JPWO2013114806A1 - Biometric authentication device and biometric authentication method - Google Patents

Abstract

The biometric authentication apparatus includes an acquisition unit that sequentially acquires three-dimensional information including biological information of a target biological body, a detection unit that detects a predetermined operation pattern of a predetermined part of the target biological body from the three-dimensional information acquired by the acquisition unit, An extraction unit that extracts biometric feature data specified by using the motion position information of the predetermined motion pattern detected by the detection unit from the storage unit that stores a plurality of biometric feature data, and the three-dimensional acquired by the acquisition unit A generating unit that generates current biological feature data of the target living body from the information, a biometric feature data extracted by the extracting unit, and a matching unit that checks the current biological feature data of the target living body generated by the generating unit.

Description

  The present invention relates to a biometric authentication technique.

  The motion capture technology is used in various fields such as generation of CG (Computer Graphics) characters in movies and games and sports analysis. In recent years, a game device called Kinect (registered trademark) has appeared, and since there is no need to attach a marker as in the past, motion capture technology is becoming familiar.

  Motion capture technology is also used in security fields such as personal authentication. Along with this, an authentication method using the gesture of the person to be authenticated has also been proposed.

  In Patent Document 1 below, detection of a specific action (blink of eyes) of a predetermined part of a living body is used as a trigger for starting a collation process of a face image, so that impersonation using a photograph is prevented, an ID number is input, and the like It has been proposed that the operation of the apparatus is unnecessary. Patent Document 2 below proposes a method for permitting the use of a device such as a vehicle based on the results of both authentication using a vehicle key owned by the person to be authenticated and authentication using a gesture of the person to be authenticated. ing.

JP 2002-251614 A JP 2010-176487 A

  However, in each method proposed in Patent Documents 1 and 2 described above, authentication using a gesture and authentication using another method cannot be effectively linked.

  Specifically, since the technique proposed in Patent Document 1 merely uses detection of a specific gesture as a trigger for starting face image matching, personal authentication itself uses a gesture. Is not done. In addition, since the technique proposed in Patent Document 2 merely performs verification between gestures and verification between other information (key information) separately, a final authentication result can be obtained. Both verification processes must be completed. Therefore, in this method, the efficiency of collation processing time is not achieved.

  The present invention has been made in view of such circumstances, and provides a technique for efficiently performing biometric authentication using a biometric action.

  Each aspect of the present invention employs the following configurations in order to solve the above-described problems.

  The first aspect relates to a biometric authentication device. The biometric authentication device according to the first aspect includes an information acquisition unit that sequentially acquires three-dimensional information including biometric information of a target biological body, and a predetermined operation of a predetermined part of the target biological body from the three-dimensional information acquired by the information acquisition unit. Extraction that extracts biometric feature data specified using motion position information of a predetermined motion pattern detected by the motion detection unit from a motion detection unit that detects a pattern and a biometric information storage unit that stores a plurality of biometric feature data , A feature data generation unit that generates current biological feature data of the target living body from the three-dimensional information acquired by the information acquisition unit, biometric feature data extracted by the extraction unit, and a target generated by the feature data generation unit A collation unit that collates the current biological feature data of the biological body.

  The second aspect relates to a biometric authentication method. The biometric authentication method according to the second aspect sequentially acquires three-dimensional information including biological information of a target living body, detects a predetermined operation pattern of a predetermined part of the target living body from the acquired three-dimensional information, and a plurality of living bodies From the biometric information storage unit that stores the feature data, the biometric feature data specified by using the motion position information of the detected predetermined motion pattern is extracted, and the current biometric feature data of the target living body is generated from the acquired three-dimensional information And comparing the extracted biometric feature data with the generated current biometric feature data of the target biometric.

  According to another aspect of the present invention, there is provided a biometric authentication system including the biometric authentication device according to the first aspect, a three-dimensional sensor that sends three-dimensional information to the information acquisition unit, and the biometric information storage unit. Alternatively, it may be a computer program that causes a computer to realize the configuration of the first aspect, or a computer-readable recording medium that records such a program. This recording medium includes a non-transitory tangible medium.

  According to each aspect of the present invention, it is possible to provide a technique for efficiently performing biometric authentication using a biological action.

  The above-described object and other objects, features, and advantages will become more apparent from the preferred embodiments described below and the accompanying drawings.

FIG. 1 is a diagram conceptually illustrating a hardware configuration example of the face image authentication apparatus in the first embodiment. FIG. 2 is a diagram conceptually illustrating a processing configuration example of the face image authentication apparatus in the first embodiment. FIG. 3 is a diagram illustrating an example of the identification data storage unit. FIG. 4 is a diagram illustrating an example of the biological information storage unit. FIG. 5 is a flowchart illustrating an operation example of the face image authentication apparatus according to the first embodiment. FIG. 6 is a diagram illustrating a transition example of the display image in the embodiment. FIG. 7 is a diagram illustrating a transition example of the display image in the embodiment. FIG. 8 is a diagram illustrating a transition example of the display image in the embodiment.

  Embodiments of the present invention will be described below. In addition, embodiment mentioned below is an illustration and this invention is not limited to the structure of the following embodiment.

