JP7447472B2 - Image processing device and image processing program - Google Patents

Description

The present invention relates to an image processing device and an image processing program.

For example, Patent Document 1 describes an accounting processing system that reads image data of one or more original documents such as receipts or receipts captured by a digital camera or a camera of a mobile terminal, or image data captured by a scanner device. has been done. This accounting processing system includes a voucher image extraction means for extracting voucher parts from image data, a shaping means for correcting the tilt and distortion of the clipped voucher image and shaping it into a rectangle, and a voucher image registration for saving the shaped voucher image. have the means and. In addition, in the normal mode, this evidence image cutting means attempts to cut out the evidence image from the image data using the first set of receipt extraction threshold values, and when the voucher image cannot be cut out from the image data using the first set, Next, a second set of receipt extraction thresholds in which the variation width of the receipt extraction thresholds is changed is used to try to cut out the evidence image from the image data.

Further, Patent Document 2 describes a clustering device that performs clustering similar to human intuition. This clustering device includes a data input section that inputs multidimensional data, an initial cluster generation section that divides the multidimensional data and generates a plurality of clusters, a cluster recording section that records each generated cluster, and a cluster recording section that records each cluster. a cluster selection unit that calculates parameters of a model given in advance from data belonging to the cluster for each of the clusters, and selects clusters to be integrated from the parameter values calculated for each cluster; and a cluster evaluation unit that calculates evaluation values of cluster sets in the cluster recording unit.

Further, Patent Document 3 describes an image processing device that improves the accuracy of extracting a document image. This image processing device includes a first extracting means for extracting a first region having low frequency characteristics of an image including a plurality of original images, and a second extracting means for extracting a second region having high frequency characteristics of the image. The image forming apparatus includes an extraction means and a third extraction means for extracting an area of the document image by combining the first area and the second area depending on whether the background of the image is white or not.

Patent No. 6539844 Japanese Patent Application Publication No. 2006-350730 Japanese Patent Application Publication No. 2018-085676

By the way, when a document such as a receipt or receipt is placed on a platen glass and read, the edges of the read image of the document may not be extracted. In this case, it is difficult to integrate multiple areas of the read image according to the type of document.

SUMMARY OF THE INVENTION An object of the present invention is to provide an image processing device and an image processing program that can integrate multiple areas of a read image according to the type of document even when edges cannot be extracted from the read image of the document. shall be.

In order to achieve the above object, an image processing apparatus according to a first aspect includes a processor, the processor detects a plurality of areas having foreground-like features from a read image obtained by reading a document, For each combination of two regions obtained from a plurality of regions, derive the straight-line distance between the outer edge of one region and the outer edge of the other region, and for each combination of the two regions, calculate the distance between the one region and the outer edge of the other region. The area of the gap, which is the part where the one region and the other region do not exist, is derived from the area of the inclusion region, which is a region of a predetermined shape that includes the other region, and For each, a combination in which the linear distance is within a predetermined range and the area of the gap is the smallest is selected and integrated.

Further, in the image processing device according to the second aspect, in the image processing device according to the first aspect, the processor performs predetermined Based on the characteristics of each type of document, it is determined whether or not the document can be integrated.

Further, in the image processing apparatus according to a third aspect, in the image processing apparatus according to the second aspect, the characteristic is expressed as an allowable value of document size, and the processor is configured to determine the size of each of the plurality of combinations, and the image processing apparatus according to the second aspect. When comparing the allowable values, the allowable values are compared in ascending order, and based on the comparison result, it is determined whether each of the plurality of combinations can be integrated.

Further, in the image processing apparatus according to a fourth aspect, in the image processing apparatus according to the second aspect or the third aspect, the original document is a plurality of original documents, and the processor arranges the plurality of original documents. If the conditions are defined in advance, the placement conditions are further used to determine whether or not the integration is possible.

Further, in the image processing apparatus according to a fifth aspect, in the image processing apparatus according to any one of the first to fourth aspects, the processor uses a filter capable of detecting the foreground-likeness feature, Detecting the plurality of regions.

In addition, in the image processing device according to a sixth aspect, in the image processing device according to the fifth aspect, the filter converts the brightness of the n×n (n is an odd number of 3 or more) center pixel to the n×n including the center pixel. An expansion filter that replaces the brightness with the maximum brightness among n pixels, and a brightness of the center pixel of n×n (n is an odd number of 3 or more) with the minimum brightness among the n×n pixels including the center pixel. It is said to be a filter that is a combination of a replacement contraction filter and a replacement filter.

