JP2017033477A - Image determination system, image determination method, image determination program, and record medium for recording image determination program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image determination system which adopts an image having a high possibility of being used.SOLUTION: An image determination system includes: an acquisition unit which acquires an image; a determination unit which determines whether the image satisfies an adoption condition; and a storage unit. The adoption condition is that a predetermined character or image is recognized in the image, and the storage unit stores the image determined to satisfy the adoption condition by the determination unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image determination system, an image determination method, an image determination program, and a recording medium for recording an image determination program.

  In recent years, it has become easy to capture an image with a digital camera or a portable terminal, and the use of the captured image has been diverse. For example, instead of copying an ID card, sending an image of the ID card or extracting characters by performing OCR (Optical Character Recognition) processing on the image, In some cases, information stored in images is used effectively.

  An apparatus related to a technique that uses information of an image is described in Patent Document 1. The apparatus described in Patent Document 1 is an apparatus that images a vehicle traveling on a road and detects a vehicle number from the captured image. The device of Patent Document 1 measures the distance between a vehicle crossing the road and the device by outputting a pulse beam on the road, and performs imaging at a timing when the distance falls within a predetermined set distance. And a vehicle number is read from the imaged image.

JP-A-11-296682

  However, in the above-described apparatus, for example, the information held by the subject is included in the image because the image is out of focus, the information display portion is reflected, the subject is tilted, and the like. There was a problem that the image could not be used and the image could not be used.

  Accordingly, an object of the present invention is to solve the above-described problems and provide an image determination system that employs an image that is highly likely to be used.

  A first system of the present invention includes an acquisition unit that acquires an image, a determination unit that determines whether or not the image satisfies an employment condition, and a storage unit, and the employment condition includes the image The predetermined character or image is recognized, and the storage unit stores the image determined by the determination unit to satisfy the employment condition.

  ADVANTAGE OF THE INVENTION According to this invention, the image determination system which employ | adopts the image with high possibility of being usable can be provided.

It is a block diagram which shows the structural example of 1st embodiment. It is a block diagram which shows the hardware structural example of 1st embodiment. It is a block diagram which shows the structural example of 2nd embodiment. It is a flowchart which shows an example of operation | movement of 2nd embodiment. It is a figure which shows an example of employment conditions. It is an example of the image which imaged the residence card. It is explanatory drawing of a predetermined position. It is a display example of the frame for alignment. It is a display example of the frame for alignment. It is a block diagram which shows the structural example of 3rd embodiment. It is a flowchart which shows an example of operation | movement of 3rd embodiment. It is an example of a display of character data. It is explanatory drawing of replacement | exchange of character data. It is explanatory drawing of replacement | exchange of character data. It is an example of the means for connecting to a support desk. It is a block diagram which shows the hardware structural example of 4th embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. However, the components described in the following embodiments are exemplifications, and are not intended to limit the technical scope of the present invention.
(First embodiment)
(Configuration of the first embodiment)
A configuration example of the first embodiment will be described. FIG. 1 is a block diagram showing a configuration example of the first embodiment. The image determination system 1000 includes an acquisition unit 10, a determination unit 20, and a storage unit 30. Each component shown in the figure is not a hardware unit configuration but a functional unit block.

  The acquisition unit 10 acquires an image. The determination unit 20 receives the image acquired by the acquisition unit 10 and determines whether or not the employment condition is satisfied. The adoption condition is that a predetermined character or image is recognized in the image. That is, the determination unit 20 may determine that the employment condition is satisfied even when a predetermined character or image is recognized at any position of the acquired image. The storage unit 30 acquires and stores an image that the determination unit 20 determines to satisfy the employment condition.

  Next, the hardware configuration of the first embodiment will be described with reference to FIG. FIG. 2 shows a hardware configuration for realizing each component of the first embodiment. The communication control unit 1 communicates with an external device via a network. A RAM (Random Access Memory) 2 is a random access memory used by a CPU (Central Processing Unit) 4 as a work area for temporary storage. The RAM 2 has a capacity for storing various data necessary for realizing the present embodiment. The storage unit 3 stores data such as a database necessary for realizing the present embodiment, application programs executed by the CPU 4, initial data, and the like in a nonvolatile manner. The CPU 4 is a processor for arithmetic control, and implements each functional unit of the present invention by executing a program.

  The CPU 4 may be replaced by a circuit other than the CPU. The circuit is one or a plurality of processors that execute programs, and includes CPUs, ASICs, PAL's, and the like. The plurality of circuits may cooperate in the same device or may exist in another device.

