Methods for acquiring biometric data

Abstract

This system enables more efficient generation of biometric data used for biometric authentication and more efficient detection of anomalies in that data. [Solution] The method for acquiring biometric data involves acquiring first information in which a biometric part of the person to be authenticated is imaged, executing a first anomaly detection process, executing a second anomaly detection process based on second information generated using the first information, executing a third anomaly detection process based on third information generated using the second information, generating and outputting a notification that an anomaly has been detected when an anomaly is detected in any of these processes, and if no anomaly is detected, generating and outputting the biometric data of the person to be authenticated to be used for biometric authentication using the third information.

Description

Technical Field

[0001] The present disclosure relates to a method for acquiring biological data.

Background Art

[0002] Patent Document 1 discloses a method for performing fingerprint recognition. This method captures one or more high-resolution images representing a plurality of fingers of an object by a mobile device having a camera, a storage medium, instructions stored in the storage medium, and a processor for executing the instructions, and the processor uses a segmentation algorithm to identify each fingertip segment for each finger from the one or more high-resolution images, extracts distinguishable features from each fingertip segment for each finger, generates a biometric identifier including the extracted distinguishable features, stores the generated biometric identifier in a memory, and determines the viability of whether they represent a living object based on the features or characteristics of the generated biometric identifier.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In view of the above-described conventional circumstances, the present disclosure is devised to provide a method for acquiring biological data that more efficiently performs generation of biological data used for biometric authentication and detection of abnormalities in biological data.

Means for Solving the Problems

[0005] This disclosure provides a method for acquiring biometric data performed by at least one processor, comprising: acquiring first information in which a biological part of a person to be authenticated is imaged; executing a first anomaly detection process based on the first information; executing a second anomaly detection process different from the first anomaly detection process based on second information generated using the first information; executing a third anomaly detection process different from the first and second anomaly detection processes based on third information generated using the second information; generating and outputting a notification that an anomaly has been detected when an anomaly is detected in any of the first, second, or third anomaly detection processes; and, if no anomaly is detected in any of the first, second, or third anomaly detection processes, generating and outputting biometric data of the person to be authenticated used for biometric authentication using the third information. [Effects of the Invention]

[0006] According to this disclosure, the generation of biometric data used for biometric authentication and the detection of anomalies in biometric data can be performed more efficiently. [Brief explanation of the drawing]

[0007] [Figure 1] Block diagram showing a biological data acquisition device according to Embodiment 1 [Figure 2] Flowchart showing an example of the operation procedure for a biometric data acquisition device. [Figure 3] Figures showing the first and second examples of anomaly detection. [Figure 4] Figure showing a third example of anomaly detection. [Figure 5] Block diagram showing an example of the internal configuration of the biometric data acquisition system according to Embodiment 2. [Modes for carrying out the invention]

[0008] (Background leading to this disclosure) Conventionally, when acquiring biometric data from biological parts used in biometric authentication (e.g., fingerprints, veins, or palm prints), there has been a demand for technologies to detect the falsification or forgery (i.e., impersonation) of fingerprints using, for example, printed materials, images displayed on screens, or silicon on which fingerprints have been formed. In particular, biometric authentication that acquires biometric data in a non-contact manner on a predetermined surface (e.g., a glass surface or sensor) has problems compared to biometric authentication that acquires biometric data while in contact with the predetermined surface, because of the greater freedom in how the biological part is held, it is easier to acquire biometric data unsuitable for biometric authentication, and it is easier to falsify or forge (i.e., impersonate) the biological part.

[0009] Patent Document 1 identifies the fingertip segments of each finger from a high-resolution image, extracts identifiable features from each fingertip segment for each finger, and determines the viability of whether they represent living subjects based on the features or characteristics of a biometric identifier that includes the extracted identifiable features.

[0010] However, in Patent Document 1, the viability determination is performed after the extraction of fingertip segments and biometric identifiers. Therefore, in biometric data registration or authentication using biometric data, there was a possibility that the notification of the viability determination result to the biometric data registration or authentication system, or to the user being authenticated, would be delayed, resulting in a decrease in throughput.