Further, in the image processing device according to a seventh aspect, in the image processing device according to any one of the first to sixth aspects, the straight line distance is between the outer edge of the one region and the other region. It is said that this is the minimum distance between the outer edge and the outer edge.

Further, in the image processing device according to an eighth aspect, in the image processing device according to any one of the first to seventh aspects, the predetermined shape of the inclusion area is the one area and the one area. It is assumed that the region is a circumscribed rectangle that circumscribes each of the other regions.

Furthermore, in order to achieve the above object, the image processing program according to the ninth aspect detects a plurality of regions having foreground-like characteristics from a read image obtained by reading a document, and detects a plurality of regions having foreground-like characteristics. For each combination of two regions, derive the straight-line distance between the outer edge of one region and the outer edge of the other region, and for each combination of the two regions, include the one region and the other region. The area of the gap, which is the part where the one region and the other region do not exist, is derived from the area of the inclusion region, which is a region with a predetermined shape, and the linear distance is calculated for each of the plurality of regions. is within a predetermined range and the area of the gap is the smallest, and the computer selects and integrates the combinations.

According to the first aspect and the ninth aspect, even if an edge cannot be extracted from a read image of a document, it is possible to integrate a plurality of regions of the read image according to the type of document.

According to the second aspect, there is an effect that it is possible to accurately determine whether or not to integrate according to the type of document, compared to the case where the characteristics of each type of document are not considered.

According to the third aspect, there is an effect that it is possible to accurately determine whether or not to integrate according to the type of document, compared to the case where the document size is compared in descending order of allowable value.

According to the fourth aspect, there is an effect that it is possible to accurately determine whether or not to integrate documents according to the type of documents, compared to a case where the arrangement conditions of a plurality of documents are not considered.

According to the fifth aspect, it is possible to appropriately detect a plurality of regions having foreground-like features compared to the case where no filter is used.

According to the sixth aspect, it is possible to appropriately detect a plurality of regions having foreground-like features compared to a case where a filter that is a combination of an expansion filter and a contraction filter is not used.

According to the seventh aspect, there is an effect that a plurality of regions of a read image can be appropriately integrated, compared to a case where the straight-line distance is not set to the minimum distance.

According to the eighth aspect, there is an effect that a plurality of regions of a read image can be appropriately integrated, compared to a case where the shape of the included region is not a circumscribed rectangle.

FIG. 1 is a block diagram illustrating an example of an electrical configuration of an image processing device according to an embodiment. FIG. 3 is a diagram illustrating a state in which a plurality of areas in read images of a plurality of receipts are integrated. FIG. 1 is a block diagram illustrating an example of a functional configuration of an image processing device according to an embodiment. FIG. 3 is a diagram for explaining area detection processing according to the embodiment. (A) is a diagram for explaining a method for deriving a straight-line distance according to an embodiment. (B) is a diagram showing an example of a straight-line distance matrix according to the embodiment. (A) is a diagram for explaining a method for deriving a gap area according to an embodiment. (B) is a diagram showing an example of a gap area matrix according to the embodiment. (A) is a diagram showing the relationship between a straight-line distance matrix and a plurality of regions according to the embodiment. (B) is a diagram showing the relationship between the straight-line distance matrix and the gap area matrix according to the embodiment. (A) is a diagram illustrating an example of the relationship between a combination of areas and document size according to the embodiment. (B) is a diagram showing another example of the relationship between the combination of areas and the document size according to the embodiment. (C) is a diagram showing still another example of the relationship between the combination of areas and the document size according to the embodiment. FIG. 6 is a diagram illustrating recalculation in the integration process according to the embodiment. 3 is a flowchart illustrating an example of the flow of processing by an image processing program according to an embodiment.

EMBODIMENT OF THE INVENTION Hereinafter, with reference to drawings, an example of the form for implementing this invention is demonstrated in detail.

FIG. 1 is a block diagram showing an example of the electrical configuration of an image processing apparatus 10 according to this embodiment.

As shown in FIG. 1, the image processing device 10 according to the present embodiment includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, and an input/output interface (I/O interface). /O) 14, a storage section 15, a display section 16, an operation section 17, a document reading section 18, and a communication section 19.

