aggregated area is rectangular and the character printing direction is horizontal (that is, horizontal writing), is the first original image placed at the upper left and the original image of the next page placed from the right to the right? In general, the original image of the next page is arranged in the downward direction from there, and the original image of the next page is arranged in the upper and lower directions from the first original image. Do not line up. Using this, as a next page candidate document image indicating a document image that is a candidate for the next page of the first document image, a document image arranged on the right side of the target document image and arranged immediately below the target document image The selected original image can be selected.

  Next, the page number determination unit 101 sets the first document image as a target document image, and identifies target sequence character information that is sequence character information included in the target document image. If there is order character information that is larger than the number indicated by the target order character information at the position corresponding to the target order character information in the next page candidate document image and indicates the same type number, the target order character information The information is combined with the order character information existing at the position corresponding to the target order character information in the next page candidate document image. In the example of FIG. 12, the chapter number “1.1” arranged at the upper left of the upper left original image (target original image) that is the first page and the page number “3” arranged at the lower right are as follows. Since there is order character information indicating the next page candidate document image on the right side and the document image immediately below the corresponding document image, it is included in the target document image among the next page candidate document images. If there is order character information that is larger than the number indicated by the target order character information and has the same type number at the position corresponding to the target order character information (target order character information), The next page candidate document image is combined with the order character information existing at the position corresponding to the target order character information.

  The page number determination unit 101 finds a plurality of combinations for each set of the target document image and the next page candidate document image, and determines the next page candidate document image that becomes the next page of the target document image. As a determination criterion, the next page candidate document image with the larger number of combinations may be determined as the next page of the target document image, and weighting according to the combination direction (horizontal direction, vertical direction) is performed. Thus, an evaluation value may be calculated for each combination, and the next page candidate document image having a larger sum of evaluation values may be determined as the next page of the target document image. For example, when there is a high possibility of using a horizontal arrangement for a horizontally long sheet, weighting may be performed so that the evaluation value of the combination in the horizontal direction is higher than the evaluation value of the combination in the vertical direction. However, the present invention is not limited to this, and weighting may be performed according to, for example, a user operation. In addition, when there is order character information indicating a number one larger than the number indicated by the target order character information at the position corresponding to the target order character information in the next page candidate document image, the evaluation value of the combination is high. Weighting can also be performed. As described above, the page number determination unit 101 determines the page order of a plurality of document images by determining the document image of the next page of the target document image while switching the target document image.

  FIG. 13 is a flowchart of the page number determination process. As shown in FIG. 13, the page number determination unit 101 first focuses on the first (first) document image (step S70). In the following description, the focused document image is referred to as a target document image. Next, the page number determination unit 101 pays attention to any order character information in the target document image (step S71). In the following description, the target order character information in the target document image is referred to as target order character information. The page number determination unit 101 determines whether or not the order character information exists at the same position as the target order character information in the next page candidate document image indicating the document image that is a candidate for the next page of the target document image. (Step S72). When the order character information does not exist (step S72: No), it is determined that there is no relevance (cannot be combined) (step S78).

  In step S72, when the order character information exists (step S72: Yes), it is determined whether the number type indicated by the order character information matches the number type indicated by the target order character information ( Step S73). If the types do not match (step S73: No), it is determined that there is no relationship (step S78). If the types match (step S73: Yes), it is determined whether or not the number indicated by the order character information existing at the same position as the target order character information is greater than the number indicated by the target order character information ( Step S74). If not increased (step S74: No), it is determined that there is no relevance (step S78). If it has increased (step S74: Yes), it is determined whether or not the increase amount is 1 (step S75). When the increase amount is not 1 (step S75: No), the target order character information and the order character information existing at the same position as the target order character information in the next page candidate document image are combined, but the relevance is It is determined that it is weak (step S76). When the increase amount is 1 (step S75: Yes), the target order character information and the order character information existing at the same position as the target order character information in the next page candidate document image are combined, and the relationship is strong. (Step S77).