  The biometric authentication device according to the present embodiment includes an information acquisition unit that sequentially acquires three-dimensional information including biometric information of a target living body, and a predetermined part of the target biological body that is obtained from the three-dimensional information acquired by the information acquisition unit. The biometric feature data specified using the motion position information of the predetermined motion pattern detected by the motion detection unit is extracted from the motion detection unit that detects the motion pattern and the biometric information storage unit that stores a plurality of biometric feature data. Generated by the extraction unit, the feature data generation unit that generates the current biological feature data of the target living body from the three-dimensional information acquired by the information acquisition unit, the biological feature data extracted by the extraction unit, and the feature data generation unit And a collation unit that collates the current biological feature data of the target biological body. The present embodiment is also a biometric authentication method including each operation executed by each processing unit, and is a program that causes a computer to realize each processing unit and a recording medium that stores the program.

  Here, the information acquisition unit may generate three-dimensional information by itself as a three-dimensional sensor, or may acquire the three-dimensional information from an external three-dimensional sensor. Further, the biological information included in the acquired three-dimensional information may be information on the whole body of the person, information on only the upper body and lower body, or a head, hand, foot, or the like. It may be information on a predetermined part. In addition, a living body image of the target living body can be generated from the three-dimensional information.

  The biometric information storage unit may be included in the biometric authentication device according to the present embodiment, or may be included in another device (such as a server device). The biometric feature data and the current biometric feature data may be any information that can be acquired from the three-dimensional information, such as a face, eyes (iris), and hands (fingerprints and veins).

  As described above, in the present embodiment, a predetermined motion pattern of a predetermined part of the target living body is detected, and the biological feature data specified by the motion position information of the predetermined motion pattern from the biological information storage unit, and the target biological body One-to-one matching is performed using the extracted current biological feature data. That is, in the present embodiment, biometric feature data for one-to-one matching is specified using a predetermined motion pattern, that is, motion position information of a predetermined gesture, as a key. This can be realized by uniquely determining the motion position of the predetermined motion pattern to be detected for each target living body.

  As a result, in the conventional one-to-one matching, an input operation such as a user ID or a password is required to specify one piece of biometric feature data to be verified. Input operation is unnecessary. Furthermore, according to the present embodiment, since one-to-one matching is performed, authentication processing can be performed at higher speed and higher accuracy than one-to-many matching. As described above, according to the present embodiment, the predetermined action of the living body is effectively used and the one-to-one matching of the living body information is executed. Therefore, the biometric authentication using the action of the living body can be performed efficiently and with high accuracy. Can be executed.

  Hereinafter, the details of the above-described embodiment will be described. Each detailed embodiment shown below is an example when the configuration of the biometric authentication device in the above-described embodiment is applied to face image authentication. Note that the above-described embodiment is applicable to various biometric authentications without limiting the biometric information used for authentication to a face image.

[First Embodiment]
〔Device configuration〕
FIG. 1 is a diagram conceptually illustrating a hardware configuration example of a face image authentication device (hereinafter simply referred to as an authentication device) 10 according to the first embodiment. The authentication device 10 according to the first embodiment is a so-called computer, and includes, for example, a CPU (Central Processing Unit) 2, a memory 3, an input / output interface (I / F) 4, and the like that are connected to each other via a bus 5. The memory 3 is a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk, a portable storage medium, or the like.

  As shown in FIG. 1, the input / output I / F 4 is connected to the three-dimensional sensor 7, the display unit 9, and the like. The display unit 9 is a display device such as a display. Note that this embodiment does not limit devices connected to the input / output I / F 4, but via an input unit that accepts user operation input such as a keyboard and a mouse, a printer, and a network (not shown). It may be connected to a communication device or the like that communicates with other computers. The hardware configuration of the authentication device 10 is not limited.

  The three-dimensional sensor 7 detects three-dimensional information including the subject's biological information. The detected three-dimensional information includes information on the two-dimensional image (image) of the subject obtained by visible light and information on the distance from the three-dimensional sensor 7. Hereinafter, the axis indicating the distance from the three-dimensional sensor 7 is denoted as the Z axis. The three-dimensional sensor 7 is realized by a visible light camera and a distance image sensor like Kinect (registered trademark), for example. A distance image sensor, also called a depth sensor, irradiates a subject with a near-infrared light pattern from a laser and captures the pattern with a camera that detects the near-infrared light. The distance to the person is calculated.

  The method for realizing the three-dimensional sensor 7 is not limited, and the three-dimensional sensor 7 may be realized by a three-dimensional scanner method using a plurality of visible light cameras. In FIG. 1, only one three-dimensional sensor 7 is illustrated. However, as the three-dimensional sensor 7, a plurality of sensors such as a visible light camera that captures a two-dimensional image of the subject and a sensor that detects a distance to the subject. Equipment may be provided.

  FIG. 2 is a diagram conceptually illustrating a processing configuration example of the authentication device 10 in the first embodiment. The authentication device 10 according to the first embodiment includes an information acquisition unit 11, an operation detection unit 13, an extraction unit 15, a feature data generation unit 17, a collation unit 19, an identification data storage unit 21, a biometric information storage unit 23, and a display processing unit 25. Etc. Each of these processing units is realized, for example, by executing a program stored in the memory 3 by the CPU 2. Further, the program may be installed from a portable recording medium such as a CD (Compact Disc) or a memory card or another computer on the network via the input / output I / F 4 and stored in the memory 3. Good.

