JP2017175328A - Image processing device, information processing device, and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To appropriately partition image data into a scan target object part and a background part.SOLUTION: A feeding unit feeds a scan target object. A scan unit scans the scan target object fed, and outputs image data. An edge extraction unit extracts an edge of the image data. An area detection unit detects, based on the edge, an edge area and a non-edge area of image data for judgement from an upper end to a predetermined line of the image data. A first judgement unit judges whether the edge area and the non-edge area detected are a scan target object area or a background area. The latter judgement unit judges about the scan target object area and the background area of the continuous image data based on a judgement result of the scan target object area and the background area of the image data for judgement, and the edge of the continuous image data following the image data for judgement.SELECTED DRAWING: Figure 4

Description

  The present invention relates to an image processing device, an information processing device, and an image processing method.

  Patent Document 1 discloses an image reading system that determines a document area automatically extracted from a read image area without providing a sensor dedicated to paper size detection in an automatic document feeder of the image reading apparatus. .

JP 2010-141509 A

  In Patent Document 1, the document size is obtained from two vertices of a document existing within a predetermined distance from the upper end of the scanned image data and two vertices existing within a predetermined distance from the lower end. Therefore, in Patent Document 1, it may be difficult to determine the vertex of a non-rectangular document, and it may be difficult to divide image data into a document portion and a background portion (a portion that is not a document).

  Therefore, the present invention provides a technique capable of appropriately dividing image data into a scan target part and a background part.

  A first aspect of the present invention for solving the above problems is a feeding unit that feeds a scan object, a scanning unit that scans the fed scan object and outputs image data, An edge extraction unit that extracts an edge of the image data; and an area detection unit that detects an edge region and a non-edge region of determination image data from the upper end of the image data to a predetermined line based on the edge; A pre-determination unit for determining whether the region is a scan target region or a background region with respect to the edge region and the non-edge region, and a determination result of the scan target region and the background region of the determination image data And the scan object area and the background area of the subsequent image data based on the edge of the subsequent image data following the determination image data. A connection judging unit, an image processing apparatus characterized by having a. According to the first aspect, the image processing apparatus can appropriately divide the image data into the scan target part and the background part.

  The pre-determination unit provisionally determines the non-edge area not including the edge as the background area, and temporarily determines the non-edge area including the edge and the edge area as the scan target area. May be a feature. As a result, the image processing apparatus can appropriately provisionally determine whether the edge region and the non-edge region are the background region or the scan target region.

  The scan unit overscans the scan object, and the pre-determination unit does not contact the upper edge of the determination image data with the provisionally determined edge region and the non-edge region, and the determination image The edge region and the non-edge region that have been provisionally determined may be determined as the scan object region when it includes a coordinate that touches the lower end of the data and passes through the scan object of the scan unit. . As a result, the image processing apparatus can appropriately correct the temporarily determined edge region and non-edge region as a background region or a scan target region.

  The pre-determination unit includes a case where the temporarily determined edge region and the non-edge region include a coordinate that is in contact with a lower end of the determination image data and through which the scan object of the scan unit passes. When the edge region and the non-edge region do not touch the upper end of the determination image data, the edge region and the non-edge region are determined as a first type scan object region, and the edge region and the non-edge region Is not the first type scan target area and does not contact the upper left end point and the upper right end point of the determination image data, the edge area and the non-edge area are determined to be the second type scan target area. The edge region and the non-edge region are not the first type scan target region and the second type scan target region, but the determination image data When contacting only one of the upper end point and the upper right end point, the edge region and the non-edge region are determined as a third type scan target region, and the first type scan target region and the second type scan are determined. Determining whether the edge region and the non-edge region are the scan target region or the background region based on the presence of the target region and the third type scan target region Also good. As a result, the image processing apparatus can appropriately correct the temporarily determined edge region and non-edge region as a background region or a scan target region.

  The continuation determination unit determines a determination result determined by the determination image data for the edge region and the non-edge region of the continuation image data following the edge region and the non-edge region of the determination image data. It may be characterized by applying. As a result, the image processing apparatus can appropriately determine whether the edge area and the non-edge area of the subsequent image data are the background area or the scan target area.

  A scan type determination unit that determines whether the scan unit scans the scan object fed from the feeding unit or scans the scan object placed on a table; The pre-determination unit may determine the scan object region and the background region of the determination image data according to a determination result of the scan type determination unit.

  The edge extraction unit calculates a luminance dispersion difference between a luminance dispersion of a first pixel of the image data and a luminance dispersion of a second pixel around the first pixel, and based on the luminance dispersion difference , Extracting an edge of the image data. Thereby, the image processing apparatus can appropriately extract the edge.

  According to a second aspect of the present invention for solving the above-described problem, the image processing apparatus feeds a scan object and scans image data scanned from the image processing apparatus, and the image data An edge extraction unit that extracts an edge; an area detection unit that detects an edge region and a non-edge region of image data for determination from an upper end of the image data to a predetermined line based on the edge; and the detected edge region And a pre-determination unit that determines whether the non-edge region is a scan target region or a background region, a determination result of the scan target region and the background region of the determination image data, and the determination Continuation determination for determining the scan object region and the background region of the continuation image data based on the edge of the continuation image data following the image data for use When an information processing apparatus characterized by having a. According to the second aspect, the information processing apparatus can appropriately divide the image data into the scan target part and the background part.

  A third aspect of the present invention for solving the above-mentioned problem is an image processing method of an image processing apparatus, the step of feeding a scan object, and scanning the scan object to be fed, A step of outputting image data; a step of extracting edges of the image data; and a step of detecting edge regions and non-edge regions of determination image data from an upper end of the image data to a predetermined line based on the edges. Determining whether the detected edge region and the non-edge region are a scan target region or a background region; and the scan target region and the background region of the determination image data Based on the determination result and the edge of the subsequent image data following the determination image data, the scan object of the subsequent image data A frequency and determining the background region, an image processing method, which comprises a. According to the third aspect, the image processing apparatus can appropriately divide the image data into the scan target part and the background part.

  A fourth aspect of the present invention for solving the above problem is an image processing method of an information processing apparatus, wherein the image processing apparatus supplies image data scanned by a scanning object to the image processing apparatus. Receiving the image data, extracting the edge of the image data, detecting the edge region and the non-edge region of the image data for determination from the upper end of the image data to a predetermined line based on the edge, A step of determining whether the detected edge region and the non-edge region are a scan target region or a background region, and a determination result of the scan target region and the background region of the determination image data And the scan object region of the subsequent image data based on the edge of the subsequent image data following the determination image data. And determining the fine the background region, an image processing method, which comprises a. According to the fourth aspect, the information processing apparatus can appropriately separate the image data into the scan target part and the background part.

1 is a schematic perspective view of an image processing apparatus according to a first embodiment. It is a schematic sectional drawing of a part of cover. 6 is a diagram illustrating an example of image data of a document scanned by a scanning unit. FIG. It is the figure which showed the functional block structural example of the image processing apparatus. It is the figure which showed the example of the edge extracted by the edge extraction part. It is a figure explaining the example of calculation of the luminance dispersion difference of an edge extraction part. It is a figure explaining the example of determination of an edge. It is the figure which showed the example of a detection of the edge area | region and non-edge area | region by an area | region detection part. It is a figure explaining an attention pixel and a reference pixel. It is a figure explaining the area | region detection operation example of an area | region detection part. It is a figure explaining the operation example of the front determination part. It is the figure which showed the example of a determination result of a continuation determination part. It is the figure which showed the determination conditions of the 1st pattern determination which a continuation determination part performs. It is the 1 of the figure which showed the data structural example of the memory | storage part. FIG. 6 is a first diagram illustrating an operation example of the first pattern determination of the continuation determination unit. FIG. 6B is a second diagram illustrating an operation example of the first pattern determination of the continuation determination unit. It is the figure which showed the determination conditions of the 2nd pattern determination which a continuation determination part performs. It is the 2 of the figure which showed the data structural example of the memory | storage part. FIG. 10 is a first diagram illustrating an operation example of second pattern determination of the continuation determination unit. FIG. 14B is a second diagram illustrating an operation example of the second pattern determination of the continuation determination unit. FIG. 3 is a first diagram illustrating an example of document cutting. FIG. 3B is a second diagram for explaining an example of cutting out a document; FIG. 3C is a third diagram illustrating an example of document cutout. 3 is a flowchart illustrating an operation example of the image processing apparatus. It is the figure which showed the functional block structural example of information processing apparatus. It is the figure which showed the functional block structural example of the image processing apparatus which concerns on 2nd Embodiment. It is a figure explaining the operation example of the front determination part. FIG. 5 is a diagram for explaining a first type original area, a second type original area, and a third type original area.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[First Embodiment]
FIG. 1 is a schematic perspective view of an image processing apparatus 1 according to the first embodiment. An image processing apparatus 1 shown in FIG. 1 is, for example, a multifunction peripheral, and includes a main body 2, a cover 3, an ADF (Auto Document Feeder) unit (corresponding to a feeding unit of the present invention) 4, and an input device 5. have.