[0011] The following describes in detail each embodiment that specifically discloses the configuration and operation of the method for acquiring biological data relating to this disclosure, with reference to the drawings as appropriate. However, unnecessarily detailed explanations may be omitted. For example, detailed explanations of already well-known matters or redundant explanations of substantially identical configurations may be omitted. This is to avoid the following explanation becoming unnecessarily verbose and to facilitate understanding by those skilled in the art. The attached drawings and the following explanation are provided to enable those skilled in the art to fully understand this disclosure and are not intended to limit the subject matter described in the claims.

[0012] In this disclosure, the term "biometric data" refers to data that includes the characteristics of a biological part used for biometric authentication, and includes, for example, image data of a biological part, data of one or more feature points indicating individuality in a biological part, or data of feature quantities indicating individuality obtained from a biological part. In this disclosure, the term "feature" refers to an element used to identify a fingerprint in the authentication process of biometric authentication, and includes, for example, a feature pattern or shape of a biological part, a feature quantity of a biological part, or a feature point of a biological part.

[0013] Furthermore, the term "abnormal" in this disclosure refers to a state in which the condition of a biological part as depicted in an image used to generate biometric data is unsuitable for biometric authentication, for example, due to the falsification or forgery of a biological part, or the presentation of an incorrect biological part.

[0014] <Embodiment 1> Referring to Figure 1, the biological data acquisition device P1 according to Embodiment 1 will be described. Figure 1 is a block diagram of the biological data acquisition device P1 according to Embodiment 1. Note that the biological data acquisition device P1 shown in Figure 1 is just one example and is not limited thereto.

[0015] The biometric data acquisition device P1 performs several anomaly detection processes during the process of acquiring (generating) biometric data (i.e., fingerprint images or features indicating the individuality of fingerprints) used for biometric authentication. The biometric data acquisition device P1 includes a communication unit 10, a processor 11, a memory 12, and a camera 13.

[0016] Note that the biometric data acquisition device P1 shown in Figure 1 is just one example and is not limited thereto. For example, the biometric data acquisition device P1 may not include a camera 13. In such a case, the biometric data acquisition device P1 acquires captured images of the fingers from an external device that is connected to it via a communication unit 10.

[0017] The communication unit 10 is connected to be capable of wireless communication with any external device or external server and executes data transmission and reception. Here, the wireless communication is, for example, short-range wireless communication such as Bluetooth (registered trademark), NFC (registered trademark), or communication via a wireless Local Area Network (LAN) such as Wi-Fi (registered trademark).

[0018] The communication unit 10 outputs various data acquired from an external device or external server to the processor 11. Also, the communication unit 10 transmits various data acquired from the processor 11 to an external device or external server.

[0019] The processor 11 is configured using, for example, a Central Processing Unit (hereinafter referred to as "CPU"), a Field Programmable Gate Array (hereinafter referred to as "FPGA"), or a Graphics Processing Unit (hereinafter referred to as "GPU") and performs various processes and controls in cooperation with the memory 12. Specifically, the processor 11 refers to the programs and data held in the memory 12 and executes those programs to realize functions such as acquisition of biological data and detection of abnormalities in biological data.

[0020] The abnormality detection unit 111 executes analysis processes using the captured image in which a finger is captured and the intermediate data acquired (generated) until the generation of the fingerprint image, respectively. The abnormality detection unit 111 detects an abnormality from the fingerprint shown in the fingerprint image or the intermediate data. When the abnormality detection unit 111 determines that an abnormality has been detected from the fingerprint shown in the fingerprint image or the intermediate data, it outputs a notification indicating that an abnormality has been detected.