  The information acquisition unit 11 sequentially acquires three-dimensional information including biological information of the target person (target biological body) from the three-dimensional sensor 7. As long as the three-dimensional information includes the biological information of the subject and the information on the distance from the three-dimensional sensor 7, the form of realization is not limited. The acquisition speed of the three-dimensional information is arbitrary, but the acquisition speed is related to an allowable operation speed of the operator. That is, if the acquisition speed is high, the allowable operation speed of the operator is also high.

  The motion detection unit 13 detects a predetermined motion pattern of a predetermined part of the subject from the three-dimensional information acquired by the information acquisition unit 11. Specifically, the motion detection unit 13 recognizes the predetermined part of the target person from the three-dimensional information, and the predetermined part of the target person in the predetermined direction of the predetermined dimension in the three dimensions indicated by the sequentially acquired three-dimensional information. Is detected as a predetermined motion pattern.

  Since recognition of a predetermined part should just use the technique of general image recognition (pattern recognition), description is simplified here. For example, a technique for recognizing a human body, face, eyes, mouth and the like from an image is well known. The motion detection unit 13 recognizes a predetermined part of the subject from the three-dimensional information of the subject using such a well-known method.

  The motion detection unit 13 recognizes the predetermined reference portion of the subject based on the biological image of the subject included in the three-dimensional information, and recognizes the predetermined portion based on the positional relationship with the predetermined reference portion. May be. For example, the motion detection unit 13 recognizes a face as a predetermined reference portion, and then recognizes a face closer to the three-dimensional sensor 7 on the Z axis than the face as both hands of the subject person, and sets the center of each palm. Recognized as a predetermined part.

  Note that the predetermined reference portion and the predetermined portion are not limited as long as the predetermined portion of the subject can be recognized. When the predetermined part is set on the toes of each foot and the predetermined reference part is set on both feet, both feet are recognized from the biological image, and from the distance information, the portion of both feet is closest to the three-dimensional sensor 7 What is in position is recognized as each toe of the subject.

  For the detection of the movement as the predetermined operation pattern, a general motion capture technique may be used. Since this motion capture technique itself is well known, description of itself is omitted here. For example, the motion detection unit 13 has a predetermined width (for example, 20 centimeters (cm) in the real world) in a direction in which the palm of the subject approaches the Z-axis 3D sensor 7 of the 3D information. Detects that it has moved).

  The predetermined operation pattern of this example is an operation in which the subject projects the palm forward from a certain position (in the direction of the three-dimensional sensor 7). In this example, the motion detector 13 detects the motion as a predetermined motion pattern regardless of the position at which the palm protrudes on the plane coordinates orthogonal to the Z axis. For example, when the palm is protruded from the position on the head, in front of the face, and in front of the chest, each motion is detected.

  The motion detection unit 13 may set a detection space for such a predetermined motion pattern. In other words, the motion detection unit 13 sets a detection space of a predetermined size at a predetermined position in the three-dimensional space indicated by the three-dimensional information acquired by the information acquisition unit 11, and the predetermined part of the subject outside the detection space is set. The motion is excluded, and a predetermined motion pattern of a predetermined portion of the subject in the detection space is detected. By setting the detection space, the motion detection unit 13 acquires coordinate information indicating the space. Note that the position and size of the detection space are not limited as long as the predetermined part of the subject can be reached. The motion detection unit 13 sets only the motion of the subject in the detection space set in this way as the detection target of the predetermined motion pattern.

  The motion detection unit 13 detects a predetermined part of the subject from the three-dimensional information and sets the detection space at a position indicating a predetermined positional relationship with the detected predetermined part or another predetermined part of the subject. Also good. For example, when the predetermined part is the center part of the palm, the motion detection unit 13 is in a range where both hands reach from the face in the direction of the three-dimensional sensor 7 at a position substantially the same height as the face recognized as another predetermined part. A spatial area having a size that can be reached by both hands is set at the position.

  The predetermined operation pattern may be one predetermined operation or a combination of two or more predetermined operations. The combination of two or more predetermined movements may be a combination of a plurality of different movement forms, a plurality of the same movement forms, or a combination thereof. For example, the predetermined motion pattern may be that the operation of pushing the palm forward is performed a predetermined number of times, or the operation of pushing the palm forward is composed of two times and the operation of pulling the palm forward is composed of three times. Also good.

  When detecting the predetermined motion pattern in the detection space, the motion detection unit 13 holds the motion position information of the detected predetermined motion pattern. The movement position information is information indicating a predetermined movement included in the predetermined movement pattern, that is, a position where the movement is performed. When the predetermined motion pattern includes a plurality of predetermined motions, the motion position information includes the position information on which each movement has been performed. For example, when the predetermined motion pattern is a motion of protruding the palm three times in the Z-axis direction, the motion position information indicates three positions where the motion is performed on the plane coordinates orthogonal to the Z-axis.

  FIG. 3 is a diagram illustrating an example of the identification data storage unit 21. As shown in FIG. 3, the identification data storage unit 21 stores the correspondence between the motion position information of the predetermined motion pattern and each biometric identification data. In the example of FIG. 3, the biometric identification data is described as a personal ID (Identification), and the first position information to the fifth position information are stored for each personal ID. According to the example of FIG. 3, the operation position information of the predetermined operation pattern may indicate one position, or may indicate a plurality of positions of 5 or less.