  The cover 3 can be opened and closed with respect to the upper surface of the main body 2 (reading table made of glass or the like). The cover 3 is closed with respect to the reading table of the main body 2, thereby pressing the document placed on the reading table of the main body 2.

  The ADF unit 4 is provided on the cover 3. The ADF unit 4 includes a paper feed port 4a through which a scan target such as a document is fed, and a paper discharge port 4b through which the scanned scan target is discharged. In the following description, the scan target object is a document.

  The input device 5 is a touch panel provided on the screen of the display device, for example. The input device 5 receives a predetermined operation from the user.

  When an original is placed in the paper feed opening 4a and the input device 5 receives a predetermined operation from the user, the image processing apparatus 1 automatically takes in the original placed in the paper feed opening 4a, and receives the image data of the taken-in original. Read. The image processing apparatus 1 discharges the original from which the image data has been read from the paper discharge port 4b.

  FIG. 2 is a schematic sectional view of a part of the cover 3. 2A is a schematic cross-sectional view of the cover 3 viewed from the front of the image processing apparatus 1, and FIG. 2B is a schematic cross-sectional view of the cover 3 viewed from the upper surface of the image processing apparatus 1. is there. In FIG. 2, the same components as those in FIG. FIG. 2 also shows the document 11 placed in the paper feed port 4a.

  As shown in FIGS. 2A and 2B, the cover 3 has a paper detection sensor 12. The paper detection sensor 12 detects whether or not the document 11 is placed in the paper feed port 4a. As shown in FIG. 2B, the paper detection sensor 12 is provided at a substantially central portion of the paper feed port 4a in the x-axis direction (perpendicular to the traveling direction of the document 11). That is, the paper detection sensor 12 is provided at a position through which the substantially central portion of the document 11 in the x-axis direction passes.

  As shown in FIGS. 2A and 2B, the main body 2 has a scanning unit 13. The scanning unit 13 includes, for example, an image sensor (not shown), optically scans the document 11 fed by the ADF unit 4, and outputs image data of the document 11.

  The scanning unit 13 can move to the right from the position shown in FIG. Further, the scanning unit 13 can move from the right direction in FIG. 2A to the position shown in FIG. When the paper 11 is detected by the paper detection sensor 12, the scan unit 13 is moved (arranged) to the position shown in FIG. 2A and scans the document 11 fed by the ADF unit 4.

  The scanning unit 13 can also output the image data of the document 11 placed on the reading table of the main body 2. In this case, for example, the scanning unit 13 moves rightward from the position shown in FIG. 2A and scans the document 11 placed on the reading table of the main body 2. In the following description, it is assumed that the scanning unit 13 scans the document 11 fed by the ADF unit 4.

  FIG. 3 is a diagram illustrating an example of image data of the document 11 scanned by the scanning unit 13. The image data 21 shown in FIG. 3 shows an example of image data obtained by scanning the document 11 fed by the ADF unit 4 by the scanning unit 13. An area 22 illustrated in FIG. 3 indicates an image data area of the document 11 scanned by the scanning unit 13.

  The scanning unit 13 overscans the document 11 fed by the ADF unit 4. Therefore, as shown in the overscan OS1 and OS2 in FIG. 3, the upper and lower portions of the image data 21 include image data other than the document 11 (background image data). Depending on the width of the document 11, the left and right portions of the image data 21 include background image data.

  The image processing apparatus 1 cuts out the image data portion of the document 11 from the image data 21 scanned by the scanning unit 13. That is, the image processing apparatus 1 removes the background portion from the image data 21 and cuts out the region 22. The image processing apparatus 1 divides the image data 21 output from the scanning unit 13 into two image data areas during the clipping process.

  For example, as shown in FIG. 3, the image processing apparatus 1 divides the image data 21 into two areas of determination image data 21a and continuation image data 21b. The determination image data 21a is image data up to a predetermined line (image data from the upper end of the image data 21 to a predetermined line) after the scanning unit 13 starts overscanning. The subsequent image data 21b is image data after (below) a predetermined line following the determination image data 21a.

  A dotted line shown in FIG. 3 shows an example of a predetermined line of the image data 21. The predetermined line is at least a line below the line where the scanning unit 13 starts overscanning and starts scanning the document 11. For example, the predetermined line is a line below the upper end of the region 22 shown in FIG.

  As will be described in detail below, the image processing apparatus 1 determines a portion of the document 11 (document region) and a background portion (background region) other than the document 11 in the determination image data 21a. Then, the image processing apparatus 1 determines the document area and the background area of the subsequent image data 21b following the determination image data 21a using the document area and the background area of the determination image data 21a. As a result, the image processing apparatus 1 cuts out the portion of the document 11 indicated by the region 22 from the image data 21.

  The image processing apparatus 1 transmits the image data of the clipped document portion to, for example, an information processing apparatus (not shown) such as a personal computer or a tablet terminal connected to the image processing apparatus 1. Alternatively, the image processing apparatus 1 stores the image data of the clipped document portion in an external memory (not shown) such as a USB (Universal Serial Bus) memory. As a result, the user can acquire image data of only the document portion.

  Note that the image processing apparatus 1 performs determination processing of the document area and the background area of the image data 21 together with the output of the image data 21 of the scanning unit 13. In other words, the image processing apparatus 1 performs determination processing of the document area and the background area of the image data 21 in real time while scanning.

  FIG. 4 is a diagram illustrating a functional block configuration example of the image processing apparatus 1. As illustrated in FIG. 4, the image processing apparatus 1 includes an ADF unit 4, a scanning unit 13, a control unit 31, a communication unit 32, an input unit 33, and a storage unit 34.

  The ADF unit 4 is the ADF unit described with reference to FIGS. Under the control of the control unit 31, the ADF unit 4 sends the document placed at the paper feed port 4a to the scan unit 13 and discharges it to the paper discharge port 4b.

  The scan unit 13 is the scan unit described with reference to FIG. The scan unit 13 scans the document fed by the ADF unit 4 under the control of the control unit 31 and outputs image data of the document. For example, the scanning unit 13 outputs color (RGB) image data. The image data output from the scanning unit 13 is stored in the storage unit 34, for example.

  The control unit 31 controls the operation of the image processing apparatus 1 in an integrated manner. As will be described in detail below, the control unit 31 divides the image data of the document scanned by the scanning unit 13 (image data stored in the storage unit 34) into a background portion and a document portion, and cuts out the document portion.

  The communication unit 32 communicates with an information processing apparatus such as a personal computer or a tablet terminal. The communication unit 32 communicates with the information processing apparatus by, for example, wired or wireless.

  The input unit 33 receives operation data from the user from the input device 5.