For example, a document reading device integrally provided with a document reading section 18 is applied to the image processing device 10 according to the present embodiment. Further, the document reading section 18 may be provided separately. In this case, a general-purpose computer device such as a server computer or a personal computer (PC) is applied to the image processing device 10, for example.

The CPU 11, ROM 12, RAM 13, and I/O 14 are each connected via a bus. Each functional section including a storage section 15, a display section 16, an operation section 17, a document reading section 18, and a communication section 19 is connected to the I/O 14. Each of these functional units can communicate with the CPU 11 via the I/O 14.

A control unit is configured by the CPU 11, ROM 12, RAM 13, and I/O 14. The control unit may be configured as a sub-control unit that controls a part of the operation of the image processing device 10, or may be configured as a part of a main control unit that controls the entire operation of the image processing device 10. . For example, an integrated circuit such as an LSI (Large Scale Integration) or an IC (Integrated Circuit) chipset is used for a part or all of each block of the control section. Individual circuits may be used for each of the above blocks, or a part or all of them may be integrated. Each of the blocks described above may be provided integrally, or some blocks may be provided separately. Moreover, in each of the above-mentioned blocks, a part thereof may be provided separately. The integration of the control section is not limited to LSI, but a dedicated circuit or a general-purpose processor may also be used.

As the storage unit 15, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, etc. are used. The storage unit 15 stores an image processing program 15A according to the present embodiment. Note that this image processing program 15A may be stored in the ROM 12.

The image processing program 15A may be installed in the image processing device 10 in advance, for example. The image processing program 15A may be realized by being stored in a nonvolatile storage medium, or distributed via a network, and installed in the image processing apparatus 10 as appropriate. Note that examples of nonvolatile storage media include CD-ROM (Compact Disc Read Only Memory), magneto-optical disk, HDD, DVD-ROM (Digital Versatile Disc Read Only Memory), flash memory, memory card, etc. Ru.

For example, a liquid crystal display (LCD), an organic EL (electro luminescence) display, or the like is used for the display unit 16. The display unit 16 may integrally include a touch panel. The operation unit 17 is provided with an operation input device such as a keyboard and a mouse, for example. The display unit 16 and the operation unit 17 receive various instructions from the user of the image processing device 10. The display unit 16 displays various information such as the results of processing executed in response to instructions received from the user and notifications regarding the processing.

The original reading unit 18 takes in the originals placed on the paper feed tray of an automatic document feeder (not shown) provided at the top of the image processing device 10 one by one, optically reads the taken originals, and obtains image information. get. Alternatively, the document reading unit 18 optically reads a document placed on a document table such as a platen glass to obtain image information.

The communication unit 19 is connected to a network such as the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network), and is capable of communicating with external devices such as the image forming apparatus and other PCs via the network. It is considered possible.

By the way, as described above, when a document such as a receipt is placed on a platen glass and read, the edges of the read image of the document may not be extracted. In this case, it is difficult to integrate multiple areas of the read image according to the type of document. This will be explained with reference to FIG.

FIG. 2 is a diagram illustrating a state in which a plurality of areas in read images of a plurality of receipts are integrated.

(S1) shows a state where a plurality of receipts are placed on the platen glass. For example, white thermal paper is used for these plurality of receipts.

(S2) shows a read image obtained by optically reading a plurality of receipts placed on the platen glass. It can be seen that the edges of each receipt are missing in this read image.

(S3) shows an ideal integration result when a plurality of regions included in the read image are integrated. On the other hand, (S4) shows an incorrect integration result when a plurality of regions included in the read image are integrated. (S4) is caused by the fact that edges cannot be detected in originals such as receipts, and if integration is simply performed based on distance, adjacent areas of different receipts will be integrated when they are placed close together. This is because it will be done.

The number of original documents according to this embodiment may be one or more than one. In this embodiment, a case will be described as an example in which a plurality of receipts are multi-crop scanned. Multi-crop scanning here refers to a function that reads multiple originals set on a platen glass, automatically cuts out individual original images from the scanned images, and files them individually. .

The CPU 11 of the image processing device 10 according to the present embodiment functions as each unit shown in FIG. 3 by writing the image processing program 15A stored in the storage unit 15 into the RAM 13 and executing it.

FIG. 3 is a block diagram showing an example of the functional configuration of the image processing device 10 according to this embodiment.

