Information processing apparatus, information processing method, and information processing program
The information processing device enhances form detection by identifying and expanding brightness boundaries to capture low-brightness areas near the edge, ensuring complete form recognition and extraction.
Patent Information
- Application Number
- JP2024134551
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2026-02-24
AI Technical Summary
Conventional image detection methods fail to recognize areas of low brightness near the edge of a form, such as a white-printed title, which are mistaken for the background, leading to incomplete detection of the form.
An information processing device and method that detects a first region with distinct brightness boundaries, expands this region to a second region, and further adds a third region satisfying specific conditions to define a fourth region, which is then cut out as the image of the detection target, effectively capturing areas of low brightness near the form edge.
This approach ensures accurate detection of forms by including low-brightness areas near the edge, preventing them from being missed, and allows for proper image extraction and processing.
Smart Images

Figure 2026031184000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]
[0002] Patent Document 1 discloses a technology for acquiring an image of a form placed on a scanner mat using a non-contact scanner and detecting the form area within the scanner's field of view. Specifically, when detecting the area of the form contained in the image data of the non-contact scanner, the conventional technology searches for points of change in the brightness of the image to detect the edge parts (line segments) of the form at the boundary points between the black scanner mat and the form, and detects the part where the detected line segments form a rectangle as the form area. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-147976 Summary of the Invention [Problem to be solved by the invention]
[0004] However, with the conventional method described in Patent Document 1, for example, if there is an area of low brightness near the edge of a form and the form title or the like is printed in white in this area, the brightness of this area is close to the brightness of the scanner mat behind the form, so the white-printed area may not be recognized as part of the form and may be missing.As such, the conventional technology has room for improvement in detecting the image of the detection target from an image obtained by capturing an area that includes the image of the detection target, such as a form, and the background, such as the scanner mat, behind the image of the detection target.
[0005] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide an information processing device, an information processing method, and an information processing program that can appropriately detect an image of a detection target such as a form. [Means for solving the problem]
[0006] The information processing device of the present invention includes a detection unit that detects a first region in which lines at a boundary portion where brightness differs form a specific shape in an image obtained by capturing an image of an object to be detected and a background behind the object to be detected and having a brightness lower than the brightness of the pixels included in the object to be detected; a setting unit that sets a fourth region by adding a third region that satisfies specific conditions to the first region within the portion from the edge of a second region that includes the entire first region and has an area larger than that of the first region to the edge of the first region; and a cutting unit that cuts out the set fourth region as the image of the object to be detected.
[0007] In addition, the information processing method of the present invention detects a first region in which lines at a boundary portion where brightness differs form a specific shape in an image obtained by capturing an image including an image of a detection target and a background behind the image of the detection target and having a brightness lower than the brightness of the pixels included in the image of the detection target, sets a fourth region by adding to the first region a third region that satisfies specific conditions within the portion from the edge of a second region that includes the entire first region and has an area larger than that of the first region to the edge of the first region, and then cuts out the set fourth region as the image of the detection target, performed by a computer.
