Image processing device, image processing method, and image processing system

Abstract

To provide an image processing device, an image processing method, and an image processing system that can efficiently acquire an appropriate image of an identification card in a short time even with simple photography without degrading quality of photography, by focusing on a feature of a surface on which information proving identity is written in an identification card such as a license of a driver or a My Number card.SOLUTION: In a mobile terminal 1, an aspect ratio determination unit 104 determines that an aspect ratio of a band of a photographed object corresponds to a predetermined aspect ratio. If a size determination unit 105 determines that a size of a detected object corresponds to a predetermined size, and if a layout determination unit 106 determines that an image layout of the detected object corresponds to a predetermined image layout, image data of the object is stored in a photographed image storage unit 108, and the image data is transmitted to a server 2 via a network 30 by an image transmission unit 109 and a communication unit 100.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to, for example, an image processing device, an image processing method, and an image processing system. [Background technology]

[0002] Nowadays, financial institutions are adopting a method for completing loan screening procedures online without the need for customers to visit a branch. In this case, to verify the identity of the loan applicant, they have a system in place where they can take a photo of their driver's license, My Number card, or other identification documents with their smartphone and submit the document.

[0003] Customers download a dedicated smartphone app, follow the instructions provided by the app, and place their ID card within the frame displayed on the screen of the activated camera. In this case, the photo must be taken properly to accurately capture the information on the driver's license or My Number card.

[0004] As an example, there is a proposal for a technology to identify a fixed area containing a fixed character string on an identification document (Patent Document 1). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7316479 Summary of the Invention [Problem to be solved by the invention]

[0006] When taking a photo using a personal smartphone, various checks are made to improve the quality of the photo. If the range of what is considered a correct check is too limited, the chances of the photo being successful decrease. This can cause the photo to take too long, leading users to abandon the process. Conversely, if the number of checks is reduced to make it easier to take a photo, the quality of the captured image will decrease, making it unusable as identification. In other words, the image may not pass the final visual inspection required to open an account.

[0007] Here, we will list some examples of failed images. (1) When a corner of the certificate is photographed outside the photographic area (2) When the photo is taken too close to the certificate, causing the four corners of the certificate to protrude. (3) The photo is taken from too far away from the certificate, resulting in the certificate being too small (the resolution is not sufficient for identification purposes). (4) When the smartphone is held at different heights (i.e., the ID card is photographed in a trapezoidal shape). Since the online loan screening process involves using a personally owned smartphone, the performance of each device varies. Therefore, the process of determining whether or not the ID document has been successfully photographed must be able to operate on a compatible smartphone with the minimum performance.

[0008] In cases such as those described in Patent Document 1, a process is required to determine the standard character string using a score, which not only increases the processing load on the smartphone, but also can take a long time to successfully capture the image.

[0009] The present invention has been made in view of the above background, and aims to provide an image processing device, an image processing method, and an image processing system that can efficiently obtain an appropriate image of an identification document in a short time, even with simple photography that does not degrade the quality of the image, by focusing on the characteristics of the surface of the identification document, such as a driver's license or My Number card, which contains information that proves the identity of the person. [Means for solving the problem]

[0010] In order to solve the above-mentioned problems and achieve the above-mentioned object, one embodiment of the present invention is an image processing device that is connected to a server via a network and transmits image data obtained by photographing an object to the server, and is characterized by comprising: an imaging unit that photographs the object and inputs image data; an aspect ratio determination unit that determines a detected object with an aspect ratio of the photographed object based on the image data input by the imaging unit and determines whether the aspect ratio of the detected object corresponds to a predetermined aspect ratio; a size determination unit that determines the size of the detected object based on the image data input by the imaging unit when the aspect ratio determination unit determines that the detected object corresponds to the predetermined aspect ratio and determines whether the size corresponds to the predetermined size; an arrangement determination unit that determines whether the image arrangement of the detected object corresponds to a predetermined image arrangement based on the image data input by the imaging unit when the size determination unit determines that the detected object corresponds to the predetermined size; a photographed image storage unit that stores image data of the photographed object when the arrangement determination unit determines that the detected object corresponds to the predetermined image arrangement; and a communication unit that transmits the image data stored in the photographed image storage unit to the server.