As shown in FIG. 3, the CPU 11 of the image processing device 10 according to the present embodiment includes an area detection section 11A, a distance derivation section 11B, an area derivation section 11C, a combination selection section 11D, an integration possibility determination section 11E, and an integration processing section. Functions as 11F.

The storage unit 15 according to this embodiment stores characteristic information 15B. This characteristic information 15B is information indicating predetermined characteristics for each type of document, and is information used when determining whether or not integration is possible. This characteristic information 15B includes information indicating the shape of the document (for example, the width of the document, etc.).

The area detection unit 11A detects a plurality of areas having foreground-like characteristics from a read image obtained by reading a document. Specifically, the area detection unit 11A binarizes the read image, as shown in FIG. 4, for example.

FIG. 4 is a diagram for explaining area detection processing according to this embodiment.

As shown in FIG. 4, the region detection unit 11A detects a plurality of regions using a filter capable of detecting foreground-like features. For example, a filter that is a combination of an expansion filter and a contraction filter is applied to this filter. The expansion filter replaces the brightness of a central pixel of n×n (n is an odd number of 3 or more) with the maximum brightness among n×n pixels including the central pixel. The contraction type filter replaces the brightness of a central pixel of n×n (n is an odd number of 3 or more) with the minimum brightness among n×n pixels including the central pixel.

The distance derivation unit 11B derives the straight-line distance between the outer edge of one area and the outer edge of the other area for each combination of two areas obtained from the plurality of areas detected by the area detection unit 11A. This straight-line distance is expressed, for example, as the minimum distance between the outer edge of one region and the outer edge of the other region. Specifically, one region is gi (i = 1, 2, 3, ..., N), the other region is gj (j = 1, 2, 3, ..., N), and the region gi and the region When the straight line distance between gj and da(gi, gj) is defined as the following equation (1), da(gi, gj) is defined as follows. Note that the straight-line distance da (gi, gi) is expressed, for example, as a Euclidean distance.

da (gi, gj)
=if (regions of gi and gj intersect) 0
else {min (minimum distance (E (4-side line segment of gi), E (4-side line segment of gj)))}
...(1)

FIG. 5A is a diagram for explaining a method for deriving the straight-line distance da (gi, gj) according to the present embodiment. FIG. 5(B) is a diagram showing an example of a straight-line distance matrix Ra according to this embodiment.

In the read image shown in FIG. 5(A), a plurality of regions #1 to #N (here, N=6) are detected. These regions #1 to #6 have been subjected to labeling processing, so that the regions can be identified. In this case, the linear distance da (g1, g2) is derived for the combination of region #1 and region #2 using the above equation (1). Similarly, a straight line distance da (g1, g3) is derived for the combination of area #1 and area #3, and a straight line distance da (g1, g4) is derived for the combination of area #1 and area #4. Similarly, a straight line distance da (g1, g5) is derived for the combination of area #1 and area #5, and a straight line distance da (g1, g6) is derived for the combination of area #1 and area #6.

Similarly to the above, the straight-line distance da (gi, gj) between regions #2 to #6 is derived from the other regions.

As shown in FIG. 5(A), a straight-line distance depending on the outer circumferential position between the regions is derived. For example, it is sufficient to select two points that have the minimum distance between the outer peripheral point sequences of each region. Straight line distance da(gi, gj) is derived for all combinations of two regions (gi, gj). Then, using this derivation result, as an example, a straight-line distance matrix Ra shown in FIG. 5(B) is generated. This straight distance matrix Ra is stored in the storage unit 15 in association with the read image.

For each combination of two regions obtained from the plurality of regions detected by the region detection section 11A, the area derivation section 11C calculates one region and the other region from the area of the inclusion region that includes one region and the other region. The area of the gap where no region exists is derived. This inclusion area is an area with a predetermined shape. This predetermined shape is, for example, a circumscribed rectangle that circumscribes each of the one region and the other region. Specifically, the area of one region gi is Agi, the area of the other region gj is Agj, the area of the inclusive region that includes one region gi and the other region gj is A(gi, gj), and the area of the gap is (hereinafter referred to as "gap area") is defined as dh(gi, gj), dh(gi, gj) is defined as in the following equation (2).

dh(gi, gj)
=A(gi,gj)-Agi-Agj
...(2)

FIG. 6A is a diagram for explaining a method for deriving the gap area dh (gi, gj) according to the present embodiment. FIG. 6(B) is a diagram showing an example of a gap area matrix Rh according to this embodiment.