  The storage unit 34 stores programs, data, and the like for the control unit 31 to perform calculation processing and control processing. The storage unit 34 stores a program, data, and the like for the control unit 31 to realize a predetermined application function. Various programs, data, and the like may be stored in advance in a nonvolatile recording medium, or may be received by the control unit 31 from the server via the communication network and stored in the storage unit 34. The storage unit 34 includes, for example, various IC (Integrated Circuit) memories such as a ROM (Read Only Memory), a flash ROM, and a RAM (Random Access Memory), a recording medium such as a hard disk and a memory card, and the like.

  The control unit 31 includes an edge extraction unit 41, a region detection unit 42, a previous determination unit 43, a continuation determination unit 44, and a cutout unit 45. The functions of each unit of the control unit 31 are realized by, for example, a CPU (Central Processing Unit) that executes a program stored in the storage unit 34. In addition, each part of the control part 31 may implement | achieve the function by custom IC (Integrated Circuit), such as ASIC (Application Specific Integrated Circuit), and may implement | achieve the function by CPU and ASIC. .

  The edge extraction unit 41 extracts the edge of the image data output from the scanning unit 13.

  FIG. 5 is a diagram illustrating an example of edges extracted by the edge extraction unit 41. FIG. 5A shows determination image data 51 out of image data output from the scanning unit 13, a background 52, a shadow 53, and a document 54.

  The background 52 corresponds to an area other than the original read by the scanning unit 13. The shadow 53 corresponds to the boundary between the document 54 and the background 52. The boundary between the document 54 and the background 52 appears in the image data as a shadow 53. The document 54 corresponds to the document read by the scanning unit 13.

  FIG. 5B shows an example of an edge extracted from the determination image data 51 shown in FIG. When the edge extraction unit 41 extracts an edge from the determination image data 51 of FIG. 5A, the edge extraction unit 41 is as shown in FIG.

  A white portion shown in FIG. 5B is an edge region. The edge region corresponds to the shadow 53 in FIG. A black portion shown in FIG. 5B is a non-edge region. The non-edge region corresponds to the background 52 and the document 54 in FIG.

  Although FIG. 5 shows an example of edge extraction of the determination image data 51, the edge extraction unit 41 also extracts the edge of the subsequent image data following the determination image data 51. That is, the edge extraction unit 41 extracts the edge of the image data output from the scanning unit 13.

  Although not shown in FIG. 5, when the document 54 includes characters or the like, the characters are also extracted as edges.

  The edge extraction operation of the edge extraction unit 41 will be specifically described. The edge extraction unit 41 converts the RGB image data of the original scanned by the scanning unit 13 into luminance image data. The edge extraction unit 41 converts RGB image data into luminance image data by the following equation (1).

  Next, the edge extraction unit 41 calculates the average luminance of the pixel of interest and the surrounding pixels using the luminance image data calculated by the equation (1). Then, the edge extraction unit 41 calculates the luminance variance of the pixel of interest using the calculated luminance average, and calculates the luminance variance difference between the pixel of interest and the surrounding pixels.

  FIG. 6 is a diagram for explaining a calculation example of the luminance dispersion difference of the edge extraction unit 41. The squares shown in FIG. 6 indicate pixels. “P0” indicates a target pixel. “P1 to P8” indicate pixels around the target pixel (pixels adjacent to the target pixel). Hereinafter, pixels around the target pixel may be referred to as “peripheral pixels”.

The edge extraction unit 41 calculates the average luminance of the target pixel P0 and the surrounding pixels P1 to P8. Specifically, the edge extraction unit 41 calculates the luminance average “Y _u ” between the target pixel P0 and the surrounding pixels P1 to P8 by the following equation (2).

Here, “x _j , y _i ” in Expression (2) indicates the coordinates of the pixel. “Y (x _j , y _i )” indicates the luminance of the pixel at the coordinates “x _j , y _i ” (the luminance calculated by equation (1)). That is, the edge extraction unit 41 calculates the luminance average “Y _u ” of the pixels in the thick frame shown in FIG.

The edge extraction unit 41 calculates a luminance average of the target pixel P <b> 0 using the calculated luminance average when the luminance average is calculated according to the equation (2). Specifically, the edge extraction unit 41 calculates the luminance dispersion “Y _s ” of the pixel of interest P0 by the following equation (3).

The edge extraction unit 41 calculates the luminance dispersion “Y _s ” for all the pixels of the image data. For example, the edge extraction unit 41 moves the target pixel P0 like a raster scan, and calculates the luminance dispersion “Y _s ” of all the pixels of the image data.

  After calculating the luminance variance of all pixels, the edge extraction unit 41 calculates a luminance variance difference between the luminance variance of the target pixel and the luminance variance of surrounding pixels. For example, the edge extraction unit 41 calculates a difference (luminance dispersion difference) between the luminance dispersion of the target pixel P0 illustrated in FIG. 6 and the luminance dispersion of each of the surrounding pixels P1 to P8. More specifically, the edge extraction unit 41 calculates the luminance dispersion difference between the surrounding pixel P1 and the target pixel P0, calculates the luminance dispersion difference between the surrounding pixel P2 and the target pixel P0, and so on. Then, the luminance dispersion difference between the surrounding pixel P8 and the target pixel P0 is calculated.

  After calculating the luminance dispersion difference between the target pixel and the surrounding pixels, the edge extraction unit 41 determines the edge of the image data based on the calculated luminance dispersion difference. For example, the edge extraction unit 41 may call at least one or more absolute values of the luminance dispersion difference between the target pixel P0 and the surrounding pixels P1 to P8 as a predetermined threshold (hereinafter referred to as “luminance dispersion difference threshold”). If it exceeds (Yes), the target pixel P0 is determined as an edge pixel.

  The edge extraction unit 41 calculates a luminance dispersion difference for all the pixels of the image data. For example, the edge extraction unit 41 moves the target pixel P0 like a raster scan, and calculates a luminance dispersion difference for all the pixels of the image data. Then, the edge extraction unit 41 determines an edge for all the pixels of the image data.

  FIG. 7 is a diagram illustrating an example of edge determination. FIG. 7 shows determination image data 51 among the image data of the original scanned by the scanning unit 13. In FIG. 7, the same components as those in FIG. Each of the luminance dispersion differences D0 to D2 illustrated in FIG. 7 indicates the luminance dispersion difference (absolute value) of the pixel indicated by each of the arrows A0 to A2.

  As illustrated in FIG. 7, the luminance dispersion difference D1 of the pixel indicated by the arrow A1 exceeds the luminance dispersion difference threshold, and the pixel indicated by the arrow A1 is determined to be an edge. Thereby, the edge of the determination image data 51 shown in FIG. 7 becomes as shown in FIG.

  Returning to the description of FIG. The area detection unit 42 reads determination image data out of the image data output from the scanning unit 13. Then, the region detection unit 42 detects the edge region and the non-edge region of the determination image data based on the edge extracted by the edge extraction unit 41.

  For example, the region detection unit 42 detects the edge region extracted by the edge extraction unit 41 as an edge region. For example, the region detection unit 42 determines that the closed region surrounded by the edges extracted by the edge extraction unit 41 is a non-edge region. For example, the region detection unit 42 determines a closed region surrounded by the edge extracted by the edge extraction unit 41 and the end of the determination image data as a non-edge region.

  FIG. 8 is a diagram illustrating an example of detection of edge regions and non-edge regions by the region detection unit 42. A region L1 illustrated in FIG. 8 is a region surrounded by the white solid edge illustrated in FIG. 5B, the upper end, the left end, the right end, and a part of the lower end of the determination image data 51. . Accordingly, the region L1 illustrated in FIG. 8 is detected as a non-edge region by the region detection unit 42.

  A region L2 illustrated in FIG. 8 corresponds to the white painted edge illustrated in FIG. Accordingly, the region L2 illustrated in FIG. 8 is detected as an edge region by the region detection unit 42.

  A region L3 illustrated in FIG. 8 is a region surrounded by the white painted edge illustrated in FIG. 5B and a part of the lower end of the determination image data 51. Accordingly, the region L3 illustrated in FIG. 8 is detected as a non-edge region by the region detection unit 42.

