DETECTION SYSTEM, DETECTION METHOD, AND PROGRAM

Abstract

A detection system (101) according to one embodiment of the present disclosure has a face detection unit (11), a region-setting unit (12), a hand detection unit (13) and an output unit (14). The face detection unit (11) detects the face of a target from an image depicting the target. The region-setting unit (12) sets a hand detection region in the periphery of a region which includes the face of the target when the face detection unit (11) has detected the face of the target. The hand detection unit (13) detects a hand present within the hand detection region from the image depicting the target. The output unit (14) outputs information pertaining to the face of the target which was detected by the face detection unit (11), and information pertaining to the hand of the target which was detected by the hand detection unit (13).

Description

DETECTION SYSTEM, DETECTION METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM

[0001] The present disclosure relates to a detection system, a detection method, and a non-transitory computer-readable medium.

[0002] Various techniques have been disclosed for acquiring biometric information of users at immigration inspections, etc. For example, Patent Document 1 describes a personal identification input device that captures a face image and a fingerprint image using a camera and a fingerprint sensor, respectively.

[0003] Japanese Patent Application Laid-Open No. 2004-062846

[0004] In the personal identification device described in Patent Document 1, the person to be identified, i.e., the person whose face image and fingerprint image are to be captured, needs to pay attention to both the camera that captures the face image and the fingerprint sensor that captures the fingerprint image, which causes the subject to feel annoyed.

[0005] This disclosure has been made to solve such problems, and aims to provide a detection system, a detection method, and a non-transitory computer-readable medium that are capable of acquiring biometric information that can be authenticated while reducing the burden on the subject.

[0006] A detection system according to one aspect of the present disclosure includes a face detection unit, an area setting unit, a hand detection unit, and an output unit. The face detection unit detects the face of a subject from an image of the subject. When the face detection unit detects the face of the subject, the area setting unit sets a hand detection area around an area including the face of the subject. The hand detection unit detects hands present within the hand detection area from the image of the subject. The output unit outputs information about the face of the subject detected by the face detection unit and information about the hand of the subject detected by the hand detection unit.

[0007] In a detection method according to one aspect of the present disclosure, a computer executes the following processes: the computer detects the face of a subject from an image of the subject; when the computer detects the face of the subject, the computer sets a hand detection region around an area including the face of the subject; the computer detects a hand present within the hand detection region; and the computer outputs information about the detected face and information about the detected hand.

[0008] A non-transitory computer-readable medium according to one aspect of the present disclosure is a non-transitory computer-readable medium storing a program that causes a computer to execute the following processes: The computer detects the face of a subject from an image of the subject. When the computer detects the face of the subject, the computer sets a hand detection area around an area including the face of the subject. The computer detects a hand present within the hand detection area. The computer outputs information about the detected face and information about the detected hand.

[0009] 1 is a block diagram showing the configuration of a detection system according to a first embodiment. FIG. 2 is a flowchart showing the processing of the detection system according to the first embodiment. FIG. 3 is a block diagram showing the configuration of a detection system according to a second embodiment. FIG. 4 is a block diagram showing the configuration of a detection device according to the second embodiment. FIG. 5 is a flowchart showing the processing of the detection device according to the second embodiment. FIG. 6 is a schematic diagram illustrating an example of an image of a subject according to the second embodiment. FIG. 7 is a schematic diagram illustrating an example of an image of a subject according to the second embodiment. FIG. 8 is a schematic diagram illustrating an example of an image of a subject according to the second embodiment. FIG. 9 is a block diagram showing the configuration of a detection device according to a third embodiment. FIG. 10 is a flowchart showing the processing of the detection system according to the third embodiment. FIG. 11 is a flowchart showing the processing of the detection system according to a fourth embodiment. FIG. 12 is a block diagram illustrating an example of the hardware configuration of a computer.

[0010] First Embodiment (Configuration of Detection System) A detection system according to a first embodiment will be described in detail below with reference to the drawings. Fig. 1 is a block diagram showing the configuration of the detection system according to the first embodiment.

[0011] The detection system 101 according to this embodiment detects the face and hands of a subject from an image of the subject, and outputs information relating to the detected face and information relating to the detected hands. The detection system 101 includes a face detection unit 11, a region setting unit 12, a hand detection unit 13, and an output unit 14.

[0012] The face-related information may be, for example, a portion of an image of the subject that corresponds to the detected face, i.e., an image of the detected face, or may be a feature extracted from the image.

[0013] The hand-related information may be, for example, a portion of an image of the subject that corresponds to the detected hand, i.e., an image of the detected hand, or may be a feature extracted from the image.

[0014] The face detection unit 11 detects the face of the subject from an image of the subject. When the face detection unit detects the face of the subject, the area setting unit 12 sets a hand detection area around an area including the face of the subject. When the hand detection area is set, the detection system 101 may guide the subject to assume a posture in which the hand is reflected in the hand detection area. The hand detection unit 13 detects hands present within the hand detection area from an image of the subject. The output unit 14 outputs information about the face detected by the face detection unit 11 and information about the hand detected by the hand detection unit 13.