[0011] Another embodiment of the present invention is an image processing method connected to a server via a network, which photographs an object and transmits image data obtained by photographing the object to the server, and which includes: a photographing step of photographing the object and inputting image data; an aspect ratio determination step of determining a detected object having an aspect ratio of the photographed object based on the image data input in the photographing step and determining whether the aspect ratio of the detected object corresponds to a predetermined aspect ratio; a size determination step of determining the size of the detected object based on the image data input in the photographing step if the aspect ratio determination step determines that the detected object corresponds to the predetermined aspect ratio and determines whether the size corresponds to the predetermined size; an arrangement determination step of determining whether the image arrangement of the detected object corresponds to a predetermined image arrangement based on the image data input in the photographing step if the size determination step determines that the detected object corresponds to the predetermined size; and a communication step of transmitting image data of the photographed object to the server if the arrangement determination step determines that the detected object corresponds to the predetermined image arrangement.

[0012] Another embodiment of the present invention is an image processing system that performs loan screening between a server and a terminal via a network, in which the terminal photographs an object and inputs image data, and based on the input image data, determines whether the aspect ratio, size, and image layout of the photographed object are appropriate based on pre-set criteria, and if the determination results in an appropriateness, transmits the image data of the photographed object to the server, and the server performs loan screening based on the transmitted image data. [Effects of the Invention]

[0013] According to the present invention, by focusing on the surface features of identification documents such as driver's licenses and My Number cards that contain information that proves one's identity, it is possible to efficiently obtain appropriate images of the identification documents in a short amount of time even with simple photography that does not degrade the quality of the photography. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a block diagram showing functions of an image processing apparatus according to an embodiment of the present invention; [Figure 2] FIG. 10 is an explanatory diagram illustrating rules for identity verification according to an embodiment of the present invention. [Figure 3] 1A and 1B are explanatory diagrams illustrating examples of photographing an identification card and determining whether or not the identification card is photographed according to an embodiment of the present invention. [Figure 4] 1 is a configuration diagram showing a hardware configuration of an image processing system according to an embodiment of the present invention; [Figure 5] 10 is a flowchart illustrating the operation of a mobile terminal according to an embodiment of the present invention. [Figure 6] 4 is a flowchart illustrating the operation of the image processing system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the following description and drawings are merely examples for explaining the present invention, and some omissions and simplifications have been made as appropriate for clarity of explanation. The present invention can also be implemented in various other forms. Furthermore, unless otherwise specified, each component may be singular or plural.

[0016] Preferred embodiments of the present invention will be described below with reference to the drawings. Note that the following are merely examples of the present invention, and the content of the present invention is not limited to the specific embodiments described below. The present invention can of course be modified into various embodiments, including the embodiments described below.

[0017] First, the functions will be explained using Figures 1, 2, and 3. Figure 1 is a block diagram showing the functions of the image processing device according to this embodiment, Figure 2 is an explanatory diagram explaining the rules for personal identification according to this embodiment, and Figure 3 is an explanatory diagram explaining photographic examples of identification cards and their judgments according to this embodiment.

[0018] In this embodiment, the image processing device is exemplified by a mobile terminal 1 with a camera function, such as a smartphone, as shown in Fig. 1. The mobile terminal 1 is connected to a loan screening server 2 via a network 30, such as a wireless communication network or the Internet.

[0019] In this embodiment, a mobile terminal 1 owned by a user is connected via a network 30 to a server 2 managed by or business-affiliated with a financial institution such as a bank, and a loan examination procedure is carried out. In this loan examination, a photograph of an identification document such as a driver's license or My Number card used by the user to prove his / her identity is taken on the mobile terminal 1 side, and the photograph is sent to the server 2.