  FIG. 4 is a diagram illustrating an example of the biometric information storage unit 23. As shown in FIG. 4, the biometric information storage unit 23 stores a plurality of biometric feature data and biometric identification data associated with each biometric feature data. In the example of FIG. 4, the biometric identification data is written as a personal ID. Each biometric feature data stored in the biometric information storage unit 23 is each biometric information legitimately acquired from each individual in advance in order to indicate the legitimacy of each individual. The biometric feature data is, for example, data indicating facial features acquired from each individual's facial image. The method for extracting biometric feature data as biometric information from each individual and the configuration of the biometric feature data itself may be a well-known one used in a well-known biometric authentication technique. Omitted.

  The extraction unit 15 acquires biometric identification data corresponding to the motion position information of the predetermined motion pattern detected by the motion detection unit 13 from the identification data storage unit 21, and the biometric feature associated with the acquired biometric identification data. Data is extracted from the biological information storage unit 23. In the example of FIGS. 3 and 4, the extraction unit 15 extracts the personal ID corresponding to the motion position information (a plurality of position information) of the predetermined motion pattern from the identification data storage unit 21, and the living body associated with the personal ID Feature data is extracted from the biometric information storage unit 23. The extraction unit 15 uses the identification data storage unit 21 to specify the records in which the position information of the identification data storage unit 21 is included in the predetermined allowable area from the positions indicated by the operation position information. From the above, the personal ID may be extracted.

  The feature data generation unit 17 generates biometric feature data of the target living body from the three-dimensional information acquired by the information acquisition unit 11. The biometric feature data generated by the feature data generation unit 17 is represented as current biometric feature data in order to distinguish it from the biometric feature data stored in the biometric information storage unit 23. For example, the feature data generation unit 17 generates current biological feature data of the target living body from a two-dimensional biological image included in the three-dimensional information. Note that the biometric feature data generation method itself by the feature data generation unit 17 may be a well-known method used in a well-known biometric authentication technique, and thus detailed description thereof is omitted here.

  The collation unit 19 collates the biometric feature data extracted from the biometric information storage unit 23 with the current biometric feature data of the target living body generated by the feature data generation unit 17. As for collation between biometric feature data, a well-known method may be used in biometric authentication, and thus description thereof is omitted here. The collation unit 19 generates output data indicating the collation result, and outputs the collation result to the display unit 9 and other output devices via the input / output I / F 4.

  The display processing unit 25 causes the display unit 9 to display a predetermined display image by sending screen data via the input / output I / F 4. Specifically, the display processing unit 25 includes a living body image of the target living body generated from the three-dimensional information acquired by the information acquiring unit 11 or a living body replicated image that replicates the living body image, and a predetermined operation pattern on the target living body. A display image including a guide image that guides the user to operate is displayed on the display unit 9. In the display image, at least a part of the guide image is arranged in a space corresponding to the detection space set by the motion detection unit 13 in the display image. A living body replicated image is, for example, an animation image that replicates a subject.

  The display processing unit 25 may display the guide image in the display image at a predetermined timing. The predetermined timing may be, for example, a timing when the motion detection unit 13 detects a predetermined part of the subject in the three-dimensional space indicated by the three-dimensional information acquired by the information acquisition unit 11, or the motion detection unit 13 may be a timing at which a predetermined pose of the subject is detected, which is set as a trigger for starting the detection process of the predetermined motion pattern by 13. Further, when the predetermined motion pattern is detected by the motion detection unit 13, the display processing unit 25 may change the induced image into a shape corresponding to the predetermined motion pattern.

  As the guidance image, a sentence explaining a predetermined operation pattern may be displayed, or an image having a user interface that can be operated by a virtual subject in a display image such as a button, a dial, or a screw is displayed. Good. For example, when the predetermined operation pattern corresponds to an operation in which a virtual subject in the display image presses a button, the display processing unit 25 may display a guide image in which a plurality of buttons are arranged in the display image. Good. In this case, the display processing unit 25 changes the color of at least one of the plurality of buttons in response to detection of a predetermined action pattern corresponding to the movement of the target person's biological image or the living body replicated image in which the action of the target person is reflected. Or may be changed to a pressed state.

[Operation example]
Hereinafter, the face image authentication method according to the first embodiment will be described. FIG. 5 is a flowchart illustrating an operation example of the authentication device 10 according to the first embodiment.

  The authentication device 10 sequentially acquires three-dimensional information including the subject's biological information (S51). This three-dimensional information may be acquired from the information detected by the three-dimensional sensor 7 as described above, or may be acquired from another device.

  The authentication device 10 detects a predetermined motion pattern of a predetermined part of the subject based on the three-dimensional information of the subject acquired sequentially (S52). At this time, the authentication apparatus 10 may set a detection space of a predetermined size at a predetermined position in the three-dimensional space indicated by the three-dimensional information, and set this detection space as a detection region of a predetermined motion pattern. Further, the authentication device 10 displays a display image including a biological image of the subject person or a biologically replicated image that duplicates the biological image and a guidance image that guides the subject person to operate a predetermined operation pattern on the display unit 9. You may let them. In this case, the authentication device 10 may deform the guide image in the display image in response to detection of the predetermined motion pattern of the subject.