[0021] Memory 12 includes, for example, a Random Access Memory (hereinafter referred to as "RAM") used as a work memory when each process of the processor 11 is executed, and a Read Only Memory (hereinafter referred to as "ROM") that stores programs and data defining the operation of the processor 11. In the RAM, data or information generated or acquired by the processor 11 is temporarily stored. In the ROM, a program defining the operation of the processor 11 is written.

[0022] Camera 13 includes a lens (not shown) and an imaging sensor (not shown). The lens (not shown) forms an image of the incident light on the imaging sensor (not shown). The imaging sensor (not shown) is a so-called image sensor, for example, a solid-state imaging device such as a Charged-Coupled Device (CCD) or a Complementary Metal Oxide Semiconductor (CMOS). Camera 13 converts the optical image formed on the imaging surface by the lens (not shown) into an electrical signal and outputs it to the processor 11.

[0023] Next, referring to each of FIGS. 2 to 4, an example of a procedure for acquiring biological data and a procedure for detecting an abnormality will be described. FIG. 2 is a flowchart showing an example of an operation procedure of the biological data acquisition device P1. FIG. 3 is a diagram showing first and second abnormality detection examples. FIG. 4 is a diagram showing a third abnormality detection example.

[0024] The processor 11 acquires a captured image of a finger (hereinafter referred to as "finger image") captured by the camera 13 (St11). Note that the finger images IMG11, IMG12, IMG13, IMG14 (see FIG. 3) referred to here are captured images in which at least one finger out of four fingers from the index finger to the little finger is captured.

[0025] The anomaly detection unit 111 performs image analysis on the entire acquired finger images IMG11 to IMG14 and executes the first anomaly detection process (St12). The anomaly detection unit 111 may also execute the first anomaly detection process after noise processing (for example, processing to remove background other than fingers) or grayscale processing has been performed on the finger images IMG11 to IMG14 acquired by the processor 11.

[0026] The first anomaly detection process, as described here, is a process that detects abnormalities in the fingers based on the state of the fingers shown in the finger images IMG11 to IMG14, and performs, for example, left / right determination, front / back determination, or forgery (counterfeiting) determination. Left / right determination detects whether the fingers shown in the finger images IMG11 to IMG14 are from the right hand or the left hand, and determines whether the detected hand is the hand to be authenticated. Front / back determination determines whether the fingers shown in the finger images IMG11 to IMG14 are fingerprints (i.e., the palm side and front side). Forgery (counterfeiting) determination determines whether the fingers shown in the finger images IMG11 to IMG14 are fingers that have been forged or counterfeited using, for example, silicone, rubber, images (screen or photograph), or models.

[0027] The anomaly detection unit 111 determines in the first anomaly detection process whether or not an anomaly has been detected from the finger images IMG11 to IMG14 (St13). Here, finger image IMG11 shown in Figure 3 is an image of the hand to be authenticated, in which the four fingers necessary for left / right determination are captured and there are no anomalies. Finger image IMG12 is an image in which fingerprints are not captured. Finger image IMG13 is an image captured by camera 13 of a photograph of another person's finger. Finger image IMG14 is an image captured by camera 13 of an image of another person's finger captured on the screen of, for example, a smartphone.

[0028] For example, the anomaly detection unit 111 determines that an anomaly has been detected from the finger images IMG11 to IMG14 if it determines in the left / right determination that fingers of a hand different from the one being authenticated have been detected, if it determines in the front / back determination that the fingers shown in the finger images IMG11 to IMG14 are not fingerprints (i.e., palm side and not front side), or if it determines in the forgery determination that the fingers shown in the finger images IMG11 to IMG14 are forged or spoofed fingers. The anomaly detection unit 111 may arbitrarily change the determination process executed in the first anomaly detection process based on the number of fingers shown in the finger images IMG11 to IMG14. For example, if there are 1 to 3 fingers shown in the finger images IMG11 to IMG14, the anomaly detection unit 111 may omit the left / right determination. The method of the first anomaly detection process described above is just an example and is not limited thereto; any publicly known technology may be used.