[0015] (Processing of the Detection System) Next, the processing, i.e., the method, of the detection system according to embodiment 1 will be described in detail with reference to the drawings. Fig. 2 is a flowchart showing the processing of the detection system according to embodiment 1. Note that in the following description, Fig. 1 will be referred to as appropriate.

[0016] First, the face detection unit 11 detects the face of the subject from an image of the subject (step S101). The face detection unit 11 supplies information about the detected face of the subject to the area setting unit 12 and the output unit 14.

[0017] Next, the region setting unit 12 sets a hand detection region around the region including the subject's face (step S102). The region setting unit 12 supplies information about the set hand detection region to the hand detection unit 13.

[0018] Next, the hand detection unit 13 detects the hand present in the hand detection area (step S103). The hand detection unit 13 supplies information about the detected hand of the subject to the area setting unit 12 and the output unit 14.

[0019] Finally, the output unit 14 outputs information about the face and information about the hands, and the detection system 101 ends the series of processes.

[0020] As described above, the detection system 101 according to this embodiment detects the face of the subject from an image of the subject, and detects the subject's hands from a hand detection area set around the area including the subject's face.

[0021] With this configuration, the subject does not need to pay attention to multiple image capture devices. Therefore, the detection system 101 can reduce the subject's discomfort. In other words, the detection system 101 according to this embodiment can reduce the subject's burden.

[0022] <Second Embodiment> (Configuration of Detection System) Hereinafter, a detection system according to the second embodiment will be described in detail with reference to the drawings. First, the configuration of the detection system according to the second embodiment will be described. Fig. 3 is a block diagram showing the configuration of the detection system according to the second embodiment.

[0023] The detection system 102 is a system that performs biometric authentication of subjects who use facilities such as airports and ports. The detection system 102 mainly comprises a detection device 1, an image capture device 2, a display device 3, and an authentication device 4. The detection device 1 and the authentication device 4 are connected to each other so that they can communicate with each other via a network N1. The network N1 may be a telephone line, a wide area network, or a local area network.

[0024] The detection device 1 is installed, for example, at an airport, and acquires biometric information of a subject S who is a passenger. After acquiring the biometric information of the subject S, the detection device 1 supplies the acquired biometric information to the authentication device 4. Upon receiving the biometric information from the detection device 1, the authentication device 4 authenticates the received biometric information. After performing the authentication, the authentication device 4 supplies information regarding the result of the authentication to the detection device 1. Upon receiving information regarding the result of the authentication from the authentication device 4, the detection device 1 executes processing such as granting permission for the subject S to pass in accordance with this information.

[0025] More specifically, the detection device 1 acquires an image of the subject S, and detects information about the face of the subject S and information about the hands of the subject S from the acquired image as biometric information for authenticating the subject S. Here, the detection system 102 according to this embodiment outputs an image of the face of the subject S as information about the face of the subject S. Furthermore, the detection system 102 according to this embodiment outputs an image of the hand of the subject S as information about the hand of the subject S.

[0026] However, the information about the subject's face and the information about the hands output by the detection system according to this disclosure are not limited to an image of the subject's face and an image of the subject's hands, respectively. For example, the detection system according to this disclosure may output facial features of the subject as information about the subject's face. The detection system according to this disclosure may also output an image or features of the subject's irises. The detection system according to this disclosure may also output hand features of the subject as information about the subject's hands. The detection system according to this disclosure may also output an image or features of the subject's fingerprints. The detection system according to this disclosure may also output an image or features of the subject's palm veins. In other words, the information about the subject's face and the information about the hands output by the detection system according to this disclosure may be information that can authenticate the subject.

[0027] The photographing device 2 photographs the subject S based on control from the photographing control unit 16. Then, the photographing device 2 supplies the photographed image of the subject S to the photographing control unit 16. Note that, although the photographing device 2 according to this embodiment photographs the subject S at predetermined time intervals, the configuration of the photographing device 2 is not limited to this. For example, the photographing device 2 may be configured to photograph the subject S every time the detection device 1 completes a predetermined process. Also, although the photographing device 2 according to this embodiment is configured with one camera, the configuration of the photographing device 2 is not limited to this and may be configured with, for example, two or more cameras.

[0028] The image capturing device 2 may be a camera that captures images by detecting light in the visible light range, or may be a camera that captures images by detecting light in the non-visible light range. For example, if the information about the subject S's hand includes an image or feature values ​​of the veins in the palm of the subject S's hand, the image capturing device 2 may capture images of the subject S by detecting light in the infrared range.

[0029] The display device 3 displays a guide image to the subject S. For example, the display device 3 may display an image notifying the subject S that an image will be taken to acquire biometric information. Furthermore, when a hand detection area, which will be described later, is set, the display device 3 may display a reference posture image to prompt the subject S to take a predetermined posture.

[0030] More specifically, the display device 3 may acquire from the detection device 1 an image indicating the range of the hand detection area and an image of the subject S. The display device 3 may display the images superimposed on each other. Then, the display device 3 may notify the subject S to assume a posture that causes his or her hand to be reflected in the hand detection area.