[0020] As shown in FIG. 1, the mobile terminal 1 includes a communication unit 100, a shooting condition storage unit 101, an operation and display unit 102, a shooting and display control unit 103, an aspect ratio determination unit 104, a size determination unit 105, an arrangement determination unit 106, a face detection unit 107, a captured image storage unit 108, an image transmission unit 109, and the like.

[0021] The communication unit 100 communicates data and the like with communication devices such as a server 2 connected to the network 30. The photographing condition storage unit 101 stores a judgment criteria table (hereinafter referred to as judgment criteria TBL) 101a in which different judgment criteria are set depending on the type of identification such as a driver's license, a My Number card, and the like.

[0022] This judgment standard TBL101a is a set of pre-set and stored conditions for obtaining appropriate photographic results, such as the placement of various information for verifying identity, information such as the size and aspect ratio of the main areas of the band, the size of each area, the allowable range of the aspect ratio of the band, etc.

[0023] Here, the criteria for determining whether an identification document is appropriate according to the determination criteria TBL101a will be described in detail with reference to Fig. 2. Fig. 2 shows examples of identification documents, such as a driver's license and a My Number card.

[0024] As shown in Figure 2, the driver's license has a height (size) of dx and a width (size) of dy. The size of the band DBL placed on the front of the driver's license is a height (size) of dblx and a width (size) of dbly. The placement (position) of this band DBL is also stored.

[0025] The driver's license band DBL has the expiration date printed on it, and green, blue, or gold bands are arranged in the background. Incidentally, green indicates a "new license holder," blue indicates a "first-time renewal," "ordinary driver," or "violator," and gold indicates a "good driver." Although not shown, size and layout (position) information is stored for the facial image DFC, which is a facial photograph.

[0026] As shown in Figure 2, the My Number Card has a height (size) of mx and a width (size) of my. The size of the band MBL placed on the front of the driver's license is a height (size) of mblx and a width (size) of mbly. The band of the My Number Card contains additional information such as address changes, and a blue band is used as the background.

[0027] The arrangement (position) of the band MBL is also stored. Although not shown, information on the size and arrangement (position) of the face image MFC is stored.

[0028] The operation and display unit 102 inputs operations related to the loan examination procedure between the server 2 and outputs the inputs to the communication unit 100 , and also displays the screen based on the data received from the server 2 .

[0029] Furthermore, the operation and display unit 102 inputs an operation to photograph an object and displays the photographed image of the object. Since the user photographs an identification card during a loan examination, the identification card corresponds to the object. The photographing and display control unit 103 photographs the object in response to instructions from the operation and display unit 102 and controls the display of the operation and display unit 102.

[0030] The aspect ratio determination unit 104 detects a characteristic part, i.e., a band, from the object based on the image data input by the shooting and display control unit 103 during shooting, determines the aspect ratio of the detected object, and if it is within a predetermined tolerance range, it is deemed appropriate at this stage of determination and proceeds to the next determination.

[0031] Here, the characteristic parts are the rectangular bands DBL and MBL placed on the driver's license and My Number card in the example of Figure 2. The ratio of the length to the width of the bands differs between the driver's license and the My Number card.

[0032] Therefore, different criteria are applied depending on whether the user selects an image of the driver's license or the My Number card to be used to proceed with the loan examination on the operation and display unit 102. These criteria are stored in the photographing condition storage unit 101.

[0033] In the case of a driver's license, the aspect ratio is determined based on the image data of the band DBL, with the allowable size range being 28-35% of the height dblx and the width dbly. On the other hand, in the case of an Individual Number Card, the aspect ratio is determined based on the image data of the band MBL, with the allowable size range being 7-14% of the height mblx and the width mbly. Note that the above allowable ranges are merely examples and can be modified.