[0029] If the anomaly detection unit 111 determines in the first anomaly detection process that an anomaly has been detected from the finger image (St13, YES), it generates a notification that an anomaly has been detected and outputs it to the processor 11 or to a monitor (not shown) provided by the biometric data acquisition device P1.

[0030] On the other hand, if the anomaly detection unit 111 determines in the first anomaly detection process that no anomalies are detected from the finger image (St13, NO), it requests the processor 11 to generate information of the fingertip detection result as intermediate data. The processor 11 performs fingertip detection to detect the area in the finger image where the fingertip (fingerprint) of each finger is captured (hereinafter referred to as the "detection area") (St14). The information of the detection areas AR11, AR12, AR13, AR14 (see Figure 3) here refers to information such as the number, size, position (coordinates) of the detection areas, or the positional relationship of each detection area.

[0031] The anomaly detection unit 111 analyzes the information of the fingerprint detection areas AR11 to AR14 of each finger obtained as a fingertip detection result and executes a second anomaly detection process (St15).

[0032] The second anomaly detection process, as described here, is a process that detects anomalies in fingerprints (fingers) based on the analysis results of the fingerprints (fingers) captured in the detection areas AR11 to AR14, and performs, for example, a finger count determination, a type determination, or a coordinate determination. The finger count determination determines whether the number of fingers detected in the detection areas AR11 to AR14 is the number of fingers to be authenticated or the number of fingers required for authentication. The type determination determines whether the detected fingers are of a type to be authenticated. The coordinate determination determines whether the fingerprints are located in a position that is expected (for example, an imaging position suitable for authentication) based on the coordinates of the detection areas AR11 to AR14. The anomaly detection unit 111 may arbitrarily change the determination process performed in the second anomaly detection process based on the number of fingers captured in the finger image. For example, if there are 1 to 3 fingers detected, the anomaly detection unit 111 may omit the type determination.

[0033] In the second abnormality detection process, the abnormality detection unit 111 determines whether or not an abnormality has been detected based on the information from detection regions AR11 to AR14 (St16). Here, detection region AR11 shown in Figure 3 is the region where the little finger of the right hand was detected. Detection region AR12 is the region where the ring finger of the right hand was detected. Detection region AR13 is the region where the middle finger of the right hand was detected. Detection region AR14 is the region where the index finger of the right hand was detected.

[0034] For example, the anomaly detection unit 111 determines that an anomaly has been detected in the finger image if, in the finger count determination, it determines that the number of fingers detected is not the number of fingers to be authenticated or the number of fingers required for authentication; in the type determination, it determines that the fingers shown in the finger image are not fingerprints (i.e., palmar or frontal); or in the forgery (counterfeiting) determination, it determines that the fingers shown in the finger image are forged or counterfeit. The anomaly detection unit 111 may arbitrarily change the determination process executed in the first anomaly detection process based on the number of fingers shown in the finger image. For example, if there are 1 to 3 fingers shown in the finger image, the anomaly detection unit 111 may omit the left / right determination. The method of the second anomaly detection process described above is just an example and is not limited thereto; any publicly known technology may be used.

[0035] If the anomaly detection unit 111 determines in the second anomaly detection process that an anomaly has been detected in the detection areas AR11 to AR14 (St16, YES), it generates a notification that an anomaly has been detected and outputs it to the processor 11 or to a monitor (not shown) provided by the biological data acquisition device P1.

[0036] On the other hand, if the anomaly detection unit 111 determines in the second anomaly detection process that no anomalies are detected in the detection regions AR11 to AR14 (St16, NO), it requests the processor 11 to generate fingertip images IMG21, IMG22, and IMG23 (see Figure 4) as intermediate data. The processor 11 generates fingertip images IMG21 to IMG23 for each finger by extracting the fingertips (fingerprints) of each finger detected from the hand image (St17).