[0008] In addition, the information processing program of the present invention causes a computer to perform the following process: detect a first region in which lines at a boundary portion where the brightness differs in an image obtained by capturing an image including an image of a detection target and a background behind the image of the detection target and whose brightness is lower than the brightness of the pixels included in the image of the detection target form a specific shape; set a fourth region by adding to the first region a third region that satisfies specific conditions within the portion from the edge of a second region that includes the entire first region and has an area larger than that of the first region to the edge of the first region; and cut out the set fourth region as the image of the detection target. [Effects of the Invention]
[0009] According to the present invention, it is possible to provide an information processing device, an information processing method, and an information processing program that can appropriately detect an image of a detection target such as a form. [Brief explanation of the drawings]
[0010] [Figure 1A] FIG. 1A is a diagram illustrating an example of the configuration of an information processing system 10 according to an embodiment of the present disclosure. [Figure 1B] FIG. 1B is a diagram showing the appearance of the non-contact scanner 14. As shown in FIG. [Figure 2] FIG. 2 is a diagram showing an example of the main functions of the information processing device 12. As shown in FIG. [Figure 3] FIG. 3 is a diagram showing an example of the function of the specific processing unit 290. As shown in FIG. [Figure 4A] FIG. 4A is a diagram for explaining the function of specific processing unit 290. As shown in FIG. [Figure 4B] FIG. 4B is a diagram for explaining the function of specific processing unit 290. As shown in FIG. [Figure 4C] FIG. 4C is a diagram for explaining the function of specific processing unit 290. As shown in FIG. [Figure 4D] FIG. 4D is a diagram for explaining the function of specific processing unit 290. [Figure 4E] FIG. 4E is a diagram for explaining the function of specific processing unit 290. As shown in FIG. [Figure 4F] FIG. 4F is a diagram for explaining the function of specific processing unit 290. [Figure 4G] FIG. 4G is a diagram for explaining the function of specific processing unit 290. [Figure 5] FIG. 5 is a diagram for explaining the operation of the information processing device 12. In FIG. [Figure 6A] FIG. 6A is a diagram for explaining the functions of the information processing device 12 according to the comparative example. [Figure 6B] FIG. 6B is a diagram for explaining the function of the information processing device 12 according to the comparative example. [Figure 6C] FIG. 6C is a diagram for explaining the function of the information processing device 12 according to the comparative example. [Figure 7A]FIG. 7A is a diagram for explaining the function of specific processing unit 290 according to the modified example. [Figure 7B] FIG. 7B is a diagram for explaining the function of specific processing unit 290 according to the modified example. [Figure 7C] FIG. 7C is a diagram for explaining the function of specific processing unit 290 according to the modified example. [Figure 7D] FIG. 7D is a diagram for explaining the function of the specific processing unit 290 according to the modified example. [Figure 7E] FIG. 7E is a diagram for explaining the function of specific processing unit 290 according to the modified example. [Figure 7F] FIG. 7F is a diagram for explaining the function of specific processing unit 290 according to the modified example. DETAILED DESCRIPTION OF THE INVENTION
[0011] Hereinafter, an example of an embodiment of an information processing device, an information processing method, and an information processing program according to the technique of the present disclosure will be described with reference to the accompanying drawings. First, the terminology used in the following description will be explained.
[0012] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).
[0013] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.
[0014] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.
[0015] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.
[0016] 1A shows an example of the configuration of an information processing system 10 according to an embodiment. The information processing system 10 includes an information processing device 12 and a non-contact scanner 14.
[0017] The information processing device 12 may be interpreted as, for example, a server. The information processing device 12 may include a computer 22, a database 24, and a communication I / F 26. The computer 22 may include a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 may also be connected to the bus 34. The communication I / F 26 is connected to a network 54. The network 54 may be interpreted as a WAN (Wide Area Network) and / or a LAN (Local Area Network), etc.
[0018] The non-contact scanner 14 may be interpreted as a device capable of reading an image of a detection target 100 such as a document. The non-contact scanner 14 may include a camera 40 that captures an image of the detection target 100, a computer 36, a reception device 38, and a communication I / F 44.
[0019] The detection target 100 may include, for example, a form, an identification document, etc. A form may be interpreted as, for example, a document required for a user to perform a specific task, specifically, an estimate, a purchase order (purchase order), a delivery note, a receipt, an inspection certificate, an invoice, etc. An identification document may be interpreted as, for example, a document with a photograph that proves the identity of a user who is making a specific contract or application for a mobile phone or the like, specifically, a driver's license, a disability certificate, a My Number card, a passport, etc.
[0020] The non-contact scanner 14 is not limited to a dedicated device for capturing images of documents and the like, but may be a device such as a smartphone, personal computer, or tablet terminal that has a function of transmitting image data of images of documents and the like to the information processing device 12. The image data may be interpreted as data including an image obtained by capturing an image of an area including the image of the detection target 100 and an image of its background.
[0021] 1B, the non-contact scanner 14 may further include a head 14a incorporating a camera 40, a base 14b on which the detection target 100 is placed, and a support 14c extending from the base 14b above the base 14b to support the head 14a. The head 14a may be located, for example, several tens of centimeters away from the base 14b so that the camera 40 can capture an image of the entire base 14b.