[0034] In determining this aspect ratio, as shown in Figure 3(a), if a driver's license is selected as the subject to be photographed for identification and the photograph is taken with the My Number Card MID, the aspect ratio of the band MBL in image processing based on the image data IMG will be determined to be inappropriate because it will be different from that of the driver's license.Of course, if a driver's license is selected as the subject to be photographed for identification, the same determination will be made that the photograph is inappropriate.

[0035] The size determination unit 105 determines, based on the image data, whether the size of the band determined to be appropriate by the aspect ratio determination unit 104 falls within a predetermined allowable range. In this case, as shown in Fig. 2, it is determined whether the height and width of the band fall within a preset upper and lower limit allowable range.

[0036] In the case of a driver's license, the size is determined based on the image data of the band DBL, with dblx1 to dblx2 (%) set as the allowable range for the height dblx and dbly1 to dbly2 (%) set as the allowable range for the width dbly. On the other hand, in the case of an Individual Number Card, the aspect ratio is determined based on the image data of the band MBL, with mblx1 to mblx2 (%) set as the allowable range for the height and mbly1 to mbly2 (%) set as the allowable range for the width mbly.

[0037] In determining this size, as shown in Figure 3(b), when selecting a driver's license as the subject to photograph for identification purposes, if the photograph is taken from too far away from the identification card DID, the image will be small and unclear, resulting in a smaller amount of data for the identification card DID relative to the image data IMG.

[0038] As a result, the amount of data required for image processing may be insufficient, and there is a risk that the character or facial image on the driver's license information may not be recognized or may be misrecognized. In this case, the result of the judgment is deemed inappropriate. The judgment criteria TBL101a defines this tolerance range, i.e., the judgment criteria. The same applies when selecting a My Number card as the subject to be photographed.

[0039] In Figure 3(b), an example is given in which the image of the ID card DID is small, but the opposite can also happen if the image is too large and other necessary information is missing, so in this case too, the result will be determined to be inappropriate.

[0040] The placement determination unit 106 determines, based on the image data, whether the center position of the band determined to be appropriate by the size determination unit 105 falls within a predetermined allowable range and whether the inclination falls within a predetermined allowable range.

[0041] In the case of a driver's license, the center position of the band is determined based on the image data of the band DBL, and dblc1 to dblc2 (%) are set as the allowable range for the center position defined on the band. On the other hand, in the case of an Individual Number Card, the center position of the band is determined based on the image data of the band MBL, and mblc1 to mblc2 (%) are set as the allowable range for the center position defined on the band.

[0042] In determining this center position, as shown in Figure 3(c), when a driver's license is selected as the subject of a photograph to prove identity, the position of the band DBL may be too high, for example, resulting in a partial loss of the facial image DFC, resulting in a determination result that the center position of the band DBL is inappropriate. Of course, the same applies when a My Number card is selected as the subject of a photograph. In the case of a driver's license, the image data of the band DBL is used to determine the tilt of the band, and the allowable range is set to ±dt° (rotation degrees left and right) from the horizontal for proper determination. On the other hand, in the case of an Individual Number Card, the image data of the band MBL is used to determine the tilt of the band, and the allowable range is set to ±mt° (rotation degrees left and right) from the horizontal for proper determination.

[0043] In determining this inclination, as shown in Figure 3(d), when a driver's license is selected as the subject of a photograph to prove identity, the position of the band DBL may exceed the allowable range, resulting in, for example, a portion of the face image DFC being missing, and the inclination of the band DBL may be determined to be inappropriate. Of course, the same applies when a My Number card is selected as the subject of a photograph. If the layout determining unit 106 determines that the layout is appropriate, the face detecting unit 107 further determines whether a face image has been detected based on the image data.

[0044] In the case of a driver's license, as shown in Figures 2 and 3(e), the target for facial image detection is the image data IMG input by photographing, and the allowable range for deviation from the position specified as the placement of the facial image is set to df1 to df2%. Taking Figure 3(e) as an example, if there is dirt on the surface or missing parts of the facial image when photographing, the facial image cannot be detected and the result is determined to be inappropriate. Of course, the same applies when selecting a My Number card as the target for photographing.