  As illustrated in FIG. 2, the storage unit 3 can implement a storage unit 30. The CPU 4 can realize the acquisition unit 10 and the determination unit 20. The association between each hardware configuration and each component is not limited to that shown in FIG. 2, and any combination may be used. For example, the acquisition unit 10 may be realized by the RAM 2. The acquisition unit 10 and the determination unit 20 may be realized by different circuits. The image determination system 1000 may be realized by a single device or a plurality of devices. In other words, the acquisition unit 10, the determination unit 20, and the storage unit 30 included in the image determination system 1000 may be realized by hardware in different devices.

The application program stored in the storage unit 3 is a program that executes processing performed by the acquisition unit 10 and the determination unit 20. CPU4 reads an application program from the memory | storage part 3, and performs the process of the acquisition part 10 and the determination part 20 In order to employ | adopt the image by which the predetermined character or image was recognized in the predetermined position according to 1st embodiment. Images that are likely to be used can be employed.
(Second embodiment)
(Configuration of Second Embodiment)
A configuration example of the second embodiment will be described. FIG. 3 is a block diagram showing a configuration example of the second embodiment. The image determination system 1002 includes an image determination device 100. The image determination apparatus 100 may be, for example, a mobile phone terminal, a tablet terminal, a personal computer, a digital camera, or the like. The image determination apparatus 100 includes an acquisition unit 11, a determination unit 21, a storage unit 31, and an imaging unit 40.

  The storage unit 31 stores different employment conditions for each document type in association with the document type. Documents include identification documents such as driver's licenses, passports, residence cards, and documents and cards containing personal information such as credit cards and cash cards. The adoption condition is a condition that serves as a reference for determining whether or not the image captured by the imaging unit 40 is to be used, and indicates that a predetermined character or image is recognized at a predetermined position. The storage unit 31 stores a predetermined position and a predetermined character in association with the document type as the employment condition. The storage unit 31 may store a predetermined image in place of a predetermined character as an employment condition. Store the image. The association between the document type and the employment condition may be realized by the storage unit 31 storing a table including “document type”, “position (coordinates, etc.)”, and “predetermined character or image”, for example. Good. Alternatively, the program executed by the acquisition unit 11 and the determination unit 21 may be operated so as to determine a corresponding employment condition when a specific document type is acquired.

  The imaging unit 40 captures a document that is a subject including personal information and generates an image. The image generation by the imaging unit 40 may be performed at regular time intervals, or may be performed at a timing when the user presses a shutter button (not shown). Alternatively, the image generation by the imaging unit 40 may be performed at a timing when an instruction based on the determination result of the image by the determination unit 21 is given.

  The acquisition unit 11 acquires an image obtained by imaging a subject including personal information from the imaging unit 40. The acquisition unit 11 may acquire the image every time the imaging unit 40 generates an image, or may acquire the image collectively at regular intervals. The acquisition unit 11 acquires the document type selected by the user via a designation unit (not shown). The designation unit may be, for example, a touch panel, operation buttons, a mouse connected to the image determination device 100, a keyboard, or the like that constitutes the image determination device 100. The document type designated by the user represents the type of document imaged by the imaging unit 40, and may be a driver's license, a passport, a residence card, or the like, for example.

  The determination unit 21 acquires the image and document type acquired by the acquisition unit 11. Then, the determination unit 21 determines whether the acquired image satisfies the employment condition corresponding to the acquired document type. The determination unit 21 reads out the employment condition associated with the acquired document type from the storage unit 31 and determines the acquired image. That is, the determination unit 21 determines whether a predetermined character or image corresponding to the document type is recognized at a corresponding predetermined position. When the acquired image satisfies the employment condition, the determination unit 21 stores the image in the storage unit 31. Note that recognition and determination of characters or images can be realized by existing techniques using image features such as pattern matching, statistical identification, and structure identification.

  When the acquired image does not satisfy the employment condition, the determination unit 21 instructs the imaging unit 40 to continue imaging. Alternatively, when the acquired image does not satisfy the adoption condition and a certain time has elapsed since the start of image capturing, the determination unit 21 may instruct the image capturing unit 40 to stop image capturing.

  Note that the determination unit 21 may recognize characters displayed on the image by performing OCR processing on a predetermined position. The OCR processing at this time is hereinafter referred to as determination OCR processing. The adoption condition in this case may be that the character recognized by the determination OCR process is the same as the predetermined character. That is, the determination unit 21 determines whether or not the character recognized at the predetermined position by the determination OCR process is the same as the predetermined character corresponding to the predetermined position (may be a part of the characters). If there is, it is determined that the employment condition is satisfied. When no character is recognized by the determination OCR process, and when the recognized character is not the same as the predetermined character, the determination unit 21 determines that the employment condition is not satisfied.