  After detecting the predetermined motion pattern, the authentication device 10 extracts biometric identification data corresponding to the detected motion position information of the predetermined motion pattern from the identification data storage unit 21 (S53). When the predetermined action pattern is a combination of a plurality of actions, biometric identification data corresponding to the combination of position information where each action is performed is extracted.

  The authentication device 10 extracts biometric feature data corresponding to the biometric identification data extracted in (S53) from the biometric information storage unit 23 that stores biometric feature data of a plurality of persons (S54).

  The authentication device 10 generates current biological feature data of the subject based on the three-dimensional information of the subject acquired sequentially (S55).

  The authentication device 10 collates the biometric feature data extracted from the biometric information storage unit 23 in (S54) and the current biometric feature data generated in (S55) (S56), and outputs the collation result (S57). ). In FIG. 5, (S55) may be executed before (S53), or may be executed between (S53) and (S54).

[Operation and Effect of First Embodiment]
As described above, in the first embodiment, the predetermined motion pattern (predetermined gesture) of the subject is detected from the three-dimensional information sequentially obtained by the three-dimensional sensor 7 or the like, and information on the position where the predetermined motion pattern is performed ( The biometric identification data corresponding to the movement position information is specified, and the biometric feature data corresponding to the biometric identification data is extracted. One-to-one matching is performed between the biometric feature data and the current biometric feature data reflecting the current biometric information of the subject.

  Therefore, according to the first embodiment, one-to-one verification of biometric information can be performed according to a predetermined gesture of the subject without requiring the subject's input operation or the like. That is, according to the first embodiment, biometric authentication using a biometric operation can be executed efficiently and with high accuracy.

  In addition, according to the first embodiment, a guide image for causing the subject to perform a motion of the predetermined motion pattern is displayed, and the guide image is deformed according to the predetermined motion pattern. If it operates, a predetermined operation pattern (pressing operation, pulling operation, etc.) can be naturally executed.

  In addition, according to the first embodiment, since a detection space for a predetermined motion pattern is set, the predetermined motion pattern is determined depending on the part of the target person, the other person, or the object in the three-dimensional space indicated by the three-dimensional information. Can be prevented from being inhibited. That is, the target person can cause the face image authentication apparatus 10 to perform face authentication by a natural operation.

[Modification]
In the first embodiment described above, the biometric identification data (the personal ID in FIGS. 3 and 4) is used, but the biometric identification data may not be used. In this case, the authentication device 10 does not have the identification data storage unit 21, and the biometric information storage unit 23 may store a plurality of pieces of motion position information and biometric feature data stored in the identification data storage unit 21. Thereby, (S53) and (S54) shown in FIG. 5 are replaced with processing for extracting biometric feature data corresponding to the detected motion position information of the predetermined motion pattern.

  In the first embodiment described above, the combination of the guide image and the predetermined operation pattern may be arbitrarily switched. Even if the movement of the subject pushing the palm forward is a predetermined movement pattern, even if the movement of the subject pulling the palm forward is the predetermined movement pattern, both movements are performed if each movement is executed at the same position. The position information is equal. Therefore, as long as the combination of the guide image and the predetermined motion pattern that does not change the motion position information corresponding to the subject person is used, collation is possible as in the first embodiment even if the combination is arbitrarily switched. In this case, the authentication device 10 according to the first embodiment further includes a pattern switching unit, and the pattern switching unit performs switching of the induced image and switching of the predetermined operation pattern at an arbitrary timing by the operation detection unit 13 and the display processing. The unit 25 is instructed. If it does in this way, it can make it difficult for a 3rd person to grasp | ascertain a predetermined motion pattern from a subject's motion.

  In the first embodiment described above, the authentication device 10 includes the identification data storage unit 21 and the biometric information storage unit 23. However, the identification data storage unit 21 and the biometric information storage unit 23 are provided in other devices and are authenticated. The device 10 may access the identification data storage unit 21 and the biometric information storage unit 23 in the other device.

  Each above-mentioned embodiment and each modification can be combined in the range in which the contents do not conflict.

  Examples will be given below to describe the above-described embodiment in more detail. The present invention is not limited in any way by the following examples. In this embodiment, the verification result is used for door lock authentication. In the embodiment, a display image as shown in the examples of FIGS. 6, 7, and 8 is displayed on the display unit 9. 6, 7, and 8 are diagrams illustrating examples of display image transition in the embodiment.

  In the present embodiment, as shown in FIG. 6, an image in a three-dimensional space generated by sequentially acquired three-dimensional information is displayed on the display unit 9. In this case, the three-dimensional sensor 7 captures an image of the target person and its surrounding space, detects distance information from the three-dimensional sensor 7, and the three-dimensional information including the image and the distance information is the information acquisition unit 11. Obtained by The display processing unit 25 causes the display unit 9 to display the video generated from the three-dimensional information.

  In the present embodiment, as shown in FIG. 7, in the detection space in the display image, the subject takes a posture (hereinafter referred to as a start gesture) in which the palms of both hands are put together and fixed in front of the face. When the start gesture is detected by the motion detection unit 13, detection of a predetermined motion pattern is started. In the detection of the start gesture, the motion detection unit 13 recognizes a face that is easy to recognize an image as a predetermined reference portion in the display image, and detects a face closer to the three-dimensional sensor 7 on the Z axis than the face. Recognize as both hands. The motion detector 13 recognizes the center of each palm as a predetermined part from the shape of both hands together.