[0045] If the face image is determined to be appropriate by the face detection unit 107, the face detection unit 107 further determines whether the positional relationship between the band and the face image is appropriate based on the image data.

[0046] In the case of a driver's license, the facial image position is determined based on the image data input during photography, and the key point for determination is the positional relationship between the center position of the band DBL and the facial image DFC, with respect to the positional relationship of the band of the facial image that is set in advance.

[0047] That is, dp1 to dp2% of the distance between the center position of the band DBL and the face image DFC is set as the allowable range. If the distance is determined to be outside this allowable range, the result is determined to be inappropriate. Of course, the same applies when the My Number card is selected as the subject to be photographed.

[0048] 3(f), the captured image storage unit 108 stores the image data in that state and outputs the image data to the downstream image transmission unit 109. The image transmission unit 109 outputs the input image data to the communication unit 100, completing the submission of the identification card to the server 2.

[0049] Next, the system configuration will be described. Fig. 4 is a diagram showing one hardware configuration of the image processing system according to this embodiment.

[0050] 4, the mobile terminal 1 is configured with a CPU 11, memory 12, application 13, camera 14, operation panel 15, communication unit 16, etc. The CPU 11 controls the entire mobile terminal 1 using a program stored in the memory 12, and also executes processing related to loan screening using the application 13 stored in the memory 12. The application 13 is installed by downloading a distribution application 24 from the server 2.

[0051] The memory 12 stores an application 13 that executes various processes in addition to a program that controls the entire mobile terminal 1, and also stores data etc. when various processes are executed. The application 13 is a program for executing the loan screening-related processes shown in Figures 5 and 6, and stores the aforementioned judgment criteria TBL 101a.

[0052] Camera 14 performs a photographing process and inputs image data (moving images or still images) in response to operations on operation panel 15. Operation panel 15 is, for example, a touch-type device for display output and operation input. Communication unit 16 is a device connected to network 30 and communicates with external devices such as server 2.

[0053] As shown in FIG. 2, the server 2 is configured with a CPU 21, a memory 22, an examination application 23, a distribution application 24, an operation unit 25, a communication unit 26, and the like.

[0054] The CPU 21 controls the entire server 2 using a program stored in the memory 22 , and also executes processing related to loan examination using a loan examination application 23 stored in the memory 22 .

[0055] The memory 22 stores a program for controlling the entire server 2, a loan examination application 23, a distribution application 24, etc., and also stores data etc. when various processes are executed.

[0056] The loan screening application 23 is a program for executing the processing related to the loan screening in Figure 5, and the distribution application 24 is a program that is distributed to the mobile terminal 1 via the network 30 and causes the mobile terminal 1 to execute the processing related to the loan screening in Figures 5 and 6.

[0057] The operation unit 25 is a device for displaying screens and performing input operations in loan examinations, etc. The communication unit 26 is a device connected to the network 30 and for communicating with external devices such as the mobile terminal 1.

[0058] Next, the operation will be described with reference to Figures 5 and 6. Figure 5 is a flowchart explaining the operation of the mobile terminal according to this embodiment, and Figure 6 is a flowchart explaining the operation of the image processing system according to this embodiment. Note that the processing described below is performed by CPU 11 in mobile terminal 1 using a program stored in memory 12, and by CPU 21 in server 2 using a program stored in memory 22.

[0059] First, the overall flow of the system will be explained using Figure 5. It is assumed that application 13 has been installed in advance on mobile terminal 1 from server 2. On mobile terminal 1, a user applying for a loan examination operates operation panel 15 to request a loan examination via network 30 (step S501). Here, although not shown, a menu screen is provided by server 2, and the user operates according to the menu screen.