[0022] A black scanner mat 14d, for example, may be provided on the platform 14b. The scanner mat 14d is present behind the image of the detection target 100 and may be interpreted as a non-detection target or background having a lower brightness than the image of the detection target 100 and the brightness of the pixels behind the image of the detection target and included in the image of the detection target. The brightness of the entire area of the scanner mat 14d may be lower than the brightness of a first area included in the detection target 100. A specific example of the first area included in the detection target 100 will be described later. Since the brightness of the scanner mat 14d is lower than the brightness of the detection target 100, it is possible to identify the edges of the image of the detection target 100 placed on the scanner mat 14d.
[0023] Note that the non-detection target or background object is not limited to the scanner mat 14d, but may be anything that exists behind the detection target 100 and has a brightness lower than the brightness of the pixels contained in the image of the detection target 100, such as a floor, a table, a tablecloth, a handkerchief, a towel, etc.
[0024] The camera 40 may be interpreted as an imaging device that two-dimensionally reads an image of the detection target 100 placed on the scanner mat 14d by the user. Specifically, the camera 40 may be interpreted as a digital camera including an optical system such as a lens, an aperture, and a shutter, and an imaging element. The imaging element may be interpreted as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0025] 1A , the computer 36 may include a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38 and the camera 40 are also connected to the bus 52. The reception device 38 may include a touch panel, a microphone, or the like to receive user input. The processor 46 may transmit image data captured by the camera 40 to the information processing device 12 via the communication I / F 44 and the network 54 in accordance with settings input to the touch panel or the like.
[0026] FIG. 2 shows an example of the main functions of the information processing device 12. In the information processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of an "information processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. The configuration of the specific processing unit 290 will be described in detail below.
[0027] The storage 32 stores image data 58. The image data 58 may be interpreted as data of an image captured by the non-contact scanner 14, and is used by the specific processing unit 290. The storage 32 may also store image data 58 after it has been processed by the specific processing unit 290.
[0028] As shown in FIG. 3, the identification processing unit 290 may include an input unit 291, a detection unit 292, a setting unit 293, and a cut-out unit 294.
[0029] (input section 291) The input unit 291 may input image data 58 transmitted from the non-contact scanner 14. Specifically, when the form 100A placed on the scanner mat 14d as shown in FIG. 4A is imaged by the non-contact scanner 14, the input unit 291 inputs image data 58 obtained by imaging the region R including the form 100A and the scanner mat 14d. The input unit 291 saves the input image data 58 in the storage 32. The scanner mat 14d is located behind the form 100A and is an example of a background whose luminance is lower than that of the form 100A.
[0030] 4A, the form 100A includes a low-luminance region Ra near the upper edge E_UP of the form 100A within the overall region R100A of the form 100A. Region Ra is an area where, for example, the form title "Request Form A" is printed in white. The luminance of region Ra may be the same as the luminance of the background (i.e., scanner mat 14d), or it may be slightly higher or lower than the luminance of scanner mat 14d.
[0031] Area Ra may exist within area R100A near an edge of form 100A, such as the bottom, left, or right side. In this way, even if area Ra, whose brightness is equivalent to the brightness of scanner mat 14d, exists near the edge of form 100A, information processing device 12 can properly detect area R100A including area Ra with low brightness, using functions such as detection unit 292 and setting unit 293, which will be described later.
[0032] (Detection unit 292) 4B based on the image data 58 stored in the storage 32. For example, the detection unit 292 may detect the first region R1 in which line segments of a boundary portion Re1 with different brightnesses form a specific shape based on the brightness of the image.
[0033] 4A, the specific shape of the form 100A is a rectangle. The detection unit 292 may first search (scan) for points of change in the brightness of pixels included in the image, thereby detecting a plurality of boundary points between pixels of a first brightness and pixels of a second brightness higher than the first brightness, among a plurality of pixels included in the image.