[0031] Next, the detection device 1 will be further described with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of the detection device 1 according to the second embodiment. The detection device 1 mainly includes a face detection unit 11, an area setting unit 12, a hand detection unit 13, an output unit 14, an image quality determination unit 15, and an image capture control unit 16. These components of the detection device 1 are appropriately connected to each other so that they can communicate with each other, in order for the detection device 1 to perform the functions described in this disclosure.

[0032] The photographing control unit 16 controls the photographing device 2. For example, the photographing control unit 16 may determine the timing at which the photographing device 2 starts photographing, or may determine the timing at which the photographing device 2 ends photographing. The photographing control unit 16 acquires an image photographed by the photographing device 2 and supplies the image to the face detection unit 11.

[0033] For example, the photographing control unit 16 may cause the photographing device 2 to start photographing when a sensor (not shown) detects that the subject is within the photographing range of the photographing device 2. Furthermore, the photographing control unit 16 may cause the photographing device 2 to end photographing when the detection device 1 outputs an image of the subject's face and an image of the hand. With such a configuration of the detection device 1, the time that the subject needs to pay attention to the photographing device 2 is shortened, thereby reducing the burden on the subject.

[0034] The face detection unit 11 detects the face of the subject from an image of the subject. More specifically, the face detection unit 11 acquires an image of the subject from the imaging control unit 16 and detects the face of the subject from the image.

[0035] Here, detecting a face refers to identifying a section that includes the subject's face from within an image of the subject. The face detection unit 11 then supplies the section to the image quality determination unit 15 as an image of the subject's face.

[0036] The face detection unit 11 may detect the subject's face from the acquired image by, for example, dividing the acquired image into multiple sections and determining whether each section contains part or all of the subject's face. The face detection unit 11 may also have, for example, artificial intelligence (AI) that has learned images of human faces. The face detection unit 11 may then load the acquired image into the AI ​​and have the AI ​​detect the subject's face. In other words, the face detection unit 11 may use various methods capable of detecting the subject's face.

[0037] When the face detection unit 11 detects the face of the subject from an image of the subject, it supplies the image of the subject and information about the position of the face in the image to the area setting unit 12. Then, the face detection unit 11 supplies the image of the detected face to the image quality determination unit 15.

[0038] However, the information regarding the position of the face in the image may be, for example, coordinate information of the section in the image in which the face is reflected.Furthermore, the information regarding the position of the face in the image may be, for example, image data in which the boundary line of the section in which the face is reflected is superimposed on the image.

[0039] If the face of the subject cannot be detected from the captured image of the subject, the face detection unit 11 may acquire a new image of the subject from the imaging control unit 16. Then, the face detection unit 11 may continue acquiring images until the subject's face is detected. Furthermore, the face detection unit 11 may continue acquiring images from the imaging control unit 16 and continuing to attempt face detection until the output unit 14, which will be described later, outputs information about the subject's face and information about their hands.

[0040] The region setting unit 12 acquires an image of the subject and information about the position of the face in the image from the face detection unit 11. Then, based on the acquired information about the position of the face in the image, the region setting unit 12 sets a hand detection region around the region including the face of the subject.

[0041] The hand detection area here refers to an area set in an image of the subject, and the hand detection unit 13 (described later) detects the subject's hand within the hand detection area. In other words, the area setting unit 12 limits the range in which the hand detection unit 13 detects the subject's hand to the periphery of an area including the subject's face. With this configuration, the detection device 1 can prevent the hand of a person other than the subject that appears in the acquired image from being mistakenly detected as the subject's hand.

[0042] Furthermore, the region setting unit 12 may set, as the hand detection region, a region that exists within a range of a predetermined width and a predetermined height, with the position of the face as the center, for example.

[0043] Here, when a hand detection area is set, detection system 102 may guide the subject to assume a posture that allows the hand to be reflected in the hand detection area. For example, when a hand detection area is set, detection system 102 may display an image of the subject and the hand detection area in a superimposed manner on display device 3. Then, detection system 102 may guide the subject to assume a posture that allows the hand to be present in the hand detection area displayed on display device 3.

[0044] The hand detection unit 13 detects a hand present within a hand detection area from an image captured by the imaging device. More specifically, the hand detection unit 13 acquires an image of the subject and position information of the hand detection area from the area setting unit 12. Then, the hand detection unit 13 detects the subject's hand present within the hand detection area in the image.

[0045] Here, detecting hands refers to identifying a section including the subject's hands from an image of the subject. The hand detection unit 13 then supplies the section to the image quality determination unit 15 as an image of the subject's hands.

[0046] The hand detection unit 13 may, for example, divide the acquired image into multiple sections and determine whether each section within the hand detection area contains part or all of the subject's hand, thereby detecting the subject's hand from within the hand detection area of ​​the acquired image. The hand detection unit 13 may also have, for example, artificial intelligence that has learned images of human hands. The hand detection unit 13 may then load the acquired image into the artificial intelligence and have the artificial intelligence detect the subject's hand. In other words, the hand detection unit 13 may use various methods capable of detecting the subject's hand.