  In addition, the dashed-dotted line shown in FIG. 8 has shown the part (coordinate) through which the paper detection sensor 12 passes.

  An example of the operation of the area detection unit 42 will be specifically described. First, the definition of the target pixel and the reference pixel will be described.

  FIG. 9 is a diagram for explaining a target pixel and a reference pixel. “Note” shown in FIG. 9 indicates a target pixel, and “reference” indicates a reference pixel. When the pixel of interest is an edge pixel, the reference pixel is a pixel adjacent to the left of the pixel of interest, an upper left pixel, an upper pixel, and an upper right pixel, as shown in FIG. When the target pixel is a non-edge pixel, the reference pixel is a pixel adjacent to the left of the target pixel and an upper pixel, as shown in FIG. 9B.

  The area detection unit 42 assigns a label value to the target pixel. When there is no reference pixel having the same edge value as the target pixel (a value indicating whether it is an edge or a non-edge), the region detection unit 42 adds “1” to the label value last assigned to the target pixel. A label value is assigned (the label value to be assigned first is “1”). However, when there is a reference pixel having the same edge value as that of the target pixel, the region detection unit 42 assigns the smallest label value of the reference pixel to the target pixel. Further, when the smallest label value of the reference pixel is assigned to the target pixel, the region detection unit 42 corrects the label value of the reference pixel having the same edge value as the target pixel to the smallest label value.

  FIG. 10 is a diagram for explaining an example of the region detection operation of the region detection unit 42. The squares shown in FIG. 10 correspond to the pixels of the image data. Hatched squares correspond to non-edge pixels, and unhatched squares correspond to edge pixels. Moreover, the pixel of the label value with the underline shown in FIG. 10 has shown the attention pixel.

  As shown in FIG. 10A, the area detection unit 42 assigns label values in order from the upper left pixel to the right pixel. When there is no reference pixel having the same edge value as the target pixel, the region detection unit 42 assigns a label value obtained by adding “1” to the label value assigned last to the target pixel. In addition, when there is a reference pixel having the same edge value as the target pixel, the region detection unit 42 assigns the smallest label value of the reference pixel to the target pixel.

  For example, the pixel in the third row from the top in FIG. 10A and the seventh column from the left is the target pixel. This target pixel is a non-edge pixel. In this case, both reference pixels based on (B) in FIG. 9 are pixels having an edge different from the edge value of the target pixel. Accordingly, the label value of the target pixel in the third row from the top in FIG. 10A and the seventh column from the left is “4” obtained by adding “1” to the label value “3” last assigned to the target pixel. "

  Assume that the pixel of interest has moved to the right of the label value “4” shown in FIG. This target pixel is a non-edge pixel. In this case, since both of the reference pixels based on (B) in FIG. 8 are non-edge pixels that are the same as the edge value of the target pixel, the label value is the reference pixel as shown in (B) in FIG. This is “1”, which is the minimum value of the label value. Further, the reference pixel on the left side of the target pixel is the same non-edge pixel as the target pixel, and the region detection unit 42 indicates the correction label value “4” of the reference pixel as shown in FIG. The correction label value is changed to “1”.

  When the area detection unit 42 repeats the above operation, a label value as shown in FIG. 10C is assigned to each pixel. When the region detection unit 42 assigns a label value to all the pixels, the region detection unit 42 corrects the label value to a corrected label value. For example, the region detection unit 42 corrects the label value “4” to the correction label value “1”. As a result, the label value assigned to each pixel is as shown in FIG.

  As described above, the region detection unit 42 assigns label values to the edge region and the non-edge region of the image data. Thereby, the area detection unit 42 can detect the edge area and the non-edge area of the image data for determination based on the label value. For example, the region detection unit 42 detects a non-edge region to which the label value “1” is assigned, an edge region to which the label value “2” is assigned, and a non-edge region to which the label value “3” is assigned. can do.

  Note that the region detection operation of the region detection unit 42 is not limited to the above operation example. A general image data processing technique can be used to detect the edge region and the non-edge region of the determination image data.

  Returning to the description of FIG. The front determination unit 43 determines whether the edge region and the non-edge region detected by the region detection unit 42 are a document region or a background region. The pre-determination unit 43 determines whether the edge region and the non-edge region detected by the region detection unit 42 are document regions or regions according to the following procedure.

  (Procedure 1) First, the pre-determination unit 43 detects the region detected by the region detection unit 42 when the regions (edge region and non-edge region) detected by the region detection unit 42 satisfy all of the following two conditions: Are temporarily determined as a background region. On the other hand, the pre-determination unit 43 tentatively determines the area detected by the area detection unit 42 as a document area when even one of the following two conditions is not satisfied.

Condition 1-1: It is a non-edge area Condition 1-2: No edge is included in the area

  FIG. 11 is a diagram illustrating an operation example of the pre-determination unit 43. FIG. 11A shows the provisional determination result of the document area and the background area for the non-edge areas L1 and L3 and the edge area L2 in FIG. In FIG. 11, black portions indicate portions that are provisionally determined as background regions, and white portions indicate portions that are provisionally determined as document regions.

  For example, the non-edge regions L1 and L3 in FIG. 8 satisfy the condition 1-1 and the condition 1-2. Accordingly, the front determination unit 43 temporarily determines the non-edge regions L1 and L3 as background regions. On the other hand, the edge region L2 does not satisfy the condition 1-1. Accordingly, the pre-determination unit 43 provisionally determines the edge area L2 as a document area.

  Accordingly, the provisional determination result of the document area and the background area for the non-edge areas L1 and L3 and the edge area L2 in FIG. 8 is as shown in FIG. In addition, the dashed-dotted line shown in FIG. 11 has shown the coordinate which the paper detection sensor 12 passes.

  (Procedure 2) Next, the pre-determination unit 43 determines (changes) the tentatively determined area as the document area when the tentatively determined area satisfies all the following three conditions.

Condition 2-1: Touching the lower end of the determination image data Condition 2-2: Including coordinates through which the paper detection sensor 12 passes or including coordinates through which a paper feed sensor that detects the start and completion of feeding passes (Including the coordinates through which the document of the scanning unit 13 passes, for example, the coordinates of the document in the scanning direction axis (x axis) of the scanning unit 13 shown in FIG. 2B)
Condition 2-3: Do not touch the upper end of the image data for determination

  FIG. 11B shows the determination result of the document area and the background area with respect to the temporary determination result of FIG.

  For example, the non-edge region L1 provisionally determined as the background region does not satisfy the condition 2-3. Therefore, the previous determination unit 43 leaves the non-edge region L1 as the background region. The edge region L2 provisionally determined as the document region satisfies the conditions 2-1 to 2-3. Accordingly, the pre-determination unit 43 leaves the edge area L2 as the original area. The non-edge region L3 determined as the background region satisfies the conditions 2-1 to 2-3. Accordingly, the pre-determination unit 43 determines (changes) the non-edge region L3 as a document region.

  Thereby, the provisional determination result shown in FIG. 11A is changed as shown in FIG. That is, the determination results of the document area and the background area for the non-edge areas L1 and L3 and the edge area L2 in FIG. 8 are finally as shown in FIG.

  Returning to the description of FIG. The continuation determination unit 44 determines the continuation image data based on the determination result of the document region and the background region of the determination image data determined by the previous determination unit 43 and the edge of the continuation image data extracted by the edge extraction unit 41. The document area and the background area are determined. For example, the continuation determination unit 44 applies the determination result determined by the determination image data to the edge region and non-edge region of the subsequent image data following the edge region and non-edge region of the determination image data.

  More specifically, the continuation determination unit 44 determines that the edge region of the continuation image data following the edge region of the determination image data determined as the background region is a background region. Further, the continuation determination unit 44 determines that the non-edge area of the continuation image data following the non-edge area of the determination image data determined as the background area is the background area. Further, the continuation determination unit 44 determines that the edge area of the continuation image data following the edge area of the determination image data determined as the document area is the document area. Further, the continuation determination unit 44 determines that the non-edge area of the continuation image data following the non-edge area of the determination image data determined to be the document area is the document area.