  At this time, in this embodiment, the display processing unit 25 displays the transparent keyboard 31 as a guide image in front of the subject in the display image. At this time, the transparent keyboard 31 is arranged on a two-dimensional plane orthogonal to the Z axis in the three-dimensional space indicated by the three-dimensional information. Thereby, the motion detection unit 13 recognizes the position information in the two-dimensional plane as the position information of each button of the transparent keyboard 31.

  The predetermined operation pattern in the present embodiment is an operation in which the palm of the subject moves by a predetermined width in a direction approaching the Z-axis three-dimensional sensor 7. The subject operates so as to press the button of the transparent keyboard 31 (guidance image) on which the subject image in the display image is displayed on the display unit 9 while viewing the display image (video) reflected on the display unit 9. . Since this operation matches the predetermined operation pattern of the present embodiment, the operation detection unit 13 detects this operation as a predetermined operation pattern.

  When the operation detection unit 13 detects the predetermined operation pattern, the display processing unit 25 changes the color of the button virtually operated according to the predetermined operation pattern as shown in FIG. The example of FIG. 8 shows a state where the button indicating “1” on the transparent keyboard 31 is pressed.

  The motion detection unit 13 holds the motion position information every time a predetermined motion pattern, that is, a virtual button pressing motion is detected. In this embodiment, the position information of the virtually operated button is held as the operation position information. The operation detection unit 13 continues to detect the predetermined operation pattern until an operation of virtually pressing the “OK” button of the transparent keyboard 31 is detected. When the “OK” button is virtually pressed after the plurality of buttons are virtually pressed, the operation position information of the predetermined operation pattern indicates a plurality of positions.

  The extraction unit 15 extracts the biometric feature data corresponding to the motion position information of the predetermined motion pattern from the biometric information storage unit 23, and the collation unit 19 uses the biometric feature data as shown in FIG. 6, FIG. 7, and FIG. One-to-one matching is performed with the current biological feature data extracted from the video. The display processing unit 25 displays this collation result in the display image as “OK”, “NG”, “◯”, “x”, and the like.

  The collation unit 19 in this embodiment sends the collation result to the door lock control unit. Thereby, when the collation result indicates success, the door lock is released by the control unit, and when the collation result indicates failure, the door lock remains locked.

  In the present embodiment, it has been described that the motion detection unit 13 recognizes the position information in the two-dimensional plane as the position information of each button of the transparent keyboard 31, but the motion detection unit 13 does not recognize the character associated with each button. Information (numbers displayed on each button of the transparent keyboard 31) may be recognized, and this character information may be used as biometric identification data. Specifically, the motion detection unit 13 identifies a number associated with the button corresponding to the motion position of the predetermined motion pattern, and extracts biometric feature data corresponding to this number from the biometric information storage unit 23.

  A part or all of the above-described embodiments, modifications, and examples may be specified as in the following supplementary notes. However, each embodiment, each modification, and each example are not limited to the following descriptions.

(Appendix 1)
An information acquisition unit for sequentially acquiring three-dimensional information including biological information of the target biological body;
An operation detection unit for detecting a predetermined operation pattern of a predetermined part of the target living body from the three-dimensional information acquired by the information acquisition unit;
An extraction unit that extracts biometric feature data specified by using the motion position information of the predetermined motion pattern detected by the motion detection unit from a biometric information storage unit that stores a plurality of biometric feature data;
A feature data generation unit that generates current biological feature data of the target living body from the three-dimensional information acquired by the information acquisition unit;
A collation unit for collating the biometric feature data extracted by the extraction unit with the current biometric feature data of the target living body generated by the feature data generation unit;
A biometric authentication device.

(Appendix 2)
The motion detector is
A detection space having a predetermined size is set at a predetermined position in the three-dimensional space indicated by the three-dimensional information;
Excluding the movement of the predetermined part of the target living body outside the detection space, and detecting the predetermined movement pattern of the predetermined part of the target living body in the detection space;
The biometric authentication device according to appendix 1.

(Appendix 3)
A display image including a living body image of the target living body generated from the three-dimensional information or a living body replicated image that replicates the living body image, and a guidance image that guides the target living body to operate the predetermined operation pattern. The biometric authentication according to appendix 2, further comprising a display processing unit that causes the display unit to display the display image in which at least a part of the guide image is arranged in a space corresponding to the detection space in the display image. apparatus.

(Appendix 4)
The biometric authentication device according to appendix 3, wherein the display processing unit changes the guidance image when the predetermined motion pattern is detected by the motion detection unit.

(Appendix 5)
The predetermined motion pattern is a movement of the predetermined part of the target living body with a predetermined width in a predetermined direction of a predetermined dimension in a three-dimensional space indicated by the three-dimensional information.
The operation position information of the predetermined operation pattern for specifying the biometric feature data indicates a position where the movement is performed in a two-dimensional plane other than the predetermined dimension,
The biometric information storage unit stores biometric identification data associated with each of the plurality of biometric feature data,
The extraction unit includes:
Including an identification data storage unit for storing a correspondence relationship between the movement position information of the predetermined movement pattern and each biometric identification data,
The biometric identification data corresponding to the motion position information of the predetermined motion pattern detected by the motion detection unit is acquired from the identification data storage unit, and the biometric feature data associated with the acquired biometric identification data is stored in the biometric feature data. Extract from the biological information storage unit,
The biometric authentication device according to any one of appendices 1 to 4.