[0034] Next, the detection unit 292 may perform a Hough transform on the detected boundary points to detect the four line segments LR, LL, LU, and LB that form the rectangular first region R1, i.e., the boundary portion Re1. Because the brightness of the region Ra is equivalent to the brightness of the scanner mat 14d, as described above, the detection unit 292 cannot recognize the boundary between the scanner mat 14d and the region Ra at this stage. Therefore, the detection unit 292 can detect the first region R1, which does not include the region Ra that exists near the edge of the form 100A, based on the boundary portion Re1.
[0035] If the form 100A has a triangular shape, the detection unit 292 may detect a boundary portion Re1 between a pixel with a first luminance and a pixel with a second luminance higher than the first luminance as three line segments that form a triangular first region R1. If the form 100A has a pentagonal shape, the detection unit 292 may detect a boundary portion Re1 between a pixel with a first luminance and a pixel with a second luminance higher than the first luminance as five line segments that form a pentagonal first region R1.
[0036] (Settings section 293) To detect the area Ra near the edge of the form 100A, the setting unit 293 first sets a second area R2 by expanding the first area R1, as shown in Fig. 4C. Specifically, the setting unit 293 sets the second area R2 at a certain distance from the top, bottom, left, and right edges of the first area R1, with an edge Re2 whose center is located at the same position as the center of the first area R1. The edge Re2 of the second area R2 may be interpreted as an area that includes the entire first area R1 and has an area larger than the area of the first area R1.
[0037] If a specific number of pixels (e.g., 100 or more) with a brightness equal to or greater than a specific threshold (e.g., brightness of 128) exist within a specific search range from the periphery of the first region R1 of the form 100A to a position 1 cm away from the edge of the form (boundary portion Re1, i.e., the edge of the first region R1) (i.e., if there is a portion where the form title is printed in white), the first region R1 is expanded from the first region R1 to the second region R2, with the upper limit of the search range being 1 cm, up to the portion where there are 100 or more pixels with a brightness equal to or greater than 128. The search range may be set to any value depending on the type of detection target 100, may be set manually by the user, or may be set automatically by the information processing device 12 using a table in which multiple types of detection targets 100 are associated with search ranges for each detection target 100.
[0038] Next, the setting unit 293 may detect a third region R3 as shown in Figures 4D and 4E, and set a fourth region R4 as shown in Figure 4F by adding the detected third region R3 to the first region R1.
[0039] The setting unit 293 may first detect a third region R3 that satisfies a specific condition from a portion P1 (the entire second region R2 excluding the first region R1) from an edge Re2 of the second region R2 to a boundary portion Re1, i.e., an edge of the first region R1.
[0040] More specifically, since a document title such as "Request Form A" is printed in white in area Ra, the setting unit 293 may detect the part of part P1 that contains a predetermined number of pixels whose brightness is equal to or higher than a specific brightness, i.e., area Ra, as the third area R3, as shown in Figure 4D.
[0041] 4E, the third region R3 may include a first portion P_1st that includes a predetermined number of pixels having a brightness equal to or higher than a specific brightness, and a second portion P_2nd that includes a brightness lower than that of the first portion P_1st or does not include any of the pixels. The setting unit 293 may detect, as the third region R3, the first portion P_1st, that is, a portion of the third region R3 that includes a certain number of pixels having a high brightness.
[0042] The first portion P_1st may be interpreted as a region adjacent to the first region R1. The second portion P_2nd may be interpreted as a portion of the third region R3 excluding the first portion P_1st, or as a region not adjacent to the first region R1. The second portion P_2nd may be interpreted as a region on the opposite side of the first portion P_1st from the first region R1 side, across the first portion P_1st, which has higher brightness.
[0043] Then, the setting unit 293 may add the third region R3 shown in Fig. 4D or the first portion P_1st as the third region R3 shown in Fig. 4E to the first region R1, thereby setting a single fourth region R4 obtained by integrating these as shown in Fig. 4F. Specifically, the setting unit 293 may add the first portion P_1st, which includes a predetermined number of pixels having a brightness equal to or higher than a specific brightness, from the portion from the edge Re2 of the second region R2 to the edge (boundary portion Re1) of the first region R1 as the third region R3 to the first region R1, but may not add the second portion P_2nd, excluding the first portion P_1st, from the portion from the edge Re2 of the second region R2 to the edge (boundary portion Re1) of the first region R1 to the first region R1.