[0047] When the hand detection unit 13 detects the subject's hand within the hand detection area, it supplies an image of the detected hand to the image quality determination unit 15. Note that, if the subject's face cannot be detected from the image of the subject, the face detection unit 11 may acquire a new image of the subject from the imaging control unit 16. Then, the face detection unit 11 may continue acquiring images until the subject's face is detected. Furthermore, the face detection unit 11 may continue acquiring images from the imaging control unit 16 and continuing to attempt face detection until the output unit 14, which will be described later, outputs information about the subject's face and information about the hand.

[0048] The image quality determination unit 15 acquires an image of the subject's face from the face detection unit 11, and acquires an image of the subject's hand from the hand detection unit 13. The image quality determination unit 15 determines whether the acquired image of the subject's face and the image of the subject's hand have been captured with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication.

[0049] The image quality determination unit 15 may evaluate, for example, the degree of blurring or the CNR (Contrast to Noise Ratio) of the acquired image. If the degree of blurring or the CNR of the acquired image is smaller than a predetermined threshold, the image quality determination unit 15 may determine that the acquired image has been captured with an image quality that allows extraction of quality features suitable for biometric authentication. Note that the image quality determination unit 15 may determine the image quality of the acquired image using evaluation criteria other than the degree of blurring or the CNR of the acquired image.

[0050] Furthermore, the image quality determination unit 15 may determine whether the image of the subject's face and the image of the subject's hands detected from one image have been captured with an image quality that allows extraction of features of a quality suitable for biometric authentication. That is, the image quality determination unit 15 may detect the image of the subject's face acquired from the face detection unit 11 and the image of the subject's hands acquired from the hand detection unit 13 from the same image.

[0051] With this configuration, the detection system 102 can indicate that the acquired face image and hand image are related, making it easier for the detection system 102 to ensure that the detected face image and hand image are of the same person.

[0052] Furthermore, if the image quality determination unit 15 determines that the detected face image and hand image of the subject are not captured with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, the image quality determination unit 15 may notify the image capture control unit 16 of this fact. In this case, the image capture control unit 16 may perform image processing on the captured image of the subject before supplying it to the face detection unit 11 and the hand detection unit 13. The image processing here may be, for example, a process of adjusting the color tone of the image. The image processing may also be a process of applying a signal obtained by converting the image to a low-pass filter.

[0053] The output unit 14 outputs information about the face detected by the face detection unit 11 and information about the hands detected by the hand detection unit 13. More specifically, when the image quality determination unit 15 determines that the image of the face and the image of the hand of the subject have been captured with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, the output unit 14 outputs the image of the face as information about the face of the subject to the authentication device 4. Then, the output unit 14 outputs the image of the hand as information about the hand of the subject to the authentication device 4.

[0054] When the output unit 14 outputs information about the face detected by the face detection unit 11 and information about the hand detected by the hand detection unit 13, the output unit 14 may notify the shooting control unit 16 that this information has been output. In this case, the output unit 14 may also notify the face detection unit 11, the area setting unit 12, and the hand detection unit 13 that this information has been output.

[0055] (Processing of the detection system) Next, the processing of the detection system, i.e., the detection method, according to the second embodiment will be described in detail with reference to the drawings. Fig. 5 is a flowchart showing the processing of the detection system according to the second embodiment. More specifically, Fig. 5 is a flowchart showing the processing of the detection device 1 according to the second embodiment. In the following description, Fig. 4 will be referred to as appropriate.

[0056] First, the face detection unit 11 acquires an image of the subject (step S201). More specifically, the face detection unit 11 acquires an image of the subject captured by the imaging device 2 from the imaging control unit 16. FIG. 6 is a schematic diagram showing an example of an image acquired by the face detection unit 11. The face detection unit 11 acquires an image P in which the subject S appears, as shown in FIG. 6. Note that the face detected by the detection device 1 according to this embodiment is the face F of the subject S shown in FIG. 6, and the hand detected by the detection device 1 according to this embodiment is the hand H of the subject S shown in FIG. 6.

[0057] Next, the face detection unit 11 detects the face of the subject (step S202). In step S202, the face detection unit 11 may identify a section FA including the face of the subject S, for example, as shown in FIG. 7, and supply the section FA as an image of the face of the subject S.

[0058] In step S202, if the face detection unit 11 has not detected the face of the subject, the detection device 1 executes step S201 again. That is, the face detection unit 11 repeatedly executes steps S201 and S202 until the face of the subject is detected. In step S202, if the face detection unit 11 detects the face of the subject (step S203: YES), the detection device 1 proceeds to step S203.

[0059] Next, the region setting unit 12 sets a hand detection region (step S203). More specifically, the region setting unit 12 sets the hand detection region around the region including the subject's face. Here, the region around the region including the subject's face may be used to mean the region around a section FA including the subject's face in an image of the subject. For example, as shown in FIG. 9 , the region setting unit 12 may set the hand detection region DA so that it is adjacent to the section FA including the face of the subject S.