  Then, the page number determination unit 101 determines whether or not attention is paid to all the order character information in the target document image (step S79). When not paying attention to all the order character information (step S79: No), the page number determination unit 101 updates the target order character information (step S80), and repeats the processing after step S72. When attention is paid to all the order character information (step S79: Yes), the page number determination unit 101 determines whether or not attention is paid to all document images (step S81). When not paying attention to all the original images (step S81: No), the page number determination unit 101 updates the target original image (step S82) and repeats the processing after step S71. When all document images are focused (step S81: Yes), the page number determination unit 101 determines the page order of a plurality of document images based on the number of combinations and the strength of relevance (step S83).

  Next, specific contents of the table of contents determination process will be described. FIG. 14 is an image diagram of image data (input image data) read from six documents arranged side by side. The first page (the upper left document image in this example) is the table of contents page.

  FIG. 15 is an image diagram of the table of contents determination process. In this example, the table of contents determination unit 102 includes “table of contents”, “agenda”, and the like in the next page candidate document image indicating a document image that is a candidate for the first page or the next page of the first page. Then, it is determined whether or not one or more character information representing a predetermined character string for the table of contents exists, and a document image including one or more character information representing the character string for the table of contents is a table of contents page. Is determined. If necessary, the table of contents page may be determined by comparing the layouts in the screen with other document images. In the example of FIG. 15, it is determined that the first page is the table of contents page. Then, the table of contents determination unit 102 generates table of contents information in which a plurality of character strings included in the page of the table of contents and the order of appearance are associated with each other based on the character information included in the page of the table of contents. The order of a plurality of pages is determined based on the character information included in the document image other than the current page.

  FIG. 16 is a flowchart of the table of contents determination process. First, the table of contents determination unit 102 pays attention to the leading document image (step S90). For the sake of convenience of explanation, in this example, the document image arranged at the upper left in FIG. 15 is the first document image, and the document image arranged immediately to the right and directly below is the next document image that is a candidate for the next page. It is assumed that it is a page candidate document image. In the following description, one of the two next page candidate document images is referred to as a “first next page candidate document image”, and the other is referred to as a “second next page candidate document image”. In the following description, the focused document image is referred to as “target document image”.

  Next, the table of contents determination unit 102 determines whether or not there is one or more character information representing a character string for the table of contents in the target document image (step S91). If there is no one or more pieces of character information representing a table of contents character string (step S91: No), the process proceeds to step S95 described later. If there is one or more character information representing a character string for the table of contents (step S91: Yes), it is determined whether or not the character printing direction of the target document image is horizontal (horizontal writing) (step S92). When the character printing direction of the target document image is the horizontal direction (step S92: Yes), the table of contents determination unit 102 sequentially looks from the top of the target document image in the sub-scanning direction, The table of contents information associated with the appearance order is generated and stored (step S93). If the character printing direction of the target document image is not the horizontal direction (step S92: No), that is, in the case of vertical writing, the table of contents determination unit 102 sequentially looks from the right in the main scanning direction of the target document image. Then, the table of contents information in which the character string that appears and the order of appearance is associated is generated and stored (step S94).

  Next, the table of contents determination unit 102 determines whether or not attention has been paid to the first next page candidate document image (step S95). When attention has not been paid to the first next page candidate document image (step S95: No), the table of contents determination unit 102 pays attention to the first next page candidate document image (step S96), and the processing after step S91. repeat. When attention has been paid to the first next page candidate document image (step S95: Yes), the table of contents determination unit 102 determines whether attention has been paid to the second next page candidate document image (step S97). ). When attention has not been paid to the second next page candidate document image (Step S97: No), attention is paid to the second next page candidate document image (Step S98), and the processes after Step S91 are repeated. When attention has been paid to the second next page candidate area (step S97: Yes), the table of contents determination unit 102 determines whether or not a character string included in the table of contents information exists in the document image other than the page of the table of contents. (Step S99), and if there is a character string included in the table of contents information (step S99: Yes), the page order of the original image is determined according to the appearance order of the character string (step S100).