  Further, the image determination device 100 may not include the imaging unit 40. In that case, the acquisition unit 11 may acquire an image received by a receiving unit (not shown). That is, the image determination apparatus 100 may acquire an image obtained by capturing a document from the outside by wireless or wired communication.

The adoption condition may be that a predetermined character or image corresponding to each predetermined position is recognized at a plurality of predetermined positions. The adoption condition may be that corresponding characters or the like are recognized at all predetermined positions, or that corresponding characters or the like are recognized at a predetermined number of predetermined positions.
(Operation of Second Embodiment)
FIG. 4 is a flowchart showing the operation of the second embodiment. First, the acquisition unit 11 acquires the document type selected by the user via a designation unit (not shown) (S1). The designation of the document type by the user may be performed via an application stored in the image determination apparatus 100. In the present embodiment, the user designates the document type as “resident card”. The designation unit may be, for example, a touch panel, operation buttons, a mouse connected to the image determination device 100, a keyboard, or the like that constitutes the image determination device 100. When the document type is acquired, the image capturing unit 40 is activated and image capturing is started. Note that the document type may be selected after the image capturing is started.

  In the present embodiment, it is assumed that the user images the residence card using the imaging unit 40. A residence card is a card issued to a person who resides in Japan for a medium to long term as a result of permission related to the status of residence (medium to long term resident), and is a certificate that proves that the person is a legal person. Has the character of The residence card contains personal information such as name, address, gender, and nationality.

  The user brings the image determination device 100 and the residence card close to each other and stops still in a positional relationship where the imaging unit 40 can image the residence card. The imaging unit 40 captures an image that falls within the angle of view and generates an image. In the present embodiment, generation of the second and subsequent images after the imaging unit 40 is activated is performed at a timing when an instruction based on the determination result of the image by the determination unit 21 is given.

  The acquisition unit 11 acquires an image captured by the imaging unit 40 (S2). In the present embodiment, the acquisition unit 11 acquires the image every time the imaging unit 40 generates an image. The determination unit 21 acquires the image and document type acquired by the acquisition unit 11. Then, the determination unit 21 determines whether or not the acquired image satisfies an employment condition corresponding to the acquired document type (S3). That is, the determination unit 21 reads out the employment condition associated with the acquired document type from the storage unit 31. And the determination part 21 determines whether a predetermined character is recognized in the acquired image in the predetermined position in adoption conditions.

  More specifically, the storage unit 31 stores, for example, information illustrated in FIG. The storage unit 31 stores the employment conditions that are different for each document type in association with the document type. Since the adoption condition is that a predetermined character or image is recognized at a predetermined position, the storage unit 31 stores a predetermined character and a predetermined position in association with each document type. As shown in FIG. 5, for the document type “residence card”, the characters “residence card”, “Minister of Justice”, and “Government of Japan” are associated with the positions A, B, and C on the respective residence card. Is remembered. Predetermined positions such as A, B, and C can be represented by, for example, X and Y coordinate values of four corners of a rectangle surrounding a predetermined character. Note that the way of expressing the position and the position of the origin are not limited to this.

  When the determination unit 21 obtains that the document type is “residence card”, the predetermined character “residence card”, “Minister of Justice”, “Government of Japan” and predetermined positions A, B, and C thereof from the storage unit 31. Read out. Then, the determination unit 21 determines whether the acquired image satisfies the employment condition, that is, whether a predetermined character is recognized at the read predetermined position.

  FIG. 6 shows an example of the relationship between the position on the image obtained by capturing the residence card and the character. In FIG. 6, the X axis and the Y axis are set with the lower left corner of the residence card 2000 shown in the image as the origin. From FIG. 5, the position of the predetermined position 2001 is “A”, the position of the predetermined position 2002 is “B”, and the position of the predetermined position 2003 is “C”. Recognition of the position as the origin in the image may be performed by detecting the contour of the residence card 2000 that is shown in the image by a processing unit (not shown). That is, when the “position” of the employment condition stored in the storage unit 31 is the “position” of the subject in the image, the processing unit (not shown) may recognize the subject in the image.

  The “position” of the adoption condition stored in the storage unit 31 may not be the “position” of the subject in the image but the “position” of the entire image. For example, the position where the lower left corner of the entire image is the origin may be used as the adoption condition. In this case, the position of the subject in the image need not be recognized.