[0060] When the server 2 receives a loan examination request from the mobile terminal 1 (step S511), the loan examination begins (step S512). There are two ways to carry out this loan examination: one is to start the loan examination application 23 from step S512, and the other is to start the loan examination application 23 from the moment the loan examination request is received from the mobile terminal 1 via the application 13. Since this is a design matter, either method is acceptable.

[0061] When the loan examination begins, the server 2 requests the mobile terminal 1 to carry out the loan application procedure via the screen. The user inputs various information according to the request via the mobile terminal 1 and submits necessary documents such as an identification card. The server 2 accepts the input information and necessary documents from the mobile terminal 1 (step S513). The process of submitting the identification card required for user identification will be described in detail with reference to FIG. 6.

[0062] Once the information required for the loan application is gathered in this way, the server 2 executes a loan examination (step S514). The result of this loan examination is reported from the server 2 to the mobile terminal 1 (step S515), and the mobile terminal 1 receives the report (step S503). Although not shown, the mobile terminal 1 continues to execute processes such as officially applying for a loan if the loan is available.

[0063] The process related to the submission of identification, which is one of the processes included in step S502 of the mobile terminal 1, will be described below with reference to Fig. 6. First, although not shown, the type of identification to be submitted is selected by the user through a menu screen provided by the server 2 (step S601).

[0064] In this embodiment, as an example, a selection is made between two types: a driver's license and a My Number card. When a driver's license is selected, the criteria corresponding to the driver's license in the determination criteria TBL101a are applied (see FIG. 2), whereas when a My Number card is selected, the criteria corresponding to the My Number card in the determination criteria TBL101a are applied (see FIG. 2).

[0065] When the type of identification is selected in step S601, the camera 14 is activated and begins capturing images (step S602). This inputs video, i.e., image data, which is used in the following determination process. Details of each determination process have already been explained, so the following mainly explains the flow of the process. Also, an example will be given in which a driver's license is selected as the identification.

[0066] When photography begins, image processing is performed to acquire the detected object (step S603). Here, an area corresponding to the belt of a driver's license is detected as a characteristic part from the image data within the photography area. Specifically, since the detected object is a belt, it is desirable that it be a rectangular area with a certain height and width.

[0067] When a detected object is acquired in step S603, the height (vertical width) and width of the band that is the detected object (image data) are measured, and the aspect ratio is determined. As a result, if the aspect ratio is within the allowable range of the judgment criterion TBL101a, the aspect ratio is determined to be appropriate, and the process proceeds to step S605 (YES route in step S604).

[0068] If it is determined that the aspect ratio is not appropriate, the process returns to step S603, and a message to try again (not shown) is displayed on the operation panel 15. This allows the user to adjust the position of the identification card and the distance from the camera 14.

[0069] In this way, if the aspect ratio is appropriate, in steps S605 and S606, it is determined whether the height and width of the detected band are within the allowable ranges that specify the upper and lower limits. This determination process refers to the determination standard TBL101a.

[0070] If the height and width of the detected object are determined to be within the lower limit of the allowable range in step S605, the process proceeds to step S606. On the other hand, if the height and width are determined to be below the lower limit of the allowable range, the process returns to step S603 and starts over from acquiring the detected object.

[0071] Furthermore, if it is determined in step S606 that the height and width of the detected object are within the upper limit allowable range, the process proceeds to step S607, but if it is determined that they are above the upper limit allowable range, the process returns to step S603 and starts over from acquiring the detected object. Note that the determinations in steps S605 and S606 can be performed in any order, as either step can be performed first.

[0072] Next, in step S607, it is determined whether the center position of the band, which is the detected object, falls within the tolerance range, with reference to the determination criterion TBL101a. If it is determined in step S607 that the center position of the band is within the tolerance range, the process proceeds to step S608. On the other hand, if it is determined that the center position of the band is outside the tolerance range, the process returns to step S603 and starts over from obtaining the detected object.