[0037] The anomaly detection unit 111 performs image analysis on the fingertip images IMG21 to IMG23 of each finger and executes a third anomaly detection process (St18). Here, the fingertip image IMG21 shown in Figure 4 is an image of a fingertip on which a silicone mold of another person's fingerprint has been placed. The fingertip image IMG22 is an image of a fingertip whose fingerprint has been altered by surgery or the like. The fingertip image IMG23 is an image of a fingertip whose fingerprint has been altered by tape or the like.

[0038] The third anomaly detection process, as referred to here, is a process that detects abnormalities in fingerprints (fingers) based on fingertip images IMG21 to IMG23, and for example, performs fingerprint forgery (counterfeiting) detection. Fingerprint forgery (counterfeiting) detection determines whether there is silicone with printed fingerprints, fingerprint concealment, or fingerprint transplantation (tampering) through surgery in the fingertip (fingerprint) area.

[0039] In the third abnormality detection process, the abnormality detection unit 111 determines whether or not an abnormality has been detected based on the fingertip images IMG21 to IMG23 (St19).

[0040] For example, in the fingerprint forgery (counterfeiting) determination, if the anomaly detection unit 111 determines that the fingertip (fingerprint) captured in the fingertip image is a forged or counterfeit fingertip (fingerprint), it determines that an anomaly has been detected from the fingertip images IMG21 to IMG23. Note that the third anomaly detection processing method described above is just an example and is not limited thereto; any publicly known technique may be used.

[0041] If the anomaly detection unit 111 determines in the third anomaly detection process that an anomaly has been detected from the fingertip images IMG21 to IMG23 (St19, YES), it generates a notification that an anomaly has been detected and outputs it to the processor 11 or to a monitor (not shown) provided by the biometric data acquisition device P1.

[0042] On the other hand, if the anomaly detection unit 111 determines in the third anomaly detection process that no anomalies are detected from the fingertip images IMG21 to IMG23 (St19, NO), it requests the processor 11 to generate biometric data. The processor 11 generates fingerprint images for each finger, or extracts feature quantities from the fingerprint images to obtain biometric data. The processor 11 registers the acquired fingerprint images or feature quantities for each finger, or performs fingerprint authentication using the acquired fingerprint images or feature quantities for each finger (St20). Note that the processing in step St20 is not mandatory and may be omitted.

[0043] As described above, the biometric data acquisition device P1 according to Embodiment 1 can perform various anomaly detections to determine whether the data is suitable for biometric data and acquire biometric data used for biometric authentication by performing different anomaly detection processes on various types of information acquired in the process of obtaining biometric data (e.g., raw data or a finger image after noise processing), and on intermediate data generated or acquired in the process of generating biometric data from the finger image (e.g., information on the detection area or a fingertip image). This allows the biometric data acquisition device P1 to perform anomaly detection processes in multiple stages, and if an anomaly is detected in each anomaly detection process, it can output a notification indicating that an anomaly was detected before the biometric data was generated, that is, that the finger image is not suitable for acquiring biometric data. Therefore, the biometric data acquisition device P1 can suppress a decrease in throughput in biometric data acquisition and make the anomaly detection process more efficient.

[0044] In this disclosure, the intermediate data described above is merely an example and is not limited thereto. The intermediate data may further include images obtained by converting the raw hand image (color image) captured by the camera 13 into a grayscale (black and white image), or images obtained by removing background noise from the hand image. In such cases, the biometric data acquisition device P1 may perform an anomaly detection process that is executable using this intermediate data, which may be the same as or different from the first anomaly detection process.

[0045] Furthermore, the biometric data acquisition device P1 can improve the efficiency of each anomaly detection process by sequentially executing the first to third anomaly detection processes corresponding to each image data (finger image or intermediate data), and can also improve the accuracy of anomaly detection by using data suitable for each anomaly detection process. Specifically, the image analysis processing performed on each image data becomes more sophisticated in the order of finger image, then fingertip image (intermediate data). Therefore, the biometric data acquisition device P1 can perform a wider variety of anomaly detections on non-contact acquired finger images while suppressing a decrease in throughput performance by executing different first to third anomaly detection processes using each image data in accordance with the image analysis results obtainable through the image analysis processing performed on each image data.