  Furthermore, when a plurality of predetermined characters or images are included in the employment conditions, the “position” of the employment conditions may be a relative position of those characters or images. The relative position may be represented by, for example, a distance between the centers of two or more characters or images, an angle formed by a straight line connecting the centers of two or more characters or images with respect to the horizontal direction, or the like. Further, the “position” of the employment condition may be that the relative distance between two or more characters or images is within a predetermined range.

  If the determination unit 21 determines that the acquired image satisfies the employment condition, the determination unit 21 stores the image in the storage unit 31. The storage unit 31 stores the image acquired from the determination unit 21 (S4), and the process ends.

If the determination unit 21 determines that the acquired image does not satisfy the adoption condition, the determination unit 21 determines whether a predetermined time has elapsed since the activation of the imaging unit 40 (S5). If the predetermined time has not passed,
The determination unit 21 instructs the image capturing unit 40 to continue image capturing. When the predetermined time has elapsed, the determination unit 21 instructs the imaging unit 40 to stop imaging, and the process ends.

  Since the determination unit 20 of the image determination system 1002 of the second embodiment determines whether or not a predetermined character or image is recognized at a predetermined position, the recognition load is reduced and the time required for recognition is shortened. . In addition, since the image determination system 1002 determines an image under the above-described employment conditions that differ for each document type, the system designer can set the employment conditions according to the characteristics of the document. For example, if the vicinity of a portion having important information (portion where a face photograph or name is displayed) is set as a predetermined portion, there is a possibility that the user can employ an image that can accurately read the information. Rise.

  The adoption condition may be configured by a plurality of predetermined positions and predetermined characters corresponding to the respective predetermined positions, or may be configured by one predetermined position and predetermined characters corresponding thereto. Further, the adoption condition may be that corresponding characters or the like are recognized at all predetermined positions, or corresponding characters or the like may be recognized at a predetermined number of predetermined positions. For example, in the above-described example of the residence card, the adoption condition may be satisfied when all of the predetermined characters “residence card”, “Minister of Justice”, and “Government of Japan” are recognized at the corresponding positions.

  When the employment condition is configured by a plurality of predetermined positions and predetermined characters corresponding to the respective positions, the possibility that the information contained in the document copied in the image can be used as a whole increases. That is, it is highly possible that any part of the image is in focus and not reflected, and the document information can be read. In particular, the effect is further enhanced by setting the predetermined positions so as to be distributed on the document.

  Further, the predetermined position may have a certain spread. That is, the predetermined position may be larger than the size of the predetermined character or image. When there is a certain spread at the predetermined position, the adoption condition may be that the character or the image is recognized at any position within the region included in the predetermined position. FIG. 7 is an explanatory diagram when there is a certain spread at a predetermined position. The image 4000 is an example of an image acquired by the determination unit 21. The predetermined positions 2004 to 2006 indicate predetermined positions corresponding to the characters “Japanese government”, “residence card”, and “Minister of Justice” to be recognized. For example, the determination unit 21 determines whether or not the character “Japanese government” is recognized at any position within the predetermined position 2006.

  Thereby, the determination unit 20 can determine that the employment condition is satisfied if the residence card 2000 is within a certain range with respect to the image 4000. Therefore, even if the user does not strictly adjust the positions of the image determination apparatus 100 and the subject, the image determination apparatus 100 can employ an image that is highly likely to be used. In particular, when the “position” of the adoption condition is “position” in the entire image, it is possible to reduce the burden of position adjustment between the image determination apparatus 100 and the subject by the user.

  Furthermore, when a user captures an image, a display unit (not shown) may display a frame for alignment together with the captured image. The alignment frame is preferably set so that characters or images to be authenticated are included in the captured image. A display example of a frame for alignment by the display unit is shown in FIG. FIG. 8 shows a smartphone 3000 as an example of the image determination device 100. The display unit 70 of the smartphone 3000 sequentially acquires and displays images captured by the imaging unit 40. A smartphone 3000 shown in FIG. 8 has an imaging unit 40 on the back surface of the display unit 70 and images a residence card 2000 that is a subject.

  The four frames 80 are frames for the user to adjust the size of the residence card that appears in the image captured by the imaging unit 40. The user adjusts the size of the residence card 2000 in the image by aligning the four corners of the residence card 2000 displayed on the display unit 70 with the frame 80. In FIG. 8, the size of the residence card 2000 is smaller than the size that fits the frame 80. Therefore, the user performs an operation of bringing the smartphone 3000 and the real residence card 2000 close to each other.