(Appendix 6)
The predetermined part of the target living body is a portion in the left hand and right hand of the target living body,
The guide image is an image in which a plurality of buttons are arranged,
Position information in the two-dimensional plane for acquiring the biometric identification data corresponds to at least one position of the plurality of buttons in the display image;
The display processing unit changes at least one of the plurality of buttons in response to detection of the predetermined operation pattern.
The biometric authentication device according to appendix 5.

(Appendix 7)
The biometric authentication device according to any one of appendices 1 to 6,
A three-dimensional sensor that sends the three-dimensional information to the information acquisition unit;
The biological information storage unit;
A biometric authentication system.

(Appendix 8)
Sequentially acquiring three-dimensional information including biological information of the target biological body,
From the acquired three-dimensional information, a predetermined motion pattern of a predetermined part of the target living body is detected,
Extracting biometric feature data specified using the motion position information of the detected predetermined motion pattern from a biometric information storage unit that stores a plurality of biometric feature data,
Generating current biological feature data of the target biological body from the acquired three-dimensional information;
Collating the extracted biometric feature data with the generated current biometric feature data of the target biometric,
A biometric authentication method.

(Appendix 9)
A detection space having a predetermined size is set at a predetermined position in the three-dimensional space indicated by the three-dimensional information;
Excluding the movement of the predetermined part of the target living body outside the detection space,
Detecting the predetermined motion pattern of the predetermined part of the target living body in the detection space;
The biometric authentication method according to appendix 8, further comprising:

(Appendix 10)
A display image including a living body image of the target living body generated from the three-dimensional information or a living body replicated image that replicates the living body image, and a guidance image that guides the target living body to operate the predetermined operation pattern. And causing the display unit to display the display image in which at least a part of the guide image is arranged in a space corresponding to the detection space in the display image.
The biometric authentication method according to appendix 9, further including:

(Appendix 11)
The biometric authentication method according to appendix 10, further comprising changing the guide image when the predetermined operation pattern is detected.

(Appendix 12)
The predetermined motion pattern is a movement of the predetermined part of the target living body with a predetermined width in a predetermined direction of a predetermined dimension in a three-dimensional space indicated by the three-dimensional information.
The operation position information of the predetermined operation pattern for specifying the biometric feature data indicates a position where the movement is performed in a two-dimensional plane other than the predetermined dimension,
The biometric information storage unit stores biometric identification data associated with each of the plurality of biometric feature data,
The biometric feature data is extracted from an identification data storage unit that stores the correspondence between the motion position information of the predetermined motion pattern and each of the biometric identification data, and the biometric data corresponding to the detected motion position information of the predetermined motion pattern. Acquiring identification data, and extracting the biometric feature data associated with the acquired biometric identification data from the biometric information storage unit;
The biometric authentication method according to any one of appendices 8 to 11.

(Appendix 13)
The predetermined part of the target living body is a portion in the left hand and right hand of the target living body,
The guide image is an image in which a plurality of buttons are arranged,
Position information in the two-dimensional plane for acquiring the biometric identification data corresponds to at least one position of the plurality of buttons in the display image;
The display image is displayed by changing at least one of the plurality of buttons according to detection of the predetermined operation pattern.
The biometric authentication method according to attachment 12.

(Appendix 14)
On at least one computer,
Sequentially acquiring three-dimensional information including biological information of the target biological body,
From the acquired three-dimensional information, a predetermined motion pattern of a predetermined part of the target living body is detected,
Extracting biometric feature data specified using the motion position information of the detected predetermined motion pattern from a biometric information storage unit that stores a plurality of biometric feature data,
Generating current biological feature data of the target biological body from the acquired three-dimensional information;
Collating the extracted biometric feature data with the generated current biometric feature data of the target biometric,
A program that lets you do that.

(Appendix 15)
Said at least one computer,
A detection space having a predetermined size is set at a predetermined position in the three-dimensional space indicated by the three-dimensional information;
Excluding the movement of the predetermined part of the target living body outside the detection space,
Detecting the predetermined motion pattern of the predetermined part of the target living body in the detection space;
The program according to appendix 14, further executing the above.

(Appendix 16)
Said at least one computer,
A display image including a living body image of the target living body generated from the three-dimensional information or a living body replicated image that replicates the living body image, and a guidance image that guides the target living body to operate the predetermined operation pattern. And causing the display unit to display the display image in which at least a part of the guide image is arranged in a space corresponding to the detection space in the display image.
The program according to supplementary note 15, further causing the above to be executed.

(Appendix 17)
Said at least one computer,
The program according to appendix 16, further causing the guide image to be changed when the predetermined operation pattern is detected.