  Next, specific contents of the table of contents reuse determination process will be described. FIG. 17 is an image diagram of image data (input image data) read from a six-sheet original arranged side by side. The first page (in this example, the upper left original image) is the table of contents page, and the following pages A document image in which the appearance order of the plurality of character strings included therein matches the table of contents information and the color of any one of the plurality of character strings included in the table of contents information is changed. Existing. Reuse the table of contents information and change the color of some character strings (for example, make only one character string red), or do not change the color of some character strings (for example, characters other than some of the character strings) It is common to lighten the color of the columns) and to change the size as well. The table-of-contents reuse determination unit 103 includes a plurality of character strings included in the document image other than the table of contents page, the appearance order of which matches the table of contents information, and the plurality of character strings included in the table of contents information. If there is a document image in which the size or color of any one character string has changed or has not changed, the page order of the document image is determined based on the appearance order of the one character string.

  FIG. 18 is a flowchart of the table of contents reuse determination process. First, the table of contents reuse determination unit 103 focuses on the first document image (step S110). For the sake of convenience of explanation, in this example, the document image arranged at the upper left in FIG. 6 is the first document image, and the document image arranged at the right and directly below the next image indicates a document image that is a candidate for the next page. It is assumed that it is a page candidate document image. In the following description, one of the two next page candidate document images is referred to as a “first next page candidate document image”, and the other is referred to as a “second next page candidate document image”. In the following description, the focused document image is referred to as “target document image”.

  Next, the table of contents reuse determination unit 103 determines whether or not there is one or more character information representing a character string for the table of contents in the target document image (step S111). If the target document image does not include one or more pieces of character information representing a table of contents character string (step S111: No), the process proceeds to step S113 described later. On the other hand, when the target document image includes one or more pieces of character information representing a text string for the table of contents (step S111: Yes), the table of contents reuse determination unit 103 determines that the target document image is a page of the table of contents. Then, the table of contents information in which the character string appearing in the target document image is associated with the appearance order is generated and stored (step S112).

  Next, the table of contents reuse determination unit 103 determines whether or not the table of contents page has been found (step S113). First, the case where the table of contents page is found (step S113: Yes) will be described. In this case, the table of contents reuse determination unit 103 determines whether or not attention has been paid to the first next page candidate document image (step S114). When attention has not been paid to the first next page candidate document image (step S114: No), the table of contents reuse determination unit 103 focuses on the first next page candidate document image (step S115) and performs steps subsequent to step S111. Repeat the process. If attention has been paid to the first next page candidate document image (step S114: Yes), the table of contents reuse determination unit 103 determines whether or not attention has been paid to the second next page candidate document image (step S114). S116). When attention has not been paid to the second next page candidate document image (step S116: No), attention is paid to the second next page candidate document image (step S117), and the processes after step S111 are repeated. When the second next page candidate area has been focused (step S116: Yes), the table of contents reuse determination unit 103 determines that there is no page of the table of contents (step S118), and ends the process.

  Next, a case where the table of contents page is not found (step S113: No) will be described. In this case, the table of contents reuse determination unit 103 determines whether or not there is a document image whose character string and appearance order match the table of contents information among document images other than the table of contents page (step S119). ). When there is a document image whose appearance order matches the table of contents information among the document images other than the page of the table of contents (step S119: Yes), the table of contents reuse determination unit 103 re-reads the table of contents information. It is determined that the document is in use, and attention is paid to the document image (step S120).

  Next, the table of contents reuse determination unit 103 determines whether the size or color of any one of the plurality of character strings included in the table of contents information has changed in the document image (target document image) focused in step S120. It is determined whether or not (step S121). If the size or color of any one character string has changed (step S121: Yes), the table of contents reuse determination unit 103 determines the page order of the target document image based on the appearance order of the one character string. (Step S123). If the determination result in step S121 is negative (step S121: No), the table of contents reuse determination unit 103 determines the size of any one character string among a plurality of character strings included in the table of contents information in the target document image. Alternatively, it is determined whether or not the color has changed (step S122). When the size or color of any one character string has not changed (step S122: Yes), the table of contents reuse determination unit 103 determines the page order of the target document image based on the appearance order of the one character string. (Step S123).