  FIG. 12 is a diagram illustrating a determination result example of the continuation determination unit 44. FIG. 12 shows the background area and the document area of the image data output from the scanning unit 13 determined by the continuation determining unit 44. In FIG. 12, black portions indicate portions determined as background regions, and white portions indicate portions determined as document regions. 12 indicates the determination image data portion of the image data output from the scan unit 13, and the subsequent image data D12 indicates the subsequent image data of the image data output from the scan unit 13. Shows the part.

  The non-edge region L1 illustrated in FIG. 8 is determined as a background region by the previous determination unit 43, as described with reference to FIG. Therefore, the continuation determination unit 44 determines that the non-edge region following the non-edge region L1 of the determination image data D11 is a background region.

  The edge region L2 and the non-edge region L3 shown in FIG. 8 are determined to be document regions by the previous determination unit 43, as described with reference to FIG. Accordingly, the continuation determination unit 44 determines that the edge region following the edge region L2 of the determination image data D11 and the non-edge region following the non-edge region L3 of the determination image data D11 are document regions.

  As a result, the image data output from the scanning unit 13 is divided into a document area and a background area as shown in FIG.

  The determination operation of the continuation determination unit 44 will be specifically described. The continuation determination unit 44 performs a first pattern determination from one end to the other end (for example, from the left end to the right end) in one line of the continuation image data, and temporarily determines the document area and the background area of each pixel in one line. To do. When the continuation determination unit 44 provisionally determines the document area and the background area of each pixel from one end to the other end of the line, conversely, in the line, from the other end to one end (for example, from the right end to the left end) 2 pattern determination is performed, and the temporarily determined original area and background area are corrected. The continuation determination unit 44 performs the above processing on all lines of the continuation image data.

  FIG. 13 is a diagram illustrating determination conditions for the first pattern determination performed by the continuation determination unit 44. The attention pixel and the reference pixel shown in FIG. 13 are the same as the definition of the attention pixel and the reference pixel described in FIG.

  The continuation determination unit 44 performs the first pattern determination of each pixel from the left end to the right end of one line of the continuation image data in accordance with the determination condition shown in FIG. For example, when the target pixel is “edge”, the continuation determination unit 44 sets “1” to the fourth bit of the first determination pattern indicated by 8-bit data. Further, for example, if the reference pixel based on the definition shown in FIG. 9 includes a document and an edge reference pixel, the continuation determination unit 44 sets “1” to the third bit of the first determination pattern.

  In the above description, the first determination pattern is 8 bits, but is not limited thereto. Since the first determination pattern has “0 to 4 bits” in the bit, at least 5 bits are sufficient.

  FIG. 14 is a first diagram illustrating a data configuration example of the storage unit 34. As shown in FIG. 14, in the storage unit 34, information on “1” and “0” indicating whether the target pixel is a pixel in the document area or a background area is stored in advance in the first determination pattern. Are stored in association with each other.

  For example, it is assumed that the result of the first determination pattern of a pixel of interest by the first pattern determination of the continuation determination unit 44 is “9” (“00000101” in 8-bit data). In the case of the example in FIG. 14, the target pixel is provisionally determined to be a pixel in the background area.

  FIG. 15 is a first diagram illustrating an operation example of the first pattern determination of the continuation determination unit 44. The pixels on the line indicated by the arrow A11 in FIGS. 15A and 15C indicate the pixels at the lower end of the determination image data. That is, the pixels on the line indicated by the arrow A11 in FIGS. 15A and 15C and the pixels above it indicate the pixels of the determination image data. Further, the pixels below the pixels on the line indicated by the arrow A11 in FIGS. 15A and 15C indicate the pixels of the subsequent image data.

  The hatched cells shown in FIGS. 15A and 15C indicate non-edge pixels, and the non-hatched cells indicate edge pixels. Further, “0” shown in the square indicates a pixel in the background area, and “1” indicates a pixel in the document area.

  Note that the edges and non-edges of each pixel of the image data (unhatched and hatched cells in FIG. 15) have already been extracted by the edge extraction unit 41. Further, the document area and the background area (“0” and “1” up to the line of the arrow A11 in FIG. 15) of the determination image data have already been determined by the previous determination unit 43.

  The continuation determination unit 44 performs the first pattern determination using the edge and non-edge of the pixel at the lower end of the determination image data and the determination results of the document area and the background area, and performs the document area and background of the continuation image data. Do the area.

  For example, the pixel “a1” shown in FIG. Since the target pixel is a non-edge, the reference pixel is (B) in FIG. In this case, the first determination pattern is “01001” (“9” in decimal) as shown in FIG.

  The continuation determination unit 44 refers to the storage unit 34 illustrated in FIG. 14 and acquires the “background region” corresponding to the first determination pattern “9”. Thus, the pixel “a1” shown in FIG. 15A becomes “0” (background region) as shown in FIG. 15C.

  FIG. 16 is a second diagram illustrating an operation example of the first pattern determination of the continuation determination unit 44. FIG. 16A shows the pixel shown in FIG.

  A pixel “a2” illustrated in FIG. 16A is a target pixel. Since the target pixel is an edge, the reference pixel is (A) in FIG. In this case, the first determination pattern is “11101” (“29” in decimal) as shown in FIG.

  The continuation determination unit 44 refers to the storage unit 34 illustrated in FIG. 14 and acquires the “document area” corresponding to the first determination pattern “29”. As a result, the pixel “a2” shown in FIG. 16A becomes “1” (document area) as shown in FIG.

  When the first pattern determination is performed up to the right end in one line, the continuation determination unit 44 performs a second pattern determination in the reverse direction and corrects the first pattern determination result.

  FIG. 17 is a diagram illustrating determination conditions for the second pattern determination performed by the continuation determination unit 44. In the second pattern determination, the reference pixel is only a pixel on the right side of the target pixel regardless of whether the target pixel is an edge or a non-edge.

  The continuation determination unit 44 performs the second pattern determination of each pixel from the right end to the left end of one line of the continuation image data according to the determination condition shown in FIG. For example, when the target pixel is “original”, the continuation determination unit 44 sets “1” to the third bit of the second determination pattern indicated by the 8-bit data. For example, the continuation determination unit 44 sets “1” to the 0th bit of the second determination pattern when the pixel on the right is an edge.

  In the above description, the second determination pattern is 8 bits, but is not limited thereto. Since the second determination pattern has “0 to 3 bits” in the bit, at least 4 bits are sufficient.

  FIG. 18 is a second diagram illustrating a data configuration example of the storage unit 34. In addition to the data shown in FIG. 14, the storage unit 34 also stores data shown in FIG. The storage unit 34 stores in advance the second determination pattern and information “1” and “0” indicating whether the target pixel is a pixel in the document area or a pixel in the background area. Is done.

  For example, it is assumed that the result of the second determination pattern of a pixel of interest by the second pattern determination of the continuation determination unit 44 is “8” (“00001000” in 8-bit data). In the case of the example in FIG. 18, the target pixel is determined to be a pixel in the background area.

  FIG. 19 is a first diagram illustrating an operation example of the second pattern determination of the continuation determination unit 44. When the continuation determination unit 44 performs the first pattern determination to the right end in one line, the continuation determination unit 44 performs the second pattern determination toward the left end in the line.

  A pixel “1” with an underline in FIG. 19A is a pixel of interest. The reference pixel is a pixel on the right side of the target pixel. In this case, the second determination pattern is “1000” (“8” in decimal) as shown in FIG.

  The continuation determination unit 44 refers to the storage unit 34 illustrated in FIG. 18 and acquires the “background region” corresponding to the second determination pattern “8”. Accordingly, the underlined “1” pixel shown in FIG. 19A is corrected to “0” (background region) as shown in FIG. 19C.