[0044] (cutout part 294) As shown in FIG. 4G, the cropping unit 294 may crop the fourth region R4 set by the setting unit 293 as an image of the detection object 100, and store the cropped image data 58 in the storage 32 again.
[0045] At this time, for example, if the coordinate values of the fourth region R4, specifically the coordinate values of a corner of the edge of the fourth region R4, exceed a specific value, the cropping unit 294 may determine that the fourth region R4 is tilted, correct the coordinates of the edge of the fourth region R4 so as to eliminate the tilt, and re-store the image data 58 of the portion corresponding to the corrected form 100A in the storage 32. The image data 58 re-stored in the storage 32 may be used for, for example, OCR or the like.
[0046] Next, the function and operation of the information processing device 12 will be described with reference to FIG.
[0047] In step S1, the information processing device 12 receives the image data 58 transmitted from the non-contact scanner 14. In step S2, the information processing device 12 stores the image data 58 in the storage 32.
[0048] In step S3, the information processing device 12 reads the image data 58 from the storage 32 and detects the first region R1 based on the luminance of the read image.
[0049] In step S4, the information processing device 12 sets a second region R2 having an edge Re2 at a position a certain distance away from the top, bottom, left, and right edges of the first region R1, with the center position being the same as the center position of the first region R1.
[0050] In step S5, the information processing device 12 detects a third region R3 that satisfies a specific condition from the portion from the edge Re2 of the second region R2 to the edge of the first region R1.
[0051] In step S6, the information processing device 12 sets a fourth region R4 by adding the third region R2 to the first region R1.
[0052] In step S7, the information processing device 12 cuts out the set fourth region R4 as an image of the document 100A (detection target 100), corrects the coordinate values of the fourth region R4 as necessary, and re-stores the image data 58 of the cut-out image in the storage 32.
[0053] (Comparative Example) The functions of the information processing device 12 according to the comparative example will be described below with reference to Figures 6A to 6C. As shown in Figure 6A, within the entire area R100A of the document 100A placed on the scanner mat 14d, there is an area Ra with low brightness near the upper edge of the document 100A.
[0054] Thus, when an area Ra whose brightness is equivalent to that of scanner mat 14d exists near the edge of form 100A, information processing device 12 according to the comparative example can detect first area R1 but cannot detect area Ra, as shown in Fig. 6B. In other words, it cannot recognize the difference in brightness between area Ra and scanner mat 14d behind form 100A, and the white-printed portion in area Ra is not recognized as part of form 100A, which may result in it being missing, as shown in Fig. 6C.
[0055] (Variation) As shown in Fig. 7A, form 100A may have two or more regions whose brightness is higher than the brightness of scanner mat 14d. In this case, as shown in Fig. 7B, detection unit 292 may detect a plurality of first regions R1 that are spaced apart from each other in the image of form 100A. Specifically, detection unit 292 may detect two first regions R1 where the line segments at the boundary between the images with different brightnesses form a specific shape (here, a square or a rectangle).
[0056] 7C, the setting unit 293 may set a new first region R1a. That is, the setting unit 293 may combine the portion R5 and the multiple first regions R1, and regard the combined region as the new first region R1a.
[0057] Specifically, when two parallel first regions R1 are detected, the setting unit 293 extends, for example, both edge portions of the lower first region R1 in the X-axis direction (left-right direction of the scanner mat 14d) toward the upper first region R1 in the Y-axis direction (up-down direction of the scanner mat 14d). This allows a new first region R1a to be set in which both sides of the two first regions R1 in the X-axis direction are defined as left and right edges, the upper side of the upper first region R1 is defined as an upper edge, and the lower side of the lower first region R1 is defined as a lower edge. In other words, the setting unit 293 can set a single rectangular region whose area is larger than each of the two first regions R1. Furthermore, even if the upper and lower edges (upper edges) of the two first regions R1 are not parallel to the four sides of the scanner mat 14d, the setting unit 293 may set a new first region R1a using the above method as long as the upper and lower edges of the two first regions R1 are parallel to each other.