  Next, specific contents of the missing page determination process will be described. FIG. 19 is an image diagram showing image data read from the document of the last page among a plurality of documents obtained by aggregate printing, where the number of original documents before aggregation is a multiple of 6 + 4. The missing page determination unit 104 includes a plurality of document image areas (one to one corresponding to the number of document images indicated by the aggregation number determined by the aggregation number determination unit 23 in the image data read from the document of the last page). If at least one document image area is a blank area, a missing page determination process for determining the page order of a plurality of document images is performed according to the position of the blank area.

  Next, specific contents of the cross-page character determination process will be described. When sentences are gathered instead of presentation materials, character strings often straddle between pages. By paying attention to this feature, the accuracy of determining the page arrangement order can be increased. In the example of FIG. 20, the phrase “image forming apparatus” appears in the document. In this process, a character string represented by a certain number of characters or more among character strings existing on the page is stored in advance as a page-strand candidate character string. If a character string corresponding to a part of the stored page-stretching candidate character string is at the rear end of the document image (target document image) of interest, a document image that is a candidate for the next page of the target document image is selected. The first character string of the next page candidate document image shown is confirmed, and if it matches the remaining part, it can be determined that there is continuity between the target document image and the next page candidate document image . Using this, the arrangement order can be determined.

  As described above, in the present embodiment, based on the character information included in the input image data, the aggregation number indicating the number of document images aggregated in the input image data is determined, and the aggregated plural The page order of the plurality of document images is determined based on the character information included in each of the document images. Accordingly, it is possible to appropriately restore the same size without generating and printing information other than the reduced plurality of document images.

  Although the embodiments according to the present invention have been described above, the present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. Various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the above-described embodiments. For example, some components may be deleted from all the components shown in the embodiment.

  Note that the page order determination unit 24 only needs to include at least the page number determination unit 101, and other components (a table of contents determination unit 102, a table of contents reuse determination unit 103, a missing page determination unit 104, a page-crossing character) The column determination unit 105) may not be provided, and any one or more of the other constituent elements may be selectively provided.

  Further, for example, a second storage unit that stores a plurality of document images enlarged by the enlargement unit 27 without the page order change unit 28 is provided, and according to the page order determined by the page order determination unit 24. The document image stored in the second storage unit may be taken out.

  Further, for example, an aggregation number setting unit that changes the setting value of the aggregation number in accordance with an operation by the user (operation received by the operation unit 60) may be provided.

  In addition, for example, a page deletion unit that deletes any one of a plurality of document images to be restored at the same magnification may be provided in accordance with an operation by the user.

  The program executed by the image processing apparatus 20 (CPU 201) of the above-described embodiment is a file in an installable format or an executable format, and is a CD-ROM, flexible disk (FD), CD-R, DVD (Digital). It may be configured to be recorded and provided on a computer-readable recording medium such as Versatile Disk (USB) or USB (Universal Serial Bus), or may be configured to be provided or distributed via a network such as the Internet. Good. Various programs may be provided by being incorporated in advance in a ROM or the like.

1 MFP
10 Document Reading Device 20 Image Processing Device 21 Character Information Acquisition Unit 22 Rotation Processing Unit 23 Aggregation Number Determination Unit 24 Page Order Determination Unit 25 Trimming Processing Unit 26 Storage Unit 27 Enlargement Unit 28 Page Order Change Unit 29 Network I / F Unit 30 Output Image processing unit 31 Output unit 40 Printing device 60 Operation unit 101 Page number determination unit 102 Table of contents determination unit 103 Table of contents reuse determination unit 104 Missing page determination unit 105 Cross-page character string determination unit 201 CPU
202 ROM
203 RAM
204 Blank Paper Detection Processing Circuit 205 Rotation Processing Circuit 206 Scaling Processing Circuit 207 Trimming Processing Circuit 208 Network I / F Circuit 209 Output Image Processing Circuit