  FIG. 20 is a second diagram illustrating an operation example of the second pattern determination of the continuation determination unit 44. FIG. 20A shows the pixel shown in FIG.

  A pixel “1” with an underline in FIG. The reference pixel is a pixel on the right side of the target pixel. In this case, as shown in FIG. 20B, the second determination pattern is “1100” (decimal number “12”).

  The continuation determination unit 44 refers to the storage unit 34 illustrated in FIG. 18 and acquires the “document area” corresponding to the second determination pattern “12”. Thus, the underlined “1” pixel shown in FIG. 20A becomes “1” (document area) as shown in FIG. 20C.

  The continuation determination unit 44 performs the first pattern determination and the second pattern determination for each line up to the lower end of the continuation image data. Based on “0” and “1” assigned to each pixel of the image data by the first pattern determination and the second pattern determination, for example, as shown in FIG. Data D12 can be divided into a document area and a background area.

The process of the continuation determination unit 44 is based on the following concept.
As described below, when the reference pixel has the same edge value as the target pixel, the document region and the background region of the reference pixel are set as the target pixel.
When the reference pixel has an edge and a document area, and the target pixel is an edge, the target pixel is set as the document area.
If the reference pixel has a non-edge and document area, and the target pixel is non-edge, the target pixel is set as the document area.
If the reference pixel has an edge and a background area and the target pixel is an edge, the target pixel is set as the background area.
If the reference pixel has a non-edge and background area and the target pixel is non-edge, the target pixel is set as the background area.

When the above does not apply, whether the pixel of interest is the document region or the background region is determined by the surrounding document region and the background region as follows.
When the reference pixel is only the document area, the target pixel is set as the document area.
When the reference pixel includes a document area and a background area, when the target pixel is an edge, the target pixel is a document area. When the target pixel is a non-edge, the target pixel is a background area.
When the reference pixel is only the background area, the target pixel is set as the background area.

  Returning to the description of FIG. The cutout unit 45 cuts out a document portion from the image data output from the scan unit 13 based on the document region and the background region of the image data determined by the previous determination unit 43 and the continuation determination unit 44.

  FIG. 21 is a first diagram illustrating an example of document cutting. FIG. 21 shows a document area (a white area) and a background area (a black area) of the image data determined by the pre-determination unit 43 and the continuation determination unit 44.

  The cutout unit 45 searches the document area of the image data determined by the previous determination unit 43 and the subsequent determination unit 44 from the upper end to the lower end of the image data (in the + y-axis direction). For example, the cutout unit 45 searches the document area in the + y-axis direction as indicated by an arrow in FIG. The cutout unit 45 stores the coordinates (x, y) of the document area searched (found) first in the storage unit 34 as the upper end coordinates of the document.

  Note that the cutout unit 45 searches the first document area in the + y-axis direction while incrementing the x coordinate by one.

  FIG. 22 is a second diagram illustrating an example of document cutting. The black circles shown in FIG. 22 indicate the coordinates of the document area that the cutout unit 45 first searches in the + y-axis direction. FIG. 22 shows only 15 coordinates, but there are actually many more.

  The clipping unit 45 determines that the median value of the coordinates of the first document area searched in the + y-axis direction is the upper end of the document.

  FIG. 23 is a third diagram illustrating an example of document cutting. As shown in FIG. 23, the cutout unit 45 rearranges the coordinates of the document area searched in the + y-axis direction in descending order based on the y-coordinate values. Then, the cutout unit 45 determines the coordinate of the median value of the rearranged y coordinate values as the upper end of the document. For example, the cutout unit 45 determines the y coordinate value of the coordinate of the arrow A21 shown in FIG. 23 as the coordinate value of the upper end of the document.

  The clipping unit 45 searches the first document area in the same manner as in FIGS. 21 and 22, whether from the lower end of the image data toward the upper end (in the −y-axis direction). Then, in the same manner as in FIG. 23, the cutout unit 45 determines that the median y coordinate value of the searched document area is the coordinate value of the lower end of the document.

  In addition, the cutout unit 45 searches for the first document area in the same manner as in FIGS. 21 and 22, whether from the left end of the image data to the right end (toward the + x axis direction). Then, in the same manner as in FIG. 23, the cutout unit 45 determines the x coordinate value of the median value of the searched document area as the coordinate value of the left end of the document.

  Further, the cutout unit 45 searches for the first document area in the same manner as in FIGS. 21 and 22, whether from the right end of the image data to the left end (toward the −x axis direction). Then, the cutout unit 45 determines the x coordinate value of the median value of the searched document area as the coordinate value of the right end of the document, as in FIG.

  Then, the cutout unit 45 cuts out the document portion from the image data output from the scan unit 13 using the coordinate values (rectangular regions) indicating the top, bottom, left, and right edges of the document determined as described above. Thereby, for example, a white portion (original portion) shown in FIG. 21 is cut out.

  FIG. 24 is a flowchart illustrating an operation example of the image processing apparatus 1. The image processing apparatus 1 executes the processing of the flowchart shown in FIG. 24 when a document is placed in the paper feed port 4a and the input device 5 receives a predetermined operation from the user.

  First, the ADF unit 4 feeds a document placed in the paper feed port 4a to the scanning unit 13 (step S1).

  Next, the scanning unit 13 scans the document fed by the ADF unit 4 in step S1, and outputs image data (step S2).

  Next, the edge extraction part 41 extracts the edge of the image data output in step S2 (step S3).

  Next, the area detection unit 42 reads determination image data, which is image data for a predetermined line, from the image data output in step S2, and based on the edges extracted in step S3, the determination image data The edge region and the non-edge region are detected (step S4).

  Next, the pre-determination unit 43 determines whether the edge region and the non-edge region of the determination image data detected in step S4 based on the conditions 1-1, 1-2 and the conditions 2-1 to 2-3. It is determined whether the document area or the background area (step S5).

  Next, the continuation determination unit 44 continues the continuation image data following the determination image data based on the document area and the background area of the determination image data determined in step S5 and the edge extracted in step S3. The document area and the background area are determined (step S6).

  Next, the cutout unit 45 performs step S2 based on the document area and background area of the determination image data determined in step S5 and the document area and background area of the continuous image data determined in step S6. The document area is cut out from the image data output at (Step S7). Then, the image processing apparatus 1 ends the process of the flowchart.

  As described above, the scanning unit 13 scans the original fed from the ADF unit 4 and outputs image data. The edge extraction unit 41 extracts the edge of the image data output from the scanning unit 13, and the region detection unit 42 based on the edge extracted by the edge extraction unit 41, the edge region and the non-edge region of the determination image data Is detected. The pre-determination unit 43 determines whether the edge region and the non-edge region of the determination image data detected by the region detection unit 42 are a document region or a background region. Then, the continuation determination unit 44 converts the determination image data into the determination image data based on the edge extracted by the edge extraction unit 41 and the determination result of the document area and the background area of the determination image data determined by the previous determination unit 43. The document area and background area of subsequent image data are determined. Thereby, the image processing apparatus 1 can appropriately separate the image data into the document portion and the background portion.

  Further, the image processing apparatus 1 determines the document area and the background area of the subsequent image data based on the edge value of the target pixel and the edge value of the reference pixel patterned for determination, and the document area and the background area. As a result, the image processing apparatus 1 may perform the region determination process only once from the top to the bottom for the subsequent image data, and the processing time can be shortened.

  The control unit 31 further includes a scan type determination unit that determines whether the scanning unit 13 scans a document fed from the ADF unit 4 or scans a document placed on the reading table of the main body 2. May be. For example, when the paper detection sensor 12 detects a document and the user performs a predetermined operation on the input device 5, the scan type determination unit determines that the scan unit 13 scans a document fed from the ADF unit 4. To do. The edge extraction unit 41, the region detection unit 42, the previous determination unit 43, the continuation determination unit 44, and the cutout unit 45 are scanned by the scan type determination unit when the scan unit 13 scans a document fed from the ADF unit 4. When it is determined, the operation described above is performed.