[0060] Next, the hand detection unit 13 detects a hand present in the hand detection area (step S204). In step S205, the hand detection unit 13 may identify a section HA including the hand of the subject S, as shown in the figure, and supply the section HA as an image of the hand of the subject S.

[0061] In step S204, if the hand detection unit 13 has not detected the subject's hand (step S204: NO), the detection device 1 executes step S201 again. That is, the detection device 1 repeatedly executes steps S201 to S204 until the detection device 1 detects the subject's hand. In step S204, if the hand detection unit 13 detects the subject's hand (step S204: YES), the detection device 1 proceeds to step S205.

[0062] Next, the image quality determining unit 15 determines whether the detected face image and hand image each have an image quality suitable for biometric authentication (step S205).

[0063] If the detected face image and hand image do not have image quality suitable for biometric authentication in step S205 (step S205 NO), the detection device 1 executes step S201 again. That is, the detection device 1 repeatedly executes steps S201 to S205 until the detected face image and hand image have image quality suitable for biometric authentication in step S205. If the detected face image and hand image have image quality suitable for biometric authentication in step S205 (step S205 YES), the detection device 1 proceeds to step S206.

[0064] Finally, the output unit 14 outputs the detected face image and hand image (step S206), and the series of processes of the detection device 1 ends. Note that, at the timing of executing step S208, the output unit 14 may notify the imaging control unit 16 that step S208 has been executed.

[0065] As described above, the detection system 102 according to this embodiment detects the face and hands of a subject from an image of the subject. The detection system 102 according to this disclosure can be implemented as long as the subject can be photographed using at least the photographing device 2. With this configuration, the subject does not need to pay attention to two or more devices, namely, a photographing device that photographs the face image and a photographing device that photographs the hand image. Therefore, the detection system 101 can reduce the burden on the subject. Furthermore, after detecting the subject's face, the detection system 102 according to this embodiment sets a hand detection area around an area including the subject's face. The detection system 102 then detects hands present within the hand detection area. With this configuration, it is possible to prevent the hands of a person other than the subject from being mistakenly detected as the subject's hands in an image.

[0066] Third Embodiment (Configuration of Detection System) Hereinafter, a detection system according to the third embodiment will be described in detail with reference to the drawings. First, the configuration of the detection system according to the third embodiment will be described.

[0067] The detection system 102 according to the second embodiment outputs an image of the subject's face and an image of the subject's hands as information about the subject's face and information about the subject's hands, respectively. In contrast, the detection system 103 according to the third embodiment outputs feature amounts of the subject's face and feature amounts of the subject's hands as information about the subject's face and information about the subject's hands, respectively.

[0068] Similar to the detection system 102 according to the second embodiment, the detection system 103 according to the third embodiment includes a detection device 1, an image capturing device 2, a display device 3, and an authentication device 4. That is, the detection system 103 according to the third embodiment has a configuration similar to that shown in FIG.

[0069] 10 is a block diagram showing the configuration of a detection device 1 according to embodiment 3. The detection system 103 according to embodiment 3 differs from the detection system 102 according to embodiment 2 in that it includes a feature extraction unit 17 and a feature determination unit 18 instead of the image quality determination unit 15.

[0070] The feature extraction unit 17 extracts feature amounts from the image of the subject's face and the image of the subject's hands. More specifically, the feature extraction unit 17 acquires the image of the subject's face from the face detection unit 11 and acquires the image of the subject's hands from the hand detection unit 13. The feature extraction unit 17 then extracts feature amounts from the acquired images of the subject's face and hands. The feature extraction unit 17 supplies the extracted feature amounts to the feature determination unit 18.

[0071] The feature amount referred to here refers to data obtained by converting image data using various methods, and refers to data that can be used to authenticate a target person by comparing the data. For example, the feature amount may be expressed as a numerical value or in a format other than a numerical value. In other words, the feature amount may be data in a format that can authenticate a target person.

[0072] The feature extraction unit 17 may also extract features of the subject's face and hands from an image of the subject's face and an image of the subject's hands detected from a single image. With this configuration, the detection system 103 can indicate that the acquired face features and hand features are related to each other. That is, the detection system 103 can more easily ensure that the detected face features and hand features belong to the same person.

[0073] The feature amount determination unit 18 determines whether the feature amount extracted by the feature amount extraction unit 17 has a quality suitable for biometric authentication. The feature amount determination unit 18 may, for example, evaluate the standard deviation of the extracted feature amount. That is, the feature amount determination unit 18 may acquire multiple feature amounts and calculate their standard deviation. Then, if the standard deviation is equal to or less than a predetermined threshold, the extracted feature amount may be determined to have a quality suitable for biometric authentication. However, the feature amount determination unit 18 may evaluate the quality of the feature amount using an evaluation criterion other than the standard deviation.