  Further, the alignment frame may indicate the size of the subject appearing in the image or may indicate the size of a part of the subject appearing in the image. The alignment frame shown in FIG. 9 indicates the size of the character part to be authenticated. The user adjusts the positions of the smart phone 3000 and the real residence card 2000 so that the letter “Minister of Justice” fits in the frame 81 and the letter “Japanese government” fits in the frame 82. A part of the subject targeted by the frame is not limited to the character to be authenticated. For example, a portion that is easy for the user to use, such as a face photo portion to be authenticated and a characteristic mark, may be used as the frame target.

  Note that the form of the frame for alignment described above is not limited to that shown in FIGS. The alignment frame may be anything as long as the user can adjust the size of the subject appearing in the image by looking at it, such as a dotted line, a figure represented by practice, or a template image of the subject.

  When the image determination apparatus 100 displays the alignment frame, the user can adjust the positions of the image determination apparatus 100 and the subject. Therefore, the time required for the image determination apparatus 100 to recognize a predetermined character or image and adopt an available image can be shortened. Further, when the “position” of the adoption condition is “position” of the subject appearing in the image, the load when the processing unit (not shown) recognizes the subject appearing in the image is reduced.

  Further, the image determination system 1002 does not have to perform image determination under the above-described employment conditions that are different for each document type. That is, the storage unit 31 may not store different employment conditions for each document type. For example, the employment conditions may be the same regardless of the subject. That is, S4 in the flowchart shown in FIG. 4 may not be executed. In that case, for example, when the user performs an operation of starting the imaging unit 40, the imaging of the image may be started. The operation in which the user activates the imaging unit 40 is an operation in which the user activates an application stored in the image determination apparatus 100 using a touch panel constituting the image determination apparatus 100, a mouse connected to the image determination apparatus 100, or the like. But it ’s okay. In this case, the determination unit 21 may read the employment condition from the storage unit 31 without acquiring the document type.

  Note that the determination unit 21 may recognize characters displayed on the image by performing OCR processing on a predetermined position. The OCR processing at this time is hereinafter referred to as determination OCR processing. The adoption condition in this case may be that the character recognized by the determination OCR process is the same as the predetermined character. That is, the determination unit 21 determines whether or not the character recognized at the predetermined position by the determination OCR process is the same as the predetermined character corresponding to the predetermined position. judge. When no character is recognized by the determination OCR process, and when the recognized character is not the same as the predetermined character, the determination unit 21 determines that the employment condition is not satisfied.

When OCR processing is performed on the image adopted by the image determination system 1002 and personal information is extracted from the document image (for example, when personal information is extracted from the certificate image and assists the form input) In addition, the determination OCR processing is effective. This is because, when a predetermined character is recognized at a predetermined position by the determination OCR process, there is a high possibility that a correct character is recognized by the OCR process at other portions.
(Third embodiment)
(Configuration of the third embodiment)
A configuration example of the third embodiment will be described. FIG. 10 is a block diagram showing a configuration example of the third embodiment. The image determination system 1003 includes an image determination apparatus 101. The image determination apparatus 101 includes an acquisition unit 11, a determination unit 21, a storage unit 31, an imaging unit 40, a processing unit 50, and a reception unit 60. Since the configuration other than the processing unit 50 and the receiving unit 60 is the same as that of the second embodiment, description thereof is omitted.

  The processing unit 50 performs OCR processing on the image stored in the storage unit 31 and stores the generated character data in the storage unit 31. That is, the processing unit 50 performs OCR processing on the image that the determination unit 21 determines to satisfy the employment condition, and extracts character data from the subject that appears in the image. The generated character data may be related to personal information displayed on the certificate or the like as the subject, and is the user's name, address, nationality, and the like. The generated character data may indicate items of personal information of the user such as “name”, “address”, “nationality”, and the like.

  Further, the processing unit 50 performs the correction OCR process when the receiving unit 60 receives the selection of the correction portion from the user. The correction OCR process is an OCR process that generates character data used to correct a correction portion. The character data generated by the correction OCR process is set as the correction character data.

  More specifically, the accepting unit 60 activates the imaging unit 40 when accepting selection of a correction portion from the user. Then, the imaging unit 40 starts capturing an image again. When the determination unit 21 stores a new image in the storage unit 31 through the same operation as in the second embodiment, the processing unit 50 performs the correction OCR process on the new image. Note that the reception unit 60 may instruct the processing unit 50 to perform the correction OCR process without starting the imaging unit 40 when receiving the selection of the correction portion from the user. In other words, the processing unit 50 may perform the correction OCR process on the same image as the previous time, instead of the newly captured image.

  Further, the processing unit 50 replaces the part of the correction character data generated by the correction OCR process corresponding to the correction part received by the receiving unit 60 with the character data stored in the storage unit 31. Details will be described later in the description of the operation of the third embodiment.