[0046] For example, in the first anomaly detection process, left / right determination is not performed by individually analyzing each detection region AR11~AR14 or each fingertip image IMG21~IMG23 to determine whether the fingers in each detection region or each fingertip image belong to the right or left hand. Instead, the finger images IMG11~IMG14 are analyzed, and the determination is made based on the positional relationship of the four fingers from the index finger to the little finger. This allows the biometric data acquisition device P1 to more effectively reduce the processing time or processing load required for left / right determination and improve the accuracy of determining whether the captured fingers belong to the right or left hand.

[0047] Similarly, for example, in the first anomaly detection process, the front / back determination is not performed by individually analyzing each detection region AR11~AR14 or each fingertip image IMG21~IMG23 to determine whether a fingertip (fingerprint) or nail is captured in each detection region or each fingertip image, but rather by analyzing the entire hand image. This allows the biometric data acquisition device P1 to improve its accuracy in determining whether the captured hand is the right or left hand.

[0048] Similarly, for example, the forgery (counterfeiting) determination in the first anomaly detection process is made by analyzing the entire fingertip image, rather than analyzing only the fingertips visible in each detection region AR11~AR14 or each fingertip image IMG21~IMG23. This improves the accuracy with which the biometric data acquisition device P1 can determine whether the fingers visible in the finger image are forged (for example, the biological part being the subject is not a living organism but a photograph, an image displayed on a screen, a model of a finger made of silicone or rubber, etc.).

[0049] Therefore, in the second anomaly detection process, the number determination, type determination, or coordinate determination can be performed using the positional information of the detection regions AR11 to AR14, or the positional relationship of the detection regions AR11 to AR14, as an image analysis result of the detection regions AR11 to AR14 relative to the finger images IMG11 to IMG14, rather than using the image analysis results of the finger images IMG11 to IMG14, thereby improving the accuracy of anomaly detection. Furthermore, by performing the second anomaly detection process using the detection regions AR11 to AR14 without using the fingertip images IMG21 to IMG23, the biometric data acquisition device P1 can more efficiently reduce the number of anomaly detection processes performed using fingertip images and improve the throughput of more advanced image analysis processing using fingertip images.

[0050] Furthermore, for example, image analysis processing using fingertip images IMG21~IMG23 generally involves fewer pixels to be analyzed than hand images IMG11~IMG14. Therefore, if you want to perform more advanced image analysis processing for anomaly detection, using fingertip images IMG21~IMG23 instead of hand images IMG11~IMG14 allows you to achieve advanced image analysis processing without increasing the time required for image analysis processing.

[0051] Therefore, in the third anomaly detection process, the biometric data acquisition device P1 can concentrate on advanced image processing to detect the presence or absence of sophisticated forgery, such as falsifying (forging) fingerprints on the fingertips, thereby suppressing a decrease in throughput.

[0052] (Embodiment 2) The biometric data acquisition device P1 according to Embodiment 1 described above is an example in which imaging of the user's fingers and anomaly detection using the captured finger images are performed. The biometric data acquisition system 100 according to Embodiment 2 described below will explain an example in which imaging of the user's fingers and anomaly detection using the captured finger images are performed by different devices.

[0053] In the description of the biological data acquisition system 100 shown in Figure 5, the same components and functions as those of the biological data acquisition device P1 shown in Figure 1 are assigned the same reference numerals, thus omitting further explanation.

[0054] Referring to Figure 5, the biological data acquisition system 100 according to Embodiment 2 will be described. Figure 5 is a block diagram showing an example of the internal configuration of the biological data acquisition system 100 according to Embodiment 2.

[0055] The biological data acquisition system 100 includes a biological data acquisition device P1A and a processing device P2. The overall configuration of the biological data acquisition system 100 shown in Figure 5 is an example and is not limited thereto. For example, the processing device P2 may be connected to multiple biological data acquisition devices P1A in a communication-enabled manner.