In the read image shown in FIG. 6(A), a plurality of regions #1 to #N (here, N=6) are detected, as in the example of FIG. 5(A). In this case, the gap area dh(g1, g2) is derived for the combination of region #1 and region #2 using the above equation (2). The gap area dh (g1, g2) is the area of the hatched portion in FIG. 6(A). That is, it is derived from dh(g1,g2)=A(g1,g2)-Ag1-Ag2. However, Ag1 is the area of region #1, Ag2 is the area of region #2, and A(g1, g2) is the area of a circumscribed rectangle circumscribing each of region #1 and region #2. Similarly, the gap area dh (g1, g3) is derived for the combination of region #1 and region #3, and the gap area dh (g1, g4) is derived for the combination of region #1 and region #4. Similarly, the gap area dh (g1, g5) is derived for the combination of region #1 and region #5, and the gap area dh (g1, g6) is derived for the combination of region #1 and region #6.

For each of regions #2 to #6, the gap area dh (gi, gj) between them and other regions is derived in the same way as above. For example, using the above equation (2), the gap area dh (g4, g5) is derived for the combination of region #4 and region #5. The gap area dh (g4, g5) is the area of the hatched portion in FIG. 6(A). In other words, similarly to the combination of region #1 and region #2, it is derived from dh(g4,g5)=A(g4,g5)−Ag4−Ag5. However, Ag4 represents the area of region #4, Ag5 represents the area of region #5, and A(g4, g5) represents the area of a circumscribed rectangle that circumscribes each of region #4 and region #5.

As shown in FIG. 6(A), the gap area is derived depending on the inclusion relationship between the regions. The gap area can be obtained, for example, by defining a circumscribed rectangle that includes two regions and calculating the difference between the area of the circumscribed rectangle and the area of the two regions. Gap areas dh (gi, gj) are derived for all combinations of two regions (gi, gj). Then, by using this derivation result, a gap area matrix Rh shown in FIG. 6(B) is generated, as an example. This gap area matrix Rh is stored in the storage unit 15 in association with the read image.

The combination selection unit 11D uses the straight-line distance matrix Ra and the gap area matrix Rh stored in the storage unit 15 to select the straight-line distance da (gi, gj) within a predetermined range for each of the plurality of regions. In addition, the combination that minimizes the gap area dh (gi, gj) is selected. Here, the combination selection process will be specifically described with reference to FIGS. 7(A) and 7(B).

FIG. 7(A) is a diagram showing the relationship between the straight-line distance matrix Ra and a plurality of regions according to this embodiment. FIG. 7(B) is a diagram showing the relationship between the straight-line distance matrix Ra and the gap area matrix Rh according to the present embodiment.

As shown in FIG. 7A, by referring to the straight-line distance matrix Ra, combinations in which the straight-line distance da (gi, gj) is within a threshold value (for example, "150", etc.) are detected. In the example of FIG. 7A, the combination of region #1 and region #2, the combination of region #1 and region #3, and the combination of region #1 and region #4 have a straight line distance da(gi, gj) is within the threshold. The combination of region #1 and region #5 and the combination of region #1 and region #6 indicate that the straight-line distance da (gi, gj) exceeds the threshold value. In the straight-line distance matrix Ra, a combination in which the straight-line distance da (gi, gj) exceeds a threshold value is determined to be "NG". In the straight-line distance matrix Ra of FIG. 7(A), the combination of region #1 and region #N is "NG".

In the gap area matrix Rh shown in FIG. 7(B), the gap area dh(gi, gj) corresponding to the combination judged as "NG" above is set as a forbidden value "φ". In the example of FIG. 7B, since the combination of region #1 and region #N is "NG", the forbidden value is "φ". Among the combinations having numerical values other than the forbidden value "φ" in the gap area matrix Rh, the combination that takes the minimum value for each region is selected. In the example of FIG. 7(B), a combination that takes the minimum value "5" for a certain area is selected. Note that if all the values of the gap area matrix Rh are the forbidden value "φ", no combination is selected.