JP 2004-282668 A

Claims (10)

A character information acquisition unit that acquires character information indicating characters included in image data read from a document;
An aggregation number determination unit that determines an aggregation number indicating the number of a plurality of document images aggregated in the image data based on the character information acquired by the character information acquisition unit;
A page order determination unit that determines a page order of the plurality of document images based on the character information included in each of the plurality of document images.
Image processing device. The aggregation number determination unit
For each of a plurality of unit areas obtained by dividing the image data,
Determining whether it is a non-blank area including the character information or a blank area not including the character information;
The unit area is the non-blank area, and the unit area corresponding to the unit area is defined with a first reference line extending in the main scanning direction at a half position in the sub-scanning direction of the image data as an axis of symmetry. If the first symmetric unit region is the blank region, determine that the first symmetric unit region is the non-blank region,
When the unit area is the blank area and the first symmetric unit area is the non-blank area, it is determined that the unit area is the non-blank area;
The unit area is the non-blank area and corresponds to the unit area with a second reference line extending in the sub-scanning direction at a half position in the main scanning direction of the image data as an axis of symmetry. When the second symmetric unit region indicating is the blank region, it is determined that the second symmetric unit region is the non-blank region,
If the unit area is the blank area and the second symmetric unit area is the non-blank area, it is determined that the unit area is the non-blank area;
Determining an area where the plurality of unit areas determined to be the non-blank area are an area of the document image;
The image processing apparatus according to claim 1. The aggregation number determination unit variably sets the size of the unit area in accordance with an operation by a user.
The image processing apparatus according to claim 2. The page order determination unit
A page number determination unit that determines the page order of the plurality of document images based on the order character information that is the character information representing the number of the character information included in each of the plurality of document images;
The image processing apparatus according to claim 1. The page number determination unit identifies target order character information indicating the order character information included in a target document image indicating any one of the plurality of document images, and the target order character information; The target document image is based on the relationship with the sequence character information existing at a position corresponding to the target sequence character information among the next page candidate document images indicating document images that are candidates for the next page of the target document image. And determining the page order of the next page candidate document image,
The image processing apparatus according to claim 4. The page order determination unit
The leading document image is determined from the shape of each of the plurality of document images and the character printing direction, and the leading document image and the document image that is a candidate for the next page of the leading document image are indicated. A table of contents content determination unit that determines a page of a table of contents based on the character information included in each of the next page candidate document images or each layout;
The image processing apparatus according to claim 4 or 5. The table of contents determination unit generates table of contents information in which a plurality of character strings included in the table of contents page are associated with the appearance order based on the character information included in the table of contents page, and the table of contents information Determining the page order of the plurality of document images based on the character information included in the document images other than the table of contents pages;
The image processing apparatus according to claim 6. The page order determination unit
The first document image is determined from the shape of each of the plurality of document images aggregated in the image data and the printing direction of characters, and the first document image and the next page of the first document image are determined. Based on the character information contained in each of the next page candidate manuscript images indicating candidate manuscript images or the respective layouts, a table of contents page is determined and the character information contained in the table of contents page To generate a table of contents information in which a plurality of character strings included in the table of contents page are associated with an appearance order, and among a plurality of document images other than the page of the table of contents, a plurality of character strings included therein A table of contents reuse determination unit for determining whether or not there is a document image whose appearance order matches the table of contents information;
The image processing apparatus according to claim 4. A character information acquisition step for acquiring character information indicating characters included in the image data read from the document;
An aggregation number determination step of determining an aggregation number indicating the number of document images aggregated in the image data based on the character information acquired in the character information acquisition step;
A page order determination step for determining a page order of the plurality of document images based on the character information included in each of the plurality of document images included in the image data.
Image processing method. On the computer,
A character information acquisition step for acquiring character information indicating characters included in the image data read from the document;
An aggregation number determination step of determining an aggregation number indicating the number of document images aggregated in the image data based on the character information acquired in the character information acquisition step;
A program for executing a page order determination step for determining a page order of the plurality of document images based on the character information included in each of the plurality of document images.