[0058] Thereafter, the setting unit 293 sets a new second region R2 by expanding the first region R1a as shown in FIG. 7D, in the same manner as described above with reference to FIG. 4C.
[0059] The second region R2 has an edge Re2 at a position a certain distance from the top, bottom, left, and right edges of the new first region R1a, and the center position is the same as the center position of the new first region R1a. The edge Re2 of the second region R2 may be interpreted as a region that includes the entire new first region R1a and has an area larger than the area of the new first region R1a.
[0060] For example, if there are a specific number of pixels (e.g., 100 or more) with a brightness greater than a specific threshold (e.g., 128) within a specific search range from around the new first region R1a, for example, within a range up to a position 1 cm away from the edge of the document (boundary portion Re1, i.e., the edge of the new first region R1a) (i.e., if there is a portion where the document title is printed in white), the new first region R1a is expanded into the second region R2 up to the part where there are 100 or more pixels with a brightness greater than 128, with the 1 cm as the upper limit of the search range.
[0061] Then, the setting unit 293 may detect the third region R3, or detect the first part P_1st as the third region R3 shown in Figure 4E, as described above in Figures 4E and 4F, and set the fourth region R4 as shown in Figure 7F by adding the detected third region R3 or first part P_1st to a new first region R1a.
[0062] As described above, the information processing device 12 according to an embodiment of the present disclosure detects a first region where the line segments at the boundary between the detection target image and the background image form a specific shape, and then adds a third region that satisfies specific conditions from the edge of a second region that includes the entire first region and has a larger area than the first region to the edge of the first region to set a fourth region. This configuration makes it possible to extract the fourth region that includes a form title or the like near the edge of the first region. This makes it possible to prevent the form title or the like from being lost.
[0063] Furthermore, the present invention is not limited to the above, and it goes without saying that various modifications can be made without departing from the spirit of the present invention.
[0064] (Addendum) The following additional notes are provided regarding aspects of the present disclosure.
[0065] (Appendix 1) a detection unit that detects a first region in which line segments at a boundary between the detection target and the background form a specific shape based on the luminance of an image obtained by capturing an image of a region including an image of the detection target and a background that is behind the image of the detection target and has a lower luminance than the luminance of pixels included in the image of the detection target; a setting unit that sets a fourth region by adding a third region that satisfies a specific condition to the first region, the third region being a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to the edge of the first region; a cutout unit that cuts out the set fourth region as an image of the detection target; An information processing device comprising:
[0066] (Appendix 2) The information processing device described in Appendix 1, wherein the setting unit adds to the first area as the third area a portion of the portion from the edge of the second area to the edge of the first area that contains a predetermined number of pixels having a brightness equal to or higher than a specific brightness.
[0067] (Appendix 3) The information processing device described in Appendix 2, wherein the setting unit adds a first portion of the portion from the edge of the second region to the edge of the first region, the first portion including a predetermined number of pixels having a brightness equal to or higher than the specific brightness, to the first region as the third region, but does not add a second portion of the portion from the edge of the second region to the edge of the first region excluding the first portion to the first region.
[0068] (Appendix 4) 2. The information processing device according to claim 1, wherein the detection unit detects the line segments in the first region by searching for points of change in luminance of pixels included in the image.
[0069] (Appendix 5) The information processing device described in Appendix 4, wherein the detection unit detects, among the pixels included in the image, a boundary between a pixel of a first brightness and a pixel of a second brightness higher than the first brightness as the line segment of the first region.
[0070] (Appendix 6) When the detection unit detects a plurality of the first regions that are arranged apart from each other in the image, The information processing device described in Appendix 1, wherein the setting unit integrates a portion that is located between a plurality of the first regions that are arranged at a distance and that contains a predetermined number of pixels whose brightness is below a specific brightness with the plurality of first regions, regards the entire integrated region as a new first region, and sets the fourth region by adding the third region to the new first region.