The integration possibility determining unit 11E determines whether or not integration is possible based on predetermined characteristics for each document type, for the plurality of combinations obtained by selecting each of the plurality of regions by the combination selection unit 11D. do. Specifically, the integration possibility determining unit 11E determines whether integration is possible using the above-mentioned characteristic information 15B. For example, in the characteristic information 15B, when the document type is a receipt, the characteristic is set as "width 80 mm or less, height unlimited", and when the document type is a receipt, "width 150 mm or less, height is set". The property "unlimited" is set. That is, in this case, the characteristic information 15B is expressed as an allowable value of the document size.

When comparing the size of each of the plurality of combinations obtained by the combination selection section 11D with the allowable value of the characteristic information 15B, the integration possibility determining section 11E compares the sizes in descending order of the allowable value, and based on the comparison result, It is determined whether each of the plurality of combinations can be integrated. Here, with reference to FIGS. 8(A) to 8(C), the integration feasibility determination process will be specifically described.

FIG. 8A is a diagram illustrating an example of the relationship between area combinations and document size according to this embodiment. FIG. 8B is a diagram illustrating another example of the relationship between the combination of areas and the document size according to this embodiment. FIG. 8C is a diagram showing still another example of the relationship between the combination of areas and the document size according to this embodiment.

The size of the combination of area #3 and area #5 shown in FIG. 8(A) is calculated to be a width W1 [mm]. Here, the width W1 [mm] and the allowable value of the characteristic information 15B are compared in descending order of the allowable value of the characteristic information 15B. In this case, 80 mm (receipt) and 150 mm (receipt) are compared in this order. Note that here, since there is no restriction on the height h1 [mm], it is not used for comparison. In the example of FIG. 8A, since W1[mm]<80 mm, it is determined that the combination of area #3 and area #5 can be integrated as a receipt.

The size of the combination of area #3 and area #4 and the size of the combination of area #5 and area #6 shown in FIG. 8(B) are each calculated to have a width W2 [mm]. Here, similarly to the example of FIG. 8(A), the width W2 [mm] and the allowable value of the characteristic information 15B are compared in descending order of the allowable value of the characteristic information 15B. Note that, like the example in FIG. 8A, there is no restriction on the height h2 [mm], so it is not used for comparison. In the example of FIG. 8B, since W2 [mm]≧150 mm, it is determined that the combination of region #3 and region #4 and the combination of region #5 and region #6 cannot be integrated. Note that when 80 mm≦W2[mm]<150 mm, it is determined that the combination of area #3 and area #4 and the combination of area #5 and area #6 can be integrated as a receipt.

The size of the combination of region #1 and region #3 and the size of the combination of region #3 and region #5 shown in FIG. 8(C) are each calculated to have a width W3 [mm]. Here, similarly to the example of FIG. 8A, the width W3 [mm] and the tolerance value of the characteristic information 15B are compared in descending order of the tolerance value of the characteristic information 15B. Note that, like the example in FIG. 8A, there is no restriction on the height h3 [mm], so it is not used for comparison. In the example of FIG. 8(C), since W3 [mm] < 80 mm, it is determined that the combination of area #1 and area #3 and the combination of area #3 and area #5 can be integrated as a receipt. Ru.

Furthermore, arrangement conditions for arranging a plurality of documents may be defined in advance. In this case, the integration possibility determining unit 11E further uses the arrangement condition to determine whether integration is possible. The arrangement condition is, for example, a condition such as "arrangement at a distance of XX cm or more." By presenting this arrangement condition to the user, a plurality of documents are arranged according to the arrangement condition. By considering this arrangement condition in addition to the characteristic information 15B described above, it is possible to accurately determine whether integration is possible.

The integration processing unit 11F integrates each of the plurality of combinations based on the determination result by the integration possibility determination unit 11E, and recalculates the straight-line distance da (gi, gj) and the gap area dh (gi, gj). Specifically, if the areas to be combined can be integrated, various information (size, etc.) when the two areas are integrated is updated. In particular, regarding the gap area dh (gi, gj), as an example, as shown in FIG. 9, the integrated value in the combination of two areas is updated to the forbidden value "φ", and the row related to the integrated area and column values are updated.

FIG. 9 is a diagram for explaining recalculation in the integration process according to this embodiment.

In the example of the gap area matrix Rh shown in FIG. 9, it is updated from "5" to "φ", from "400" to "150", and from "100" to "80".