[0056] The biometric data acquisition device P1A captures images of the user's fingers and transmits the captured finger images to the processing device P2. The biometric data acquisition device P1A includes a communication unit 10A, a processor 11A, a memory 12, and a camera 13.

[0057] The communication unit 10A is connected to the processing unit P2 via wireless or wired communication and performs data transmission and reception. The communication unit 10A transmits the hand image captured by the camera 13 to the processing unit P2.

[0058] The processor 11A is configured using, for example, a CPU, FPGA, or GPU, and works in cooperation with the memory 12 to perform various processing and control operations. Specifically, the processor 11A refers to the programs and data held in the memory 12 and executes the programs to transmit the hand images output from the camera 13 to the processing unit P2.

[0059] The processing unit P2 is connected to the biological data acquisition device P1A in a manner that enables data communication. The processing unit P2 can be implemented as, for example, a PC, a notebook PC, a tablet terminal, an on-premise server, or a cloud server. The processing unit P2 includes a communication unit 20, a processor 21, and a memory 22.

[0060] The communication unit 20 is wirelessly connected to the biometric data acquisition device P1A and performs data transmission and reception. The communication unit 20 acquires the finger image transmitted from the biometric data acquisition device P1A and outputs it to the processor 21. The communication unit 20 also transmits a notification to the biometric data acquisition device P1A indicating that an anomaly has been detected, which is output from the processor 21 (anomaly detection unit 211).

[0061] The processor 21 is configured using, for example, a CPU, FPGA, or GPU, and works in cooperation with the memory 22 to perform various processes and controls. Specifically, the processor 21 refers to the programs and data held in the memory 22 and executes those programs to realize functions such as abnormal detection of biological data. The processor 21 can realize the same functions (processing) as the processor 11 in the operation procedure shown in Figure 2.

[0062] The anomaly detection unit 211 can perform the same functions (processing) as the anomaly detection unit 111 shown in Embodiment 1. The anomaly detection unit 211 performs analysis processing using the captured image of the fingers and the intermediate data acquired (generated) before the fingerprint image is generated. The anomaly detection unit 211 detects anomalies from the fingerprints captured in the fingerprint image or the intermediate data. If the anomaly detection unit 211 determines that an anomaly has been detected from the fingerprints captured in the fingerprint image or the intermediate data, it outputs a notification indicating that an anomaly has been detected.

[0063] Memory 22 includes, for example, RAM as work memory used when executing each process of processor 21, and ROM which stores programs and data that define the operation of processor 21. Data or information generated or acquired by processor 21 is temporarily stored in RAM. Programs that define the operation of processor 21 are written to ROM.

[0064] (Note) Based on the descriptions of the embodiments described above, the following technologies are disclosed.

[0065] (Technology 1) A method for acquiring biometric data performed by at least one processor 11,21, The first piece of information (hand images IMG11~IMG14) is obtained, which is an image of the body part (fingertip) of the person being authenticated (user). Based on the first information (finger images IMG11~IMG14), the first anomaly detection process is executed. Based on the second information (information of detection regions AR11 to AR14) generated using the first information (finger images IMG11 to IMG14), a second anomaly detection process different from the first anomaly detection process is executed. Based on the third information (finger tip images IMG21-IMG23) generated using the second information (information from the detection region AR11-AR14), a third anomaly detection process different from the first anomaly detection process and the second anomaly detection process is executed. When an anomaly is detected in any of the first anomaly detection process, the second anomaly detection process, or the third anomaly detection process, a notification indicating that the anomaly has been detected is generated and output. If no anomaly is detected in any of the first, second, or third anomaly detection processes, the third information (finger tip images IMG21-IMG23) is used to generate and output the biometric data of the person to be authenticated (e.g., a fingerprint image or fingerprint feature quantities) used for biometric authentication. Methods for acquiring biometric data. As a result, processors 11 and 21 can perform different anomaly detection processes on various types of information acquired during the process of obtaining biometric data (for example, finger images (raw data or data after noise processing) and intermediate data generated or acquired during the process of generating biometric data from finger images (for example, information on the detection area or fingertip images, etc.)), thereby enabling various anomaly detections to determine whether the data is suitable for biometric data and the acquisition of biometric data. This allows processors 11 and 21 to perform anomaly detection processes in multiple stages. If an anomaly is detected in each anomaly detection process, a notification can be output indicating that an anomaly was detected before the biometric data was generated, meaning that the finger images used to acquire biometric data are not suitable for biometric data acquisition. This suppresses a decrease in throughput during biometric data acquisition and makes the anomaly detection process more efficient.