[0071] (Appendix 7) detecting a first region in which a line segment at a boundary between the detection target and the background forms a specific shape based on the brightness of an image obtained by capturing an image of the detection target and a background that is behind the image of the detection target and has a lower brightness than the brightness of pixels included in the image of the detection target; a third region that satisfies a specific condition and is included in a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to an edge of the first region, and is added to the first region to set a fourth region; The set fourth region is cut out as an image of the detection target. An information processing method in which processing is performed by a computer.
[0072] (Appendix 8) detecting a first region in which a line segment at a boundary between the detection target and the background forms a specific shape based on the brightness of an image obtained by capturing an image of the detection target and a background that is behind the image of the detection target and has a lower brightness than the brightness of pixels included in the image of the detection target; a third region that satisfies a specific condition and is included in a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to an edge of the first region, and is added to the first region to set a fourth region; The set fourth region is cut out as an image of the detection target. An information processing program that causes a computer to execute a process. [Explanation of symbols]
[0073] 10 Information Processing Systems 12 Information processing equipment 14 Contactless Scanner 14a Head 14b units 14c post 14d scanner mat 22 Computer 24 databases 28 processors 32 Storage 34 Bus 36 Computer 38 Reception device 40 Camera 46 processors 50 Storage 52 Bus 54 Network 56 Specific Processing Program 58 Image Data 100 detection targets 100A Form 290 Special Processing Department 291 Input section 292 Detection unit 293 Settings 294 Cutout part
Claims
1. a detection unit that detects a first region in which line segments at a boundary portion with different luminances in an image obtained by capturing an image of an area including an image of a detection target and a background that is behind the image of the detection target and has a lower luminance than the luminance of pixels included in the image of the detection target form a specific shape; a setting unit that sets a fourth region by adding a third region that satisfies a specific condition to the first region, the third region being a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to the edge of the first region; and a cutout unit that cuts out the set fourth region as an image of the detection target; An information processing device comprising:
2. 2. The information processing device according to claim 1, wherein the setting unit adds a portion of the portion from the edge of the second region to the edge of the first region that contains a predetermined number of pixels having a brightness equal to or higher than a specific brightness to the first region as the third region.
3. 3. The information processing device of claim 2, wherein the setting unit adds a first portion of the portion from the edge of the second region to the edge of the first region, the first portion containing a predetermined number of pixels whose brightness is equal to or higher than the specific brightness, to the first region as the third region, but does not add a second portion of the portion from the edge of the second region to the edge of the first region excluding the first portion to the first region.
4. The information processing device according to claim 1 , wherein the detection unit detects the line segments in the first region by searching for points of change in luminance of pixels included in the image.
5. The information processing device according to claim 4 , wherein the detection unit detects, among pixels included in the image, a boundary between a pixel having a first luminance and a pixel having a second luminance higher than the first luminance, as the line segment of the first region.
6. When the detection unit detects a plurality of the first regions that are arranged apart from each other in the image, 2. The information processing device according to claim 1, wherein the setting unit integrates a portion that is located between a plurality of the first regions and that contains a predetermined number of pixels whose brightness is below a specific brightness with the plurality of the first regions, regards the entire integrated region as a new first region, and sets the fourth region by adding the third region to the new first region.
7. detecting a first region where line segments at a boundary portion with different luminances form a specific shape in an image obtained by capturing an image of an area including an image of a detection target and a background that is behind the image of the detection target and has a lower luminance than the luminance of pixels included in the image of the detection target; a fourth region is set by adding a third region that satisfies a specific condition to the first region, the third region being a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to an edge of the first region; cutting out the set fourth region as an image of the detection target; An information processing method in which processing is performed by a computer.
8. detecting a first region where line segments at a boundary portion with different luminances form a specific shape in an image obtained by capturing an image of an area including an image of a detection target and a background that is behind the image of the detection target and has a lower luminance than the luminance of pixels included in the image of the detection target; a fourth region is set by adding a third region that satisfies a specific condition to the first region, the third region being a portion from an edge of a second region that includes the entire first region and has an area larger than that of the first region to an edge of the first region; cutting out the set fourth region as an image of the detection target; An information processing program that causes a computer to execute a process.
Citation Information
Patent Citations
Image inclination correction device and image inclination correcting method
JP2008147976A