[0074] When the feature determination unit 18 determines that the feature extracted by the feature extraction unit 17 has a quality suitable for biometric authentication, the feature determination unit 18 outputs the feature to the output unit 14. In this case, the output unit 14 that has acquired the feature outputs the feature as information about the face and information about the hand of the subject.

[0075] Furthermore, when the feature amount determination unit 18 determines that the feature amount extracted by the feature amount extraction unit 17 is not of a quality suitable for biometric authentication, the feature amount determination unit 18 may notify the face detection unit 11, the area setting unit 12, and the hand detection unit 13 of this fact. In this case, the face detection unit 11, the area setting unit 12, and the hand detection unit 13 may acquire a new image and execute the process of detecting the face and hands of the subject again.

[0076] (Processing of the Detection System) Next, the processing, i.e., the method, of the detection system according to the third embodiment will be described in detail with reference to the drawings. Fig. 11 is a flowchart showing the processing of the detection system according to the third embodiment. In the following description, Fig. 10 will be referred to as appropriate.

[0077] However, steps S301 to S304 shown in Fig. 11 are the same as steps S201 to S204 described in the second embodiment, and therefore will not be described here. In other words, hereafter, the part corresponding to Fig. 12, that is, the subsequent processing of the detection device 1 according to the third embodiment when the determination in step S304 shown in Fig. 11 is YES, will be described.

[0078] If the hand detection unit 13 detects the subject's hand (YES in step S304), the feature extraction unit 17 detects features from the detected face image and hand image (step S305).Then, the feature determination unit 18 determines whether the extracted features have a quality suitable for biometric authentication (step S306).

[0079] If the extracted feature quantity is not of a quality suitable for biometric authentication (NO in step S306), the detection device 1 again executes step S301 shown in Fig. 11. In other words, the detection device 1 repeatedly executes steps S301 to S306 until the extracted feature quantity has a quality suitable for biometric authentication.

[0080] If the extracted feature amount has a quality suitable for biometric authentication (YES in step S306), the output unit 14 outputs the extracted feature amount (step S307), and the series of processes of the detection device 1 ends. Note that, at the timing of executing step S307, the output unit 14 may notify the imaging control unit 16 that step S307 has been executed.

[0081] As described above, the detection system 103 according to this embodiment extracts feature amounts of the subject's face and hands from an image of the subject. The detection system 103 according to this embodiment continues to capture the subject's image until it extracts feature amounts of the subject's face and hands and outputs feature amounts of a quality suitable for biometric authentication.

[0082] With this configuration, the detection system according to the present embodiment can contribute to improving the authentication system for biometric information. Therefore, the detection system according to the present embodiment can provide a detection system, a detection method, and a detection program that acquire biometric information that can be authenticated with high accuracy while reducing the burden on the subject.

[0083] <Fourth Embodiment> (Configuration of Detection System) Hereinafter, a detection system according to the fourth embodiment will be described in detail with reference to the drawings. FIG. 13 is a block diagram showing the configuration of the detection system according to the fourth embodiment. The detection system 104 according to the fourth embodiment differs from the above-described embodiments in that it includes a light irradiation unit 5. The detection device 1 according to this embodiment may have the same configuration as that of the second embodiment. The detection device 1 according to this embodiment may also have the same configuration as that of the third embodiment.

[0084] The light irradiation unit 5 irradiates at least the hand detection area with light containing a predetermined pattern image. For example, the light irradiation unit 5 may irradiate only the hand detection area with light. Alternatively, the light irradiation unit 5 may irradiate the entire body of the subject with light. However, a pattern image refers to an image in which many predetermined patterns are displayed. If light containing such an image is irradiated, it becomes difficult to photograph the irradiated area.

[0085] Furthermore, the light irradiation unit 5 blinks the light to be irradiated at a predetermined timing. That is, the light irradiation unit 5 switches between a light irradiation state and a light non-irradiation state at a predetermined timing. However, the predetermined timing is shared with the photographing device 2 or the photographing control unit 16.

[0086] Here, the image capturing device 2 captures an image of the subject at a timing when the light emitting unit 5 is not emitting light. Therefore, the image capturing device 2 is not hindered from capturing an image by the light emitting unit 5.

[0087] In this way, by sharing the timing of not irradiating light with the photographing device 2 or the photographing control unit 16, the light irradiating unit 5 can suppress photographing by photographing devices other than the photographing device 2 without suppressing photographing of the subject by the photographing device 2. As a result, the light irradiating unit 5 can suppress, for example, surreptitious photography by a malicious third party.

[0088] Furthermore, light irradiation unit 5 may acquire information about the hand detection area from detection device 1. Then, the light irradiation area may be determined based on the acquired information about the hand detection area. However, the information about the hand detection area may also be information about the position of the hand detection area.

[0089] For example, the information about the hand detection region may be coordinate information about the hand detection region. When the acquired information about the hand detection region is coordinate information about the hand detection region, the light irradiation unit 5 irradiates light onto the region corresponding to the acquired coordinate information.