(Appendix 18)
The predetermined motion pattern is a movement of the predetermined part of the target living body with a predetermined width in a predetermined direction of a predetermined dimension in a three-dimensional space indicated by the three-dimensional information.
The operation position information of the predetermined operation pattern for specifying the biometric feature data indicates a position where the movement is performed in a two-dimensional plane other than the predetermined dimension,
The biometric information storage unit stores biometric identification data associated with each of the plurality of biometric feature data,
The biometric feature data is extracted from an identification data storage unit that stores the correspondence between the motion position information of the predetermined motion pattern and each of the biometric identification data, and the biometric data corresponding to the detected motion position information of the predetermined motion pattern. Acquiring identification data, and extracting the biometric feature data associated with the acquired biometric identification data from the biometric information storage unit;
The program according to any one of appendices 14 to 17.

(Appendix 19)
The predetermined part of the target living body is a portion in the left hand and right hand of the target living body,
The guide image is an image in which a plurality of buttons are arranged,
Position information in the two-dimensional plane for acquiring the biometric identification data corresponds to at least one position of the plurality of buttons in the display image;
The display image is displayed by changing at least one of the plurality of buttons according to detection of the predetermined operation pattern.
The program according to appendix 18.

  (Supplementary note 20) A computer-readable recording medium in which the program according to any one of supplementary notes 14 to 19 is recorded.

  This application claims the priority on the basis of Japanese application Japanese Patent Application No. 2012-016933 for which it applied on January 30, 2012, and takes in those the indications of all here.

Claims (11)

An information acquisition unit for sequentially acquiring three-dimensional information including biological information of the target biological body;
An operation detection unit for detecting a predetermined operation pattern of a predetermined part of the target living body from the three-dimensional information acquired by the information acquisition unit;
An extraction unit that extracts biometric feature data specified by using the motion position information of the predetermined motion pattern detected by the motion detection unit from a biometric information storage unit that stores a plurality of biometric feature data;
A feature data generation unit that generates current biological feature data of the target living body from the three-dimensional information acquired by the information acquisition unit;
A collation unit for collating the biometric feature data extracted by the extraction unit with the current biometric feature data of the target living body generated by the feature data generation unit;
A biometric authentication device. The motion detector is
A detection space having a predetermined size is set at a predetermined position in the three-dimensional space indicated by the three-dimensional information;
Excluding the movement of the predetermined part of the target living body outside the detection space, and detecting the predetermined movement pattern of the predetermined part of the target living body in the detection space;
The biometric authentication device according to claim 1.   A display image including a living body image of the target living body generated from the three-dimensional information or a living body replicated image that replicates the living body image, and a guidance image that guides the target living body to operate the predetermined operation pattern. The living body according to claim 2, further comprising: a display processing unit that causes the display unit to display the display image in which at least a part of the guide image is arranged in a space corresponding to the detection space in the display image. Authentication device.   The biometric authentication device according to claim 3, wherein the display processing unit changes the induced image when the predetermined motion pattern is detected by the motion detection unit. The predetermined motion pattern is a movement of the predetermined part of the target living body with a predetermined width in a predetermined direction of a predetermined dimension in a three-dimensional space indicated by the three-dimensional information.
The operation position information of the predetermined operation pattern for specifying the biometric feature data indicates a position where the movement is performed in a two-dimensional plane other than the predetermined dimension,
The biometric information storage unit stores biometric identification data associated with each of the plurality of biometric feature data,
The extraction unit includes:
Including an identification data storage unit for storing a correspondence relationship between the movement position information of the predetermined movement pattern and each biometric identification data,
The biometric identification data corresponding to the motion position information of the predetermined motion pattern detected by the motion detection unit is acquired from the identification data storage unit, and the biometric feature data associated with the acquired biometric identification data is stored in the biometric feature data. Extract from the biological information storage unit,
The biometric authentication device according to any one of claims 1 to 4. The predetermined part of the target living body is a portion in the left hand and right hand of the target living body,
The guide image is an image in which a plurality of buttons are arranged,
Position information in the two-dimensional plane for acquiring the biometric identification data corresponds to at least one position of the plurality of buttons in the display image;
The display processing unit changes at least one of the plurality of buttons in response to detection of the predetermined operation pattern.
The biometric authentication device according to claim 5. The biometric authentication device according to any one of claims 1 to 6,
A three-dimensional sensor that sends the three-dimensional information to the information acquisition unit;
The biological information storage unit;
A biometric authentication system. Sequentially acquiring three-dimensional information including biological information of the target biological body,
From the acquired three-dimensional information, a predetermined motion pattern of a predetermined part of the target living body is detected,
Extracting biometric feature data specified using the motion position information of the detected predetermined motion pattern from a biometric information storage unit that stores a plurality of biometric feature data,
Generating current biological feature data of the target biological body from the acquired three-dimensional information;
Collating the extracted biometric feature data with the generated current biometric feature data of the target biometric,
A biometric authentication method. A detection space having a predetermined size is set at a predetermined position in the three-dimensional space indicated by the three-dimensional information;
Excluding the movement of the predetermined part of the target living body outside the detection space,
Detecting the predetermined motion pattern of the predetermined part of the target living body in the detection space;
The biometric authentication method according to claim 8 further comprising: A display image including a living body image of the target living body generated from the three-dimensional information or a living body replicated image that replicates the living body image, and a guidance image that guides the target living body to operate the predetermined operation pattern. And causing the display unit to display the display image in which at least a part of the guide image is arranged in a space corresponding to the detection space in the display image.
The biometric authentication method according to claim 9, further comprising:   The biometric authentication method according to claim 10, further comprising changing the guide image when the predetermined operation pattern is detected.

Images