  The accepting unit 60 accepts selection of a correction portion that the user desires to correct among the character data stored in the storage unit 31. More specifically, first, a display unit (not shown) displays the character data generated by the processing unit 50 to the user. The user looks at the display unit and determines whether there is an error in the character data.

  When there is an error in the character data, the user selects a correction portion using a designation portion (not shown). The designation unit may be, for example, a touch panel, operation buttons, a mouse connected to the image determination apparatus 101, a keyboard, or the like that constitutes the image determination apparatus 101. The accepting unit 60 accepts selection of a correction portion from a not-shown designation unit. That is, the reception unit 60 acquires information specifying the correction portion selected by the user from the designation unit.

When the user determines that there is no error in the character data, the user performs an operation to end the processing of the image determination apparatus 101. The operation of ending the processing of the image determination apparatus 101 may be, for example, a user touching a “Confirm” icon displayed on a display unit (not shown) or clicking with a mouse.
(Operation of the third embodiment)
FIG. 11 is a flowchart showing the operation of the third embodiment. Since the operations of S1 to S5 are the same as those in the second embodiment, the description thereof is omitted. The processing unit 50 performs OCR processing on the image stored in the storage unit 31 (S6). Then, the processing unit 50 stores the character data generated by the OCR process in the storage unit 31 (S7). That is, the processing unit 50 extracts character data from the subject appearing in the image by performing OCR processing on the image that the determination unit 21 determines to satisfy the employment condition. The generated character data may be related to personal information displayed on the certificate or the like as the subject, and is the user's name, address, nationality, and the like.

  A display unit (not shown) displays character data stored in the storage unit 31. An example of character data displayed on a display unit (not shown) is shown in FIG. In FIG. 12, the user's personal information such as name, date of birth, and address is displayed as character data for each item. Each of these character data is generated by OCR processing from an image obtained by capturing the residence card in FIG.

  The processing unit 50 associates each item with character data. The processing unit 50 recognizes a character in which an item such as “name” and “birth date” is described by OCR processing, thereby recognizing a character described in the vicinity (for example, on the right side) as a character corresponding to the item. May be.

  The user who sees the display in FIG. 12 determines whether there is an error in the character data. When it is determined that there is an error, the user selects a correction portion using a designation unit (not shown). The designation unit may be, for example, a touch panel, operation buttons, a mouse connected to the image determination apparatus 101, a keyboard, or the like that constitutes the image determination apparatus 101.

  Comparing FIG. 6 and FIG. 12, in FIG. 6, the “address” is “Minato-ku ○ chome ○ number ○ number” in Tokyo, but in FIG. "East" has been replaced with "bundle". That is, it can be said that the image obtained by capturing the residence card in FIG. 6 was not correctly read by the OCR process. Thus, for example, the user touches and selects the “bundle” touch panel in the display shown in FIG. 12, and then presses the correction OCR button. The correction OCR button is an icon of a camera mark shown in FIG. Note that the selection method is not limited to this. For example, the user may perform the same selection using a mouse. In addition, the user may select an erroneous character by selecting all the characters that are not erroneous. The design of the correction OCR button is not limited to that shown in FIG.

  When the reception unit 60 detects the pressing of the correction OCR button, the reception unit 60 receives selection of a correction portion from a designation unit (not shown) (S8). That is, the reception unit 60 acquires information specifying the correction portion selected by the user from the designation unit. The accepting unit 60 activates the imaging unit 40 when accepting the selection of the correction portion. In addition, the receiving unit 60 instructs the processing unit 50 to perform a correction OCR process.

  After the imaging unit 40 is activated, the image determination apparatus 101 performs the same operation as in the second embodiment. When the determination unit 21 stores a new image in the storage unit 31, the processing unit 50 performs a correction OCR process on the new image (S9). The character data generated by the correction OCR process is set as the correction character data. Note that the accepting unit 60 may not activate the imaging unit 40 when accepting selection of a correction portion from the user. In other words, the processing unit 50 may perform the correction OCR process on the same image as the previous time, instead of the newly captured image. As described above, the processing unit 50 may perform association between the character data generated by the correction OCR process and each item.

  Further, the processing unit 50 replaces the part of the correction character data generated by the correction OCR process corresponding to the correction part received by the receiving unit 60 with the character data stored in the storage unit 31 (S10). An explanatory diagram of the replacement of the character data is shown in FIG. FIG. 13 is a comparison diagram showing character data generated by the OCR processing and correction character data generated by the correction OCR processing. The processing unit 50 replaces the “bundle” portion, which is a correction portion with a circle mark, in the character data with the “east” portion of the correction character data portion with a circle mark. Since these portions are located at the same place in the entire character data or correction character data, they can be said to be corresponding portions.