[0090] With this configuration, the detection system 104 can prevent a malicious third party from secretly capturing an image of the subject's face and hands at the same time. Therefore, the detection system 104 according to this embodiment can provide a detection system, a detection method, and a detection program that can acquire biometric information that can be authenticated while reducing the burden on the subject under highly secure conditions.

[0091] <Example of Hardware Configuration> Hereinafter, a case will be described in which each functional configuration of the detection system or detection device in this disclosure is realized by a combination of hardware and software.

[0092] FIG. 14 is a block diagram illustrating an example of a hardware configuration of a computer. The management device in this disclosure can realize the above-described functions by a computer 200 including the hardware configuration shown in the figure. The computer 200 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 200 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 200 can realize desired functions by installing a predetermined program.

[0093] The computer 200 has a bus 202, a processor 204, a memory 206, a storage device 208, an input / output interface 210 (an interface is also called an I / F (Interface)), and a network interface 212. The bus 202 is a data transmission path through which the processor 204, the memory 206, the storage device 208, the input / output interface 210, and the network interface 212 transmit and receive data to and from each other. However, the method of interconnecting the processor 204 and the like is not limited to bus connection.

[0094] The processor 204 is a processor such as a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), etc. The memory 206 is a main storage device realized using a random access memory (RAM) or the like.

[0095] The storage device 208 is an auxiliary storage device realized using a hard disk, a solid-state drive (SSD), a memory card, a read-only memory (ROM), etc. The storage device 208 stores programs for realizing desired functions. The processor 204 reads the programs into the memory 206 and executes them to realize the functional components of each device.

[0096] The input / output interface 210 is an interface for connecting the computer 200 with input / output devices. For example, the input / output interface 210 is connected to an input device such as a keyboard and an output device such as a display device.

[0097] The network interface 212 is an interface for connecting the computer 200 to a network.

[0098] The program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include RAM, ROM, flash memory, SSD or other memory technologies, CD-ROM, DVD (digital versatile disc), Blu-ray (registered trademark) disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may also be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0099] While this disclosure has been described above in accordance with the above-described embodiments, this disclosure is not limited to the configurations of the above-described embodiments, and naturally includes various modifications, alterations, and combinations that may be made by a person skilled in the art within the scope of the claims of the present application.

[0100] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A detection system comprising: a face detection unit that detects the face of a subject from an image captured of the subject; an area setting unit that sets a hand detection area around an area including the face of the subject when the face detection unit detects the face of the subject; a hand detection unit that detects a hand present within the hand detection area from the image captured of the subject; and an output unit that outputs information about the face of the subject detected by the face detection unit and information about the hand of the subject detected by the hand detection unit. (Supplementary Note 2) The detection system according to Supplementary Note 1, wherein the output unit outputs an image of the face of the subject as the information about the face of the subject, and outputs an image of the hand of the subject as the information about the hand of the subject. (Supplementary Note 3) The detection system according to Supplementary Note 2, further comprising an image quality determination unit that determines whether the image of the subject's face and the image of the subject's hands have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, and when the image quality determination unit determines that the image of the subject's face and the image of the subject's hands have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, the output unit outputs the image of the face as information related to the subject's face and the image of the hand as information related to the subject's hand. (Supplementary Note 4) The detection system according to Supplementary Note 3, wherein the image quality determination unit determines whether the image of the subject's face and the image of the subject's hands detected from a single image have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication. (Supplementary Note 5) The detection system described in any one of Supplementary Notes 1 to 4, further comprising a feature extraction unit that extracts features from the image of the subject's face and the image of the subject's hands, respectively, and the output unit outputs the feature extracted from the image of the subject's face as information about the subject's face, and outputs the feature extracted from the image of the subject's hands as information about the subject's hands.(Supplementary Note 6) The detection system according to Supplementary Note 5, further comprising a feature determination unit that determines whether the feature extracted by the feature extraction unit is of a quality suitable for biometric authentication, and when the feature determination unit determines that the feature is of a quality suitable for biometric authentication, the output unit outputs the feature as information related to the face or hand of the subject. (Supplementary Note 7) The detection system according to any one of Supplements 1 to 6, further comprising a light irradiation unit that irradiates at least the hand detection area with light including a predetermined pattern image. (Supplementary Note 8) The detection system according to any one of Supplements 1 to 7, further comprising a display unit that displays a reference posture image to encourage the subject to assume a predetermined posture when the hand detection area is set. (Supplementary Note 9) A detection method, wherein a computer detects the face of the subject from an image captured of the subject, and when the face of the subject is detected, sets a hand detection area around an area including the face of the subject, detects hands present in the hand detection area, and outputs information related to the detected face and information related to the detected hands. (Supplementary Note 10) The detection method according to Supplementary Note 9, wherein the output unit outputs an image of the subject's face as information about the subject's face, and outputs an image of the subject's hand as information about the subject's hand. (Supplementary Note 11) The detection method according to Supplementary Note 10, further comprising an image quality determination unit that determines whether the image of the subject's face and the image of the subject's hand have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, wherein when the image quality determination unit determines that the image of the subject's face and the image of the subject's hand have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication, the output unit outputs the image of the face as information about the subject's face, and outputs the image of the hand as information about the subject's hand. (Supplementary Note 12) The detection method according to Supplementary Note 11, wherein the image quality determination unit determines whether the image of the subject's face and the image of the subject's hand detected from a single image have been taken with an image quality that allows extraction of feature quantities of a quality suitable for biometric authentication.(Supplementary Note 13) The detection method according to any one of Supplementary Notes 9 to 12, further comprising: a feature extraction unit that extracts feature amounts from an image of the face and an image of the hand of the subject, wherein the output unit outputs the feature amount extracted from the image of the face of the subject as information about the face of the subject, and outputs the feature amount extracted from the image of the hand of the subject as information about the hand of the subject. (Supplementary Note 14) The detection method according to claim 13, further comprising: a feature determination unit that determines whether the feature amount extracted by the feature extraction unit is of a quality suitable for biometric authentication, wherein if the feature determination unit determines that the feature amount is of a quality suitable for biometric authentication, the output unit outputs the feature amount as information about the face or hand of the subject. (Supplementary Note 15) The detection method according to any one of Supplementary Notes 9 to 14, further comprising: a light irradiation unit that irradiates light including a predetermined pattern image onto at least the hand detection region. (Supplementary Note 16) The detection method according to any one of Supplementary Notes 9 to 15, further comprising a display unit that displays a reference posture image to prompt the subject to assume a predetermined posture when the hand detection area is set. (Supplementary Note 17) A non-transitory computer-readable medium having stored thereon a program that causes a computer to execute a method of detecting a face of the subject from an image of the subject, setting a hand detection area around an area including the subject's face when the face of the subject is detected, detecting hands present within the hand detection area, and outputting information related to the detected face and information related to the detected hands.