[0073] In step S608, the judgment criterion TBL101a is referenced to determine whether the tilt of the band, which is the detected object, falls within the tolerance range. If it is determined in step S608 that the tilt of the band is within the tolerance range, the process proceeds to step S609. On the other hand, if it is determined that the tilt of the band is outside the tolerance range, the process returns to step S603 and starts over from acquiring the detected object. Note that the judgments in steps S607 and S608 can be performed in any order, as either step can be performed first.

[0074] Then, when the process proceeds to step S609, face detection is performed based on the image data. This face detection is a general face recognition process. Here, if it is determined that the position where the face is detected is within the allowable range by referring to the determination criterion TBL101a (YES route in step S610), the process proceeds to step S611. On the other hand, if it is determined that the position is not within the allowable range (NO route in step S610), the process returns to step S603 and starts over from acquiring the detected object.

[0075] Furthermore, if it is determined that the positional relationship between the position where the face was detected and the band that is the detected object is within the allowable range (YES route in step S611), the image data input by shooting is stored as a still image and transmitted to the server 2 (step S612).On the other hand, if it is determined that it is not within the allowable range (NO route in step S610), the process returns to step S603 and starts again from acquiring the detected object.

[0076] As described above, according to this embodiment, by focusing on the surface features of identification documents such as driver's licenses and My Number cards that contain information that proves one's identity, it is possible to efficiently obtain an appropriate image of the identification document in a short amount of time even with simple photography that does not degrade the quality of the image.

[0077] Specifically, for each judgment of a detected object, if the judgment result is OK, the next judgment is carried out in order. For each judgment, the conditions that result in NG are roughly judged, and if the result is NG, the subsequent judgment is stopped and restarted from the beginning.

[0078] The effect of combining multiple determinations is that the processing time for each determination is short, and if an NG occurs midway, the face detection process, which involves a heavier processing load, is not carried out, thereby minimizing processing capacity.

[0079] In particular, it can handle multiple NG patterns (tilt / size / distortion) when photographing an ID card. Even in the case of multiple NG patterns, each judgment will only result in a NG judgment.

[0080] Furthermore, since the size determining unit determines the length and width of the band based on a predetermined allowable range, it is possible to prevent determination with poor accuracy.

[0081] Furthermore, since the center and tilt of the detected object are determined by the placement determination unit, it is possible to prevent determination with a low accuracy.

[0082] Furthermore, the face detection unit performs face detection based on the image data of the target object only when the layout determination unit determines that the image layout corresponds to a predetermined one, so it is possible to proceed to face detection, which requires a high processing load, only when the proper form corresponding to the type of identification is confirmed. This makes it possible to efficiently verify the identification.

[0083] Furthermore, the aspect ratio determination unit, size determination unit, and placement determination unit are configured to make a determination based on whether the identification is a driver's license or a My Number card, so there is no need to set unnecessary tolerances in the determination, and it is possible to properly verify the identity of the person based on the type of identification.

[0084] In the above-described embodiment, an example was given of a financial institution conducting loan screening online, but the present invention is not limited to this and can also be applied to account registration for online shopping sites, online services with age restrictions, etc.

[0085] It should be noted that the present invention is not limited to the above-described embodiment, and includes various modifications. Furthermore, the above-described embodiment has been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to an embodiment having all of the described configurations.

[0086] Furthermore, some of the configurations of the above-described embodiments can be added to, deleted from, or replaced with other configurations. Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. Furthermore, the above-described configurations, functions, etc. may be realized in software, by a processor interpreting and executing a program that realizes each function.