  The processing unit 50 does not have to perform replacement for parts other than these parts. The item “name” of the correction character data generated by the correction OCR process has the name “FLIZABETH”, and the initial is read incorrectly. There is no need to replace it.

  The character data stored in the storage unit 31 is overwritten with the character data in which the processing unit 50 replaces the corrected character, and is stored in the storage unit 31 again. A display unit (not shown) displays the character data stored in the storage unit 31 again. The user who sees the display on the display unit (not shown) determines again whether there is an error in the character data. If the user determines that there is an error in the character data, the accepting unit 60 accepts the selection of the correction portion via the designation unit (not shown) by the user (S11), as in S8. And the image determination apparatus 101 repeats operation | movement of S9-S11.

  In S8 or S11, when the user determines that there is no error in the character data, the user performs an operation to end the processing of the image determination apparatus 101. The operation of ending the processing of the image determination apparatus 101 is, for example, when the user touches the touch panel of the “Confirm” icon displayed on the display unit (not shown) as shown in FIG. good. As a result, the image determination apparatus 101 ends the operation. As described above, the character data determined through the confirmation and correction of the character data by the user can be used for purposes such as automatic input of forms and collection of user information.

  The operations after S6 may be performed independently of the operations of S1 to S5. That is, the images handled in S6 and subsequent steps may be adopted through S1 to S5 and not be stored images.

  The image determination system 1003 of the third embodiment replaces the correction portion selected by the user with respect to the character data with the correction character data, so that a portion to be newly corrected does not occur due to the correction OCR processing. . In other words, since an error occurs in a different part every time the correction OCR process is performed, it is possible to reduce the troublesomeness of the user who performs the same operation many times.

  The processing unit 50 may determine the item of personal information indicated by the character data based on the position of the generated character data in the image. In this case, the storage unit 31 may store each item and the position of each item on the image in association with each other. The processing unit 50 may read information stored in the storage unit 31 and associate each item with character data recognized by the OCR process. And the memory | storage part 31 matches and memorize | stores the character data and the item which the process part 50 produced | generated.

  When the image to be subjected to the correction OCR processing is an image of a document of a document type different from the image subjected to the OCR processing, the processing unit 50 is an item associated with character data including the correction portion. A part or all of the correction character data generated for the same item may be a corresponding part. For example, it is assumed that the image that is the target of the first OCR process is an image of the residence card, and the image that is the target of the correction OCR process is an image of the driver's license. FIG. 14 is a comparison diagram showing the character data generated by the OCR process and the correction character data generated by the correction OCR process.

  First, the processing unit 50 recognizes that the character data including the correction “bundle” is associated with the item “address” and is the first character of the character data associated with the “address”. . Then, the processing unit 50 replaces the correction character data with the character data as a portion corresponding to the first character of the character data associated with the same item “address”. That is, the processing unit 50 replaces the character data “bundle” of the corrected portion with “east”. The replacement of character data may be performed on the entire character data associated with the item “address”. That is, the processing unit 50 may replace the character data “Bund Kyoto Minato-ku ○ Chome ○ No. ○ No.” including the corrected portion with “Tokyo Minato-ku ○ Chome ○ No. ○ No.”.

  As a result, the image determination system 1003 uses the correction character data generated for the same item as the correction part item as the corresponding part. Characters constituting the same content as personal information can be replaced.

  Further, the processing unit 50 may provide a means for connecting to the support desk to the user when the correction OCR processing is performed a predetermined number of times. An example of means for connecting to the support desk is shown in FIG. For example, it is assumed that the user has instructed the image determination apparatus 101 to perform correction OCR processing a predetermined number of times in order to correct character data for the item “address”. Then, the processing unit 50 displays an icon of a telephone mark as shown on the right end of the item “address” in FIG. This icon is an example of means for connecting to the support desk. When the user touches the icon on the touch panel, a communication control unit (not shown) makes a call to a support desk phone number stored in advance, and the user can talk with a person in charge of the support desk. Become.

  Further, the processing unit 50 may send out an audio announcement via a speaker (not shown) when the icon is displayed. The content of the announcement may be a message indicating that the user can connect to the support desk by touching the icon.