  On the other hand, when the scan type determination unit determines that the document placed on the reading table of the main body 2 is scanned, the control unit 31 performs a predetermined process on the document area from the image data of the document placed on the reading table. Cut out. For example, the control unit 31 extracts an edge of the image data output from the scanning unit 13, and detects a non-edge region of the image data based on the extracted edge. Then, the control unit 31 tentatively determines whether the detected non-edge region is a document region or a background region based on the following first tentative determination condition and second tentative determination condition. Based on the arrangement of the non-edge regions, the provisional determination of the non-edge regions may be corrected, and the document region may be cut out from the document region and the background region in which the provisional determination is corrected. For example, it is assumed that there are adjacent background areas, one of which is adjacent to the document area. In this case, the control unit 31 corrects the background area adjacent to the document area to the document area.

First provisional determination condition: the non-edge region is in contact with data edges of two or more sides of the image data Second provisional determination condition: the non-edge region does not include an edge

  Further, the function of the control unit 31 illustrated in FIG. 4 may be included in an information processing apparatus such as a personal computer or a tablet terminal.

  FIG. 25 is a diagram illustrating a functional block configuration example of the information processing apparatus 60. As illustrated in FIG. 25, the information processing apparatus 60 includes a control unit 31a, an I / F unit 61, and a storage unit 62.

  The control unit 31a, the edge extraction unit 41a, the region detection unit 42a, the previous determination unit 43a, the continuation determination unit 44a, and the cutout unit 45a illustrated in FIG. Since it has the same function as the unit 42, the previous determination unit 43, the continuation determination unit 44, and the cutout unit 45, description thereof will be omitted.

  An I / F unit 61 (corresponding to a receiving unit of the present invention) receives image data of a document scanned by the scanning unit 13 of the image processing apparatus 1 by wire or wirelessly. The received image data is stored in the storage unit 62.

  The storage unit 62 stores an application program that realizes the function of the control unit 31a. The storage unit 62 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive).

  The function of the control unit 31a is realized by a CPU that executes an application program stored in the storage unit 62. The control unit 31a determines the document area and the background area of the image data in the same manner as described above for the image data received by the I / F unit 61 (image data stored in the storage unit 62). To do. Then, the control unit 31a cuts out the document portion from the image data.

  As described above, the information processing apparatus 60 may divide the image data into the document area and the background area and cut out the document portion.

[Second Embodiment]
In the second embodiment, the determination method of the document area and the background area of the determination image data is different from that of the first embodiment.

  FIG. 26 is a diagram illustrating a functional block configuration example of the image processing apparatus 1 according to the second embodiment. In FIG. 26, the same components as those in FIG. 4 are denoted by the same reference numerals. Below, a different part from FIG. 4 is demonstrated. As shown in FIG. 26, the control unit 31 of the image processing apparatus 1 has a pre-determination unit 71.

  The front determination unit 71 determines whether the edge region and the non-edge region detected by the region detection unit 42 are a document region or a background region. The pre-determination unit 71 determines whether the edge region and the non-edge region detected by the region detection unit 42 are document regions or regions according to the following procedure.

  (Procedure 1) First, when the region detected by the region detection unit 42 satisfies all the following two conditions, the pre-determination unit 71 temporarily determines the region detected by the region detection unit 42 as a background region. . On the other hand, when at least one of the following two conditions is not satisfied, the pre-determination unit 71 provisionally determines the region detected by the region detection unit 42 as a document region.

Condition 11-1: Non-edge area Condition 11-2: No edge is included in the area

  FIG. 27 is a diagram for explaining an operation example of the pre-determination unit 71. FIG. 27A shows determination image data 81 among the image data output from the scanning unit 13. The determination image data 81 includes a vertical stripe 82, a background 83, a shadow 84, and a document 85. The vertical stripes 82 appear due to, for example, paper dust accumulated in the scanning unit 13.

  FIG. 27B shows an example of an edge extracted from the determination image data 81 shown in FIG. When the edge extraction unit 41 extracts an edge from the determination-use image data 81 shown in FIG. 27A, the edge extraction unit 41 becomes as shown in FIG. A white portion shown in FIG. 27B is an edge region. The vertical stripes 82 are extracted as edges.

  FIG. 27C shows edge regions and non-edge regions detected based on the edges in FIG. When the area detection unit 42 detects the edge area and the non-edge area based on the edge of FIG. 27B, as shown in FIG. 27C, the non-edge area L11, the edge area L12, and the non-edge area An edge region L13, an edge region L14, and a non-edge region L15 are detected.

  FIG. 27D shows the provisional determination results of the document area and the background area for the non-edge areas L11, L13, L15 and the edge areas L12, L14 shown in FIG. Based on the above conditions 11-1 and 11-2, the pre-determination unit 71 determines the document area and the background area for the non-edge areas L11, L13, and L15 and the edge areas L12 and L14 in FIG. The provisional determination is as shown in FIG.

  For example, the non-edge regions L11, L13, and L15 in (C) of FIG. 27 are temporarily determined as background regions (blackened portions) as shown in (D) of FIG. Further, the edge regions L12 and L14 in FIG. 27C are provisionally determined as document regions (white portions) as shown in FIG.

  (Procedure 2) Next, the pre-determination unit 71 determines whether or not the area temporarily determined above satisfies the following two conditions.

Condition 12-1: The area is in contact with the lower end of the image data for determination. Condition 12-2: The coordinates through which the paper detection sensor 12 passes or the coordinates through which the paper feed sensor passes are included.

  The pre-determination unit 71 determines that the area satisfies the above two conditions and does not contact the upper end of the determination image data as the first type original area.

  Further, if the pre-determination unit 71 is an area that satisfies the above two conditions and does not contact the upper left end and the upper right end of the image data for determination but not the first type original area, the predetermination unit 71 determines that the area is the second type The document area is determined.

  Further, the pre-determination unit 71 is an area that satisfies the above two conditions, and is not in the first-type original area or the second-type original area, but in either the upper left end or the upper right end of the determination image data. In the case of contact, the area is determined as the third type document area.

  FIG. 28 is a diagram for explaining the first type document region, the second type document region, and the third type document region. FIG. 28A shows the form of the first type document area. FIG. 28B shows a form of the second type document area. (C) and (D) of FIG. 28 show the form of the third type document area. In FIG. 28, the black-painted portion indicates the background area, and the white-painted portion indicates the document area.

  For example, the non-edge region L13 provisionally determined as the background region in (C) and (D) of FIG. 27 is a region that satisfies the above conditions 12-1 and 12-2, and is the upper right end of the determination image data. It is the area that touches only. Therefore, the non-edge region L13 is provisionally determined to be the third type document region in FIG.

  27C and 27D, the edge region L14 and the non-edge region L15, which are provisionally determined to be the document region, satisfy the above conditions 12-1 and 12-2 and are used for determination. This is an area that does not touch the upper end of the image data. Therefore, the edge region L14 and the non-edge region L15 are determined as the first type document region in FIG.

  (Procedure 3) Next, the pre-determination unit 71 determines whether the first-type original area, the second-type original area, the second-type original area, It is determined whether the third type document area is a document area or a background area.

  For example, when the first type document area exists, the front determination unit 71 determines the first type document area as the document area, and determines the second type document area and the third type document area as the background area.

  Further, when the first type original area does not exist and the second type original area exists, the pre-determination unit 71 determines that the second type original area is the original area, and determines that the third type original area is the background area. To do.

  Further, when the first-type document area and the second-type document area do not exist and the third-type document area exists, the pre-determination unit 71 determines that the third-type document area is the document area.

  Further, when the first-type document area, the second-type document area, and the third-type document area do not exist, the previous determination unit 71 determines that all areas are document areas.