[0101] This application claims priority based on Japanese Patent Application No. 2022-085727, filed on May 26, 2022, the disclosure of which is incorporated herein in its entirety.

[0102] REFERENCE SIGNS LIST 1 detection device 2 photography device 3 display device 4 authentication device 5 light irradiation unit 11 face detection unit 12 area setting unit 13 hand detection unit 14 output unit 15 image quality determination unit 16 photography control unit 17 feature amount extraction unit 18 feature amount determination unit 101 to 104 detection system 200 computer 202 bus 204 processor 206 memory 208 storage device 210 input / output interface 212 network interface

Claims

1. A face detection means for detecting a face of a subject from an image of the subject; an area setting means for setting a hand detection area around an area including the face of the subject when the face detection means detects the face of the subject; a hand detection means for detecting a hand present within the hand detection area from an image of the subject; and an output means for outputting information relating to the face of the subject detected by the face detection means and information relating to the hand of the subject detected by the hand detection means. Detection system.

2. the output means outputs an image of the subject's face as the information regarding the subject's face, and outputs an image of the subject's hand as the information regarding the subject's hand. The detection system of claim 1 .

3. further comprising an image quality determination unit that determines whether the image of the face of the subject and the image of the hand of the subject are captured with an image quality that allows extraction of a feature quantity of a quality suitable for biometric authentication; When the image quality determination means determines that the image of the face of the subject and the image of the hand of the subject have been captured with an image quality capable of extracting features of a quality suitable for biometric authentication, the output means outputs the image of the face as information related to the face of the subject, and outputs the image of the hand as information related to the hand of the subject. The detection system of claim 2 .

4. the image quality determination means determines whether or not the face image of the subject and the hand image of the subject detected from one image have been captured with an image quality capable of extracting a feature quantity of a quality suitable for biometric authentication; The detection system of claim 3 .

5. The image processing device further includes a feature extraction unit for extracting features from the face image and the hand image of the subject, the output means outputs, as the information regarding the face of the subject, a feature extracted from an image of the face of the subject, and outputs, as the information regarding the hand of the subject, a feature extracted from an image of the hand of the subject. A detection system according to any one of claims 1 to 4.

6. The biometric authentication device further includes a feature determining unit that determines whether the feature extracted by the feature extracting unit has a quality suitable for biometric authentication, When the feature amount determination means determines that the feature amount has a quality suitable for biometric authentication, the output means outputs the feature amount as information about the subject's face or hand. The detection system of claim 5 .

7. The hand detection device further includes a light irradiation unit that irradiates light including a predetermined pattern image onto at least the hand detection area. A detection system according to any one of claims 1 to 4.

8. a display unit configured to display a reference posture image for encouraging the subject to take a predetermined posture when the hand detection area is set, A detection system according to any one of claims 1 to 4.

9. The computer Detecting a face of a subject from an image of the subject; When the face of the subject is detected, a hand detection area is set around an area including the face of the subject; Detecting a hand present within the hand detection area; outputting information about the detected face and information about the detected hands; Detection methods.

10. Detecting a face of a subject from an image of the subject; When the face of the subject is detected, a hand detection area is set around an area including the face of the subject; Detecting a hand present within the hand detection area; outputting information about the detected face and information about the detected hands; program.