As a result, the image determination system 1003 provides the user with a means for connecting to the support desk, so that the user can quickly obtain support even when the user is not able to correct the character data properly and is confused. Can do. In addition, a company that provides a service using the image determination system 1003 can quickly cope with a problem that the user has, and can increase customer satisfaction.
(Fourth embodiment)
(Configuration of the fourth embodiment)
A configuration example of the fourth embodiment will be described. FIG. 16 is a block diagram illustrating a configuration example of the fourth embodiment. FIG. 16 shows a functional unit block diagram showing components and hardware configuration examples for realizing them.

  The acquisition unit 11, the determination unit 21, the processing unit 50, and the reception unit 60 in the image determination apparatus 101 may be realized by the circuit 5. The storage unit 31 may be realized by the storage unit 6. The imaging unit 40 may be realized by the imaging unit 7. The imaging unit 7 may be a CCD (Charge Coupled Device) image sensor, a digital camera equipped with a CCD image sensor, or the like.

  The description of each component and the description of other hardware are the same as those in the above-described embodiment, and will be omitted. Note that the association between the hardware configuration and each component is not limited to that illustrated in FIG. 14, and is realized by any combination. For example, the acquisition unit 11, the determination unit 21, the processing unit 50, and the reception unit 60 may be realized by circuits in different apparatuses. The storage unit 6 may be realized by an apparatus different from the image determination apparatus 101, such as an external hard disk or an SD card.

  In this specification, the steps describing the series of processes described above are executed in parallel or individually even if they are not necessarily processed in time series, as well as processes performed in time series in the described order. It also includes the processing.

  Each embodiment mentioned above is only an example which materialized the present invention, and can be variously changed if it is in the range of the meaning of the present invention indicated in the claim.

1 Communication control unit 2 RAM
3 Memory 4 CPU
5 CPU
REFERENCE SIGNS LIST 6 storage unit 7 image pickup unit 10 acquisition unit 11 acquisition unit 20 determination unit 21 determination unit 30 determination unit 30 storage unit 31 storage unit 40 image pickup unit 50 processing unit 60 reception unit 70 display unit 80 frame 81 frame 82 frame 100 image determination device 101 image determination device 1000 Image Judgment System 1001 Image Judgment System 1002 Image Judgment System 1003 Image Judgment System 2000 Resident Card Reflected in Image 2001 Predetermined Position 2002 Predetermined Position 2003 Predetermined Position 2004 Predetermined Position 2005 Predetermined Position 2006 Predetermined Position 3000 Smartphone 4000 Image

Claims (10)

An acquisition unit for acquiring images;
A determination unit for determining whether or not the image satisfies an employment condition;
A storage unit;
The adoption condition is that a predetermined character or image is recognized in the image,
The storage unit stores the image determined by the determination unit to satisfy the employment condition.
Image judgment system. The image determination system according to claim 1, wherein the adoption condition is that the predetermined character or image is recognized at a predetermined position. The image is an image of a document containing personal information,
The acquisition unit acquires a document type of the document,
The image determination system according to claim 1, wherein the determination unit determines whether or not the image satisfies the different employment conditions for each document type. 4. The image determination system according to claim 1, wherein the adoption condition is that the predetermined character or image corresponding to each of the predetermined positions is recognized at a plurality of the predetermined positions. 5. The determination unit performs determination OCR processing on the predetermined position of the image,
5. The image determination system according to claim 1, wherein the adoption condition is that character data generated by the determination OCR process is the same as predetermined character data. 6. A processing unit that performs OCR processing on the image stored in the storage unit and stores the generated character data in the storage unit;
A reception unit that receives selection of a correction portion in the character data stored in the storage unit,
6. The processing unit replaces a portion corresponding to a correction portion received by the receiving unit, out of the correction character data generated by the correction OCR process, with character data stored in the storage unit. The image determination system according to any one of the above. The processing unit determines an item of information indicated by the character data based on the position of the generated character data in the image,
The storage unit stores the character data and the items in association with each other,
When the image to be subjected to the correction OCR processing is an image of a document of a different document type from the image subjected to the OCR processing,
7. The processing unit sets a part or all of the correction character data generated for the same item as the item associated with the character data including the correction part as the corresponding part. The image determination system described. The image determination system according to claim 6, wherein the processing unit provides a user with means for connecting to a support desk when the correction OCR processing is performed a predetermined number of times. Get an image,
Determining whether the image satisfies the employment condition;
Storing the image determined by the determination unit to satisfy the employment condition;
The image determination method in which the adoption condition is that a predetermined character or image is recognized in the image. On the computer,
An acquisition process to acquire an image;
A determination process for determining whether or not the image satisfies an employment condition;
A storage process for storing the image determined by the determination unit to satisfy the employment condition;
The adoption condition is that a predetermined character or image is recognized in the image.
Image judgment program.

Images