  In the example described in the procedure 2, the edge region L14 and the non-edge region L15 are determined as the first type document region, and the non-edge region L13 is determined as the third type document region. Therefore, the edge region L14 and the non-edge region L15 are determined as the document region by the procedure 3, and the non-edge region L13 is determined as the background region.

  (Procedure 4) Next, when the area determined as the document area by the above procedure satisfies all the following two conditions, the previous determination unit 71 changes the area to the background area.

Condition 13-1: Touching the lower end of the determination image data Condition 13-2: Do not include coordinates through which the paper detection sensor 12 passes or do not include coordinates through which the paper feed sensor passes

  For example, the edge region L12 is determined as the document region in the procedure 1. The edge region L12 satisfies the above conditions 13-1 and 13-2. Accordingly, the front determination unit 71 changes the edge region L12 to the background region.

  Note that the non-edge regions L11 and L13 and the edge region L12 illustrated in FIG. 27C are finally determined as background regions by the above-described procedure 1 to procedure 4. Further, the edge region L14 and the non-edge region L15 shown in FIG. 27C are finally determined as document regions by the above-described procedure 1 to procedure 4. That is, in the determination image data 81 shown in FIG. 27A, the document area and the background area are determined as in FIG. 11B.

  As described above, the pre-determination unit 71 determines the document area and the background area of the determination-use image data based on the procedures 1 to 4. As a result, the image processing apparatus 1 can appropriately separate the image data into the document portion and the background portion even if the image data includes vertical stripes (noise) due to paper dust or the like.

  As mentioned above, although this invention was demonstrated using embodiment, the functional structure of the image processing apparatus 1 and the information processing apparatus 60 is classified according to the main processing content in order to make the structure easy to understand. . The present invention is not limited by the way of classification and names of the constituent elements. The configurations of the image processing device 1 and the information processing device 60 can be classified into more components according to the processing content. Moreover, it can also classify | categorize so that one component may perform more processes. Further, the processing of each component may be executed by one hardware or may be executed by a plurality of hardware.

  Further, the technical scope of the present invention is not limited to the scope described in the above embodiment. It will be apparent to those skilled in the art that various changes and modifications can be made to the above-described embodiment. For example, the embodiments may be combined. Further, it is apparent from the scope of the claims that embodiments with such changes or improvements can also be included in the technical scope of the present invention. The present invention can also be provided as a program that realizes the functions of the image processing apparatus 1 and the information processing apparatus 60 and a storage medium that stores the program.

  DESCRIPTION OF SYMBOLS 1 ... Image processing apparatus, 2 ... Main body, 3 ... Cover, 4 ... ADF part, 4a ... Paper feed port, 4b ... Paper discharge port, 5 ... Input device, 11 ... Document, 12 ... Paper detection sensor, 13 ... Scan part 21 ... Image data, 21a ... Image data for determination, 21b ... Continuous image data, 22 ... Area, OS1, OS2 ... Overscan, 31, 31a ... Control part, 32 ... Communication part, 33 ... Input part, 34 ... Memory , 41, 41a ... edge extraction unit, 42, 42a ... area detection unit, 43, 43a ... previous determination unit, 44, 44a ... continuation determination unit, 45, 45a ... cutout unit, 51 ... determination image data, 52 ... Background, 53 ... Shadow, 54 ... Document, 60 ... Information processing device, 61 ... I / F unit, 62 ... Storage unit, 71 ... Predetermining unit, 81 ... Image data for determination, 82 ... Vertical stripe, 83 ... Background, 84 ... Shadow, 85 ... Original.

Claims (10)

A feeding unit for feeding the scan object;
A scanning unit that scans the scanned object to be fed and outputs image data;
An edge extraction unit for extracting an edge of the image data;
An area detection unit that detects an edge area and a non-edge area of image data for determination from the upper end of the image data to a predetermined line based on the edge;
A pre-determination unit that determines whether the detected edge region and the non-edge region are a scan target region or a background region;
Based on the determination result of the scan target area and the background area of the determination image data and the edge of the subsequent image data following the determination image data, the scan target area of the subsequent image data and the A continuation determination unit for determining a background area;
An image processing apparatus comprising: The image processing apparatus according to claim 1,
The pre-determination unit provisionally determines the non-edge region that does not include the edge as the background region,
Tentatively determining the non-edge area including the edge and the edge area as the scan object area;
An image processing apparatus. The image processing apparatus according to claim 2,
The scan unit overscans the scan object,
In the pre-determination unit, the temporarily determined edge region and the non-edge region are not in contact with the upper end of the determination image data, but in contact with the lower end of the determination image data, and the scan target of the scan unit When the object includes coordinates that pass, the provisionally determined edge region and the non-edge region are determined as the scan target region,
An image processing apparatus. The image processing apparatus according to claim 2,
The pre-determination unit includes the provisionally determined edge region and the non-edge region that are in contact with a lower end of the determination image data and include coordinates through which the scan target of the scan unit passes.
When the edge region and the non-edge region do not touch the upper end of the determination image data, the edge region and the non-edge region are determined as a first type scan object region,
When the edge region and the non-edge region are not the first type scan object region and do not touch the upper left end point and the upper right end point of the image data for determination, the edge region and the non-edge region are Mold scanning object area,
When the edge region and the non-edge region touch only one of the upper left end point and the upper right end point of the determination image data, not the first type scan target region and the second type scan target region , Determining the edge region and the non-edge region as a third type scan object region,
Whether the edge area and the non-edge area are the scan object areas based on the presence or absence of the first type scan object area, the second type scan object area, and the third type scan object area Or determine whether it is the background area,
An image processing apparatus. The image processing apparatus according to any one of claims 1 to 4,
The continuation determination unit determines a determination result determined by the determination image data for the edge region and the non-edge region of the continuation image data following the edge region and the non-edge region of the determination image data. Apply,
An image processing apparatus. An image processing apparatus according to any one of claims 1 to 5,
A scan type determination unit that determines whether the scan unit scans the scan object fed from the feeding unit or scans the scan object placed on a table;
The pre-determination unit determines the scan target region and the background region of the determination image data according to a determination result of the scan type determination unit.
An image processing apparatus. The image processing apparatus according to any one of claims 1 to 6,
The edge extraction unit calculates a luminance dispersion difference between a luminance dispersion of a first pixel of the image data and a luminance dispersion of a second pixel around the first pixel, and based on the luminance dispersion difference Extracting an edge of the image data;
An image processing apparatus. A receiving unit that receives image data scanned by the image processing apparatus by feeding a scan object;
An edge extraction unit for extracting an edge of the image data;
An area detection unit that detects an edge area and a non-edge area of image data for determination from the upper end of the image data to a predetermined line based on the edge;
A pre-determination unit that determines whether the detected edge region and the non-edge region are a scan target region or a background region;
Based on the determination result of the scan target area and the background area of the determination image data and the edge of the subsequent image data following the determination image data, the scan target area of the subsequent image data and the A continuation determination unit for determining a background area;
An information processing apparatus comprising: An image processing method of an image processing apparatus,
Feeding the scan object;
Scanning the object to be fed and outputting image data;
Extracting an edge of the image data;
Detecting an edge region and a non-edge region of image data for determination from the upper end of the image data to a predetermined line based on the edge;
Determining whether the detected edge region and the non-edge region are a scan target region or a background region;
Based on the determination result of the scan target area and the background area of the determination image data and the edge of the subsequent image data following the determination image data, the scan target area of the subsequent image data and the Determining a background region;
An image processing method comprising: An image processing method for an information processing apparatus,
Receiving from the image processing apparatus image data scanned by the image processing apparatus feeding a scan object; and
Extracting an edge of the image data;
Detecting an edge region and a non-edge region of image data for determination from the upper end of the image data to a predetermined line based on the edge;
Determining whether the detected edge region and the non-edge region are a scan target region or a background region;
Based on the determination result of the scan target area and the background area of the determination image data and the edge of the subsequent image data following the determination image data, the scan target area of the subsequent image data and the Determining a background region;
An image processing method comprising:

Images