Here, the integration result by the integration processing unit 11F may be confirmed on a preview display. After confirming the integration result in a preview display, if it is determined that the integration result is correct, the integration result may be transmitted to an accounting system or the like with which the image processing device 10 is linked. Further, if it is determined that the previewed integration result is incorrect, the user may correct the integration state to be correct. Regarding the integrated area expressed as the integration result, the area including the integrated area may be acquired as a document image, or character information may be extracted from the integrated area by OCR (Optical Character Recognition). You may also do so.

Moreover, although the embodiment including the integration possibility determining section 11E has been described above, it may also be a mode not including the integration capability determining section 11E. In this case, the integration processing section 11F performs a process of integrating the plurality of combinations selected and obtained by the combination selection section 11D without performing an integration feasibility determination process.

Next, with reference to FIG. 10, the operation of the image processing device 10 according to this embodiment will be described.

FIG. 10 is a flowchart showing an example of the flow of processing by the image processing program 15A according to the present embodiment.

First, when a user instructs the image processing apparatus 10 to start multi-crop scan processing, the image processing program 15A is activated and executes the following steps.

In step 100 of FIG. 10, the CPU 11 detects a plurality of areas from read images obtained by reading a plurality of documents, as shown in FIG. 4 described above, for example.

In step 101, the CPU 11 identifies one area from the plurality of areas detected in step 100.

In step 102, the CPU 11 calculates, for example, the straight-line distance da(gi, gj) between the area specified in step 101 and another area, as shown in FIGS. 5(A) and 5(B) described above. Derive. Specifically, the straight-line distance da (gi, gj) is derived for each combination of two regions using the above equation (1).

In step 103, the CPU 11 determines, for example, the gap area, which is the area of the gap between the area identified in step 101 and another area, as shown in FIGS. 6(A) and 6(B) above. Derive dh(gi, gj). Specifically, the gap area dh (gi, gj) is derived for each combination of two regions using the above equation (2).

In step 104, the CPU 11 determines whether the derivation of the straight-line distance da (gi, gj) and the gap area dh (gi, gj) for the entire area has been completed. If it is determined that the derivation of the straight-line distance da (gi, gj) and gap area dh (gi, gj) has been completed for the entire area (in the case of an affirmative determination), the process moves to step 105, and the straight-line distance and gap area dh (gi, gj) are calculated for the entire area. If it is determined that the derivation of has not been completed (in the case of a negative determination), the process returns to step 101 and repeats the process.

In step 105, the CPU 11 determines whether or not a combination satisfying a predetermined condition has been selected, as shown in FIGS. 7(A) and 7(B) above, for example. The predetermined conditions here are that the straight-line distance da (gi, gj) between the regions is within a threshold value and that the gap area dh (gi, gj) between the regions is the minimum. If it is determined that a combination that satisfies the predetermined conditions could be selected (in the case of an affirmative determination), the process moves to step 106, and if it is determined that a combination that satisfies the predetermined conditions cannot be selected (in the case of a negative determination), the present image processing program 15A ends.

In step 106, the CPU 11 identifies one combination from the plurality of combinations selected in step 105.

In step 107, the CPU 11 determines whether the combination specified in step 106 can be integrated, as shown in FIGS. 8(A) to 8(C) above, for example. If it is determined that the identified combination can be integrated (in the case of a positive determination), the process moves to step 108, and if it is determined that the specified combination cannot be integrated (in the case of a negative determination), the process returns to step 106. repeat.

In step 108, the CPU 11 performs an integration process on the combinations determined to be able to be integrated in step 107, as shown in FIG. ) is recalculated.

In step 109, the CPU 11 determines whether the integrated determination has been completed for all combinations. If it is determined that the integrated determination has not been completed for all the combinations (in the case of a negative determination), return to step 106 and repeat the process, and if it is determined that the integrated determination has been completed for all the combinations (in the case of an affirmative determination), The series of processing by the image processing program 15A ends.

As described above, according to the present embodiment, even if edges cannot be extracted from a read image of a document, multiple areas of the read image are integrated according to the type of document.

Note that in each of the above embodiments, the processor refers to a processor in a broad sense, and includes a general-purpose processor (e.g., CPU: Central Processing Unit, etc.) and a dedicated processor (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

Further, the operation of the processor in each of the above embodiments may be performed not only by one processor, but also by a plurality of processors located at physically separate locations. Further, the order of each operation of the processor is not limited to the order described in each of the above embodiments, and may be changed as appropriate.