[0087] Information such as programs, tables, and files that realize each function may be stored in a memory, a recording device such as a hard disk or SSD, or a recording medium such as an IC card, SD card, or DVD. [Explanation of symbols]

[0088] 1. Mobile devices 2 Server 11 CPU 12 Memory 13 Applications 14 Camera 15 Touch Panel 16 Communication Unit 21 CPU 22 External Memory 23 Loan Appraisal Application 24 Distributed Applications 25 Operation Unit 26 Communication Unit 100 Communications Department 101 Shooting condition memory unit 101a Judgment Criteria TBL 102 Operation and display unit 103 Shooting and display control unit 104 Aspect ratio determination unit 105 Size determination unit 106 Placement judgment section 107 Face detection unit 108 Photographed image storage unit

Claims

1. An image processing device that is connected to a server via a network and transmits image data obtained by photographing an object to the server, an imaging unit that captures an image of an object and inputs image data; an aspect ratio determination unit that determines a detected object having an aspect ratio of the photographed object based on the image data input by the photographing unit, and determines whether the aspect ratio of the detected object corresponds to a predetermined aspect ratio; a size determination unit that determines the size of the detected object based on the image data input by the image capture unit when the aspect ratio determination unit determines that the aspect ratio corresponds to the predetermined size, and determines whether the size corresponds to the predetermined size; an arrangement determination unit that determines whether the image arrangement of the detected object corresponds to a predetermined image arrangement based on the image data input by the photographing unit when the size determination unit determines that the detected object corresponds to the predetermined size; a captured image storage unit that stores image data of the object to be photographed when the layout determination unit determines that the image layout corresponds to the predetermined image layout; a communication unit that transmits the image data stored in the captured image storage unit to the server; An image processing device comprising:

2. 2. The image processing apparatus according to claim 1, wherein the size determining unit determines the vertical and horizontal sizes of the detected object based on a predetermined allowable range.

3. 2. The image processing device according to claim 1, further comprising a face detection unit that performs face detection based on image data of the object being photographed when the layout determination unit obtains a determination result that the image layout corresponds to the specified image layout, and the photographed image storage unit stores the image data of the object when the face detection unit is able to detect a face.

4. 2. The image processing apparatus according to claim 1, wherein the object stored in said photographed image storage section is a driver's license.

5. 2. The image processing device according to claim 1, wherein the object stored in the captured image storage unit is a My Number card.

6. 2. The image processing device according to claim 1, wherein the photographing unit sets whether the object to be photographed is a driver's license or a My Number card before photographing, and the aspect ratio determination unit, the size determination unit, and the placement determination unit make a determination according to the set object.

7. An image processing method in which a device is connected to a server via a network and image data obtained by photographing an object is transmitted to the server, a photographing step of photographing an object and inputting image data; an aspect ratio determination step of determining a detected object having an aspect ratio of the photographed object based on the image data input in the photographing step, and determining whether the aspect ratio of the detected object corresponds to a predetermined aspect ratio; a size determination step of determining a size of the detected object based on the image data input in the photographing step when the aspect ratio determination step determines that the aspect ratio corresponds to the predetermined size, and determining whether the size corresponds to the predetermined size; an arrangement determination step of determining whether the image arrangement of the detected object corresponds to a predetermined image arrangement based on the image data input in the photographing step when the determination result in the size determination step indicates that the detected object corresponds to the predetermined size; a communication step of transmitting image data of the photographed object to the server when a determination result that the photographed object corresponds to the predetermined image layout is obtained in the layout determination step; An image processing method comprising:

8. The image processing method of claim 7, further comprising a face detection step for performing face detection based on image data of the object photographed when the determination step obtains a determination result that the image corresponds to the specified image layout, and the communication step is characterized in that the image data of the object is transmitted when face detection is successful in the face detection step.

9. An image processing system that executes loan examination between a server and a terminal via a network, The terminal photographs an object and inputs image data, and determines whether the aspect ratio, size, and image layout of the photographed object are appropriate based on the input image data and on preset criteria, and if the determination result is that the aspect ratio, size, and image layout of the photographed object are appropriate, transmits the image data of the photographed object to the server; The image processing system is characterized in that the server performs a loan examination based on the transmitted image data.

10. An image processing system as described in claim 9, further characterized in that the terminal determines whether the input image data is appropriate, including face detection based on the predetermined judgment criteria.

Images