The image processing apparatus according to the embodiment has been described above as an example. The embodiment may be in the form of a program for causing a computer to execute the functions of each unit included in the image processing apparatus. Embodiments may be in the form of a computer readable storage medium storing this program.

In addition, the configuration of the image processing apparatus described in the above embodiment is merely an example, and may be changed according to the situation without departing from the spirit of the invention.

Furthermore, the process flow of the program described in the above embodiment is only an example, and unnecessary steps may be deleted, new steps may be added, or the processing order may be changed without departing from the main purpose. good.

Further, in the above embodiment, a case has been described in which the processing according to the embodiment is realized by a software configuration using a computer by executing a program, but the present invention is not limited to this. The embodiments may be realized by, for example, a hardware configuration or a combination of a hardware configuration and a software configuration.

10 Image processing device 11 CPU
11A Area detection section 11B Distance derivation section 11C Area derivation section 11D Combination selection section 11E Integration possibility determination section 11F Integration processing section 12 ROM
13 RAM
14 I/O
15 Storage section 15A Image processing program 15B Characteristic information 16 Display section 17 Operation section 18 Communication section

Claims (9)

Equipped with a processor,
The processor includes:
Detects multiple areas with foreground-like characteristics from the scanned image obtained by scanning the original,
For each combination of two regions obtained from the plurality of regions, derive the straight-line distance between the outer edge of one region and the outer edge of the other region,
For each combination of the two regions, from the area of the inclusion region which is a region of a predetermined shape that includes the one region and the other region, a portion where the one region and the other region do not exist. Derive the area of a certain gap,
For each of the plurality of regions, select a combination in which the straight line distance is within a predetermined range and the area of the gap is the minimum ;
For the plurality of selected combinations, it is determined whether or not they can be integrated, and based on the judgment result, each of the plurality of combinations is integrated, or for the plurality of selected combinations, An image processing device that integrates each of multiple combinations without determining whether or not they can be integrated . The processor determines whether or not to integrate the plurality of combinations obtained by selecting each of the plurality of regions based on predetermined characteristics for each type of document. Image processing device. The characteristic is expressed as a tolerance value of document size,
When comparing the size of each of the plurality of combinations with the tolerance value, the processor compares the size of each of the plurality of combinations in descending order of the tolerance value, and determines whether or not each of the plurality of combinations can be integrated based on the comparison result. The image processing device according to claim 2. The manuscript is a plurality of manuscripts,
The image processing according to claim 2 or 3, wherein when arrangement conditions for arranging the plurality of documents are defined in advance, the processor further uses the arrangement conditions to determine whether or not the integration is possible. Device. The image processing device according to any one of claims 1 to 4, wherein the processor detects the plurality of regions using a filter capable of detecting the foreground-likeness feature. The filter is
an expansion filter that replaces the brightness of a central pixel of n×n (n is an odd number of 3 or more) with the maximum brightness among n×n pixels including the central pixel;
a contraction filter that replaces the brightness of an n×n center pixel (n is an odd number of 3 or more) with the minimum brightness among n×n pixels including the center pixel;
The image processing device according to claim 5, wherein the image processing device is a filter that combines the following. The image processing device according to any one of claims 1 to 6, wherein the straight line distance is a minimum distance between an outer edge of the one region and an outer edge of the other region. The image processing device according to any one of claims 1 to 7, wherein the predetermined shape of the inclusion area is a circumscribed rectangle that circumscribes each of the one area and the other area. Detects multiple areas with foreground-like characteristics from the scanned image obtained by scanning the original,
For each combination of two regions obtained from the plurality of regions, derive the straight-line distance between the outer edge of one region and the outer edge of the other region,
For each combination of the two regions, from the area of the inclusion region which is a region of a predetermined shape that includes the one region and the other region, a portion where the one region and the other region do not exist. Derive the area of a certain gap,
For each of the plurality of regions, select a combination in which the straight line distance is within a predetermined range and the area of the gap is the minimum ;
For the plurality of selected combinations, it is determined whether or not they can be integrated, and based on the judgment result, each of the plurality of combinations is integrated, or for the plurality of selected combinations, It is possible to integrate each of multiple combinations without determining whether or not they can be integrated .
An image processing program that is executed by a computer.