[0066] (Technology 2) The first piece of information mentioned above consists of finger images IMG11 to IMG14, which are images of the fingers of the person being authenticated. Method for acquiring biological data as described in (Technology 1). As a result, processors 11 and 21 can perform a first anomaly detection process using the finger images IMG11 to IMG14, which are acquired first in the process of obtaining biometric data, and acquire information on the detection regions AR11 to AR14 where the fingertips are detected from the finger images IMG11 to IMG14. Note that the acquisition of information on the detection regions AR11 to AR14 is performed based on the result of the first anomaly detection process, and is not performed if an anomaly is detected in the first anomaly detection process. Therefore, processors 11 and 21 can suppress the decrease in throughput in the acquisition of biometric data and determine whether the finger images used for acquiring biometric data are suitable for biometric data.

[0067] (Technology 3) The second piece of information is the detection result of the fingertips of the person being authenticated, obtained by detecting the fingertips from the finger images IMG11 to IMG14 (i.e., information from the detection region AR11 to AR14). A method for acquiring biological data as described in (Technology 1) or (Technology 2). As a result, processors 11 and 21 can perform a second anomaly detection process using information from detection regions AR11 to AR14 acquired during the process of obtaining biometric data, and acquire fingertip images IMG21 to IMG23 using information from detection regions AR11 to AR14. The acquisition of fingertip images IMG21 to IMG23 is performed based on the results of the second anomaly detection process, and is not performed if an anomaly is detected in the second anomaly detection process. Therefore, processors 11 and 21 can suppress the decrease in throughput during biometric data acquisition and determine whether the finger images used for biometric data acquisition are suitable for biometric data.

[0068] (Technology 4) The third piece of information is the fingertip images IMG21 to IMG23 generated based on the fingertip detection results. A method for acquiring biological data described in any one of (Technology 1) to (Technology 3). As a result, processors 11 and 21 can perform a third anomaly detection process using fingertip images IMG21 to IMG23 acquired during the process of obtaining biometric data, and acquire biometric data (fingerprint images or fingerprint features) using fingertip images IMG21 to IMG23. The acquisition of biometric data is performed based on the results of the third anomaly detection process, and is not performed if an anomaly is detected in the third anomaly detection process. Therefore, processors 11 and 21 can suppress the decrease in throughput during biometric data acquisition and determine whether the finger images used for biometric data acquisition are suitable for biometric data.

[0069] (Technology 5) The first anomaly detection process includes a process for detecting whether the biological part is on the palm side (front / back determination), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of a biological part (fingerprint) used for biometric authentication. In other words, processors 11 and 21 can perform a determination of the front or back of the finger (palm or back of the hand) as a process to detect one of the anomalies that can occur in a non-contact state, that is, when there is a high degree of freedom in the orientation of the biological part.

[0070] (Technology 6) The first anomaly detection process includes a process for detecting whether the biological part is the right hand or the left hand (left / right determination), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of a biological part (fingerprint) used for biometric authentication. In other words, processors 11 and 21 can perform left / right determination of the fingers as a process to detect one of the anomalies that can occur in a non-contact state, that is, when there is a high degree of freedom in the orientation of the biological part.

[0071] (Technology 7) The first anomaly detection process includes a process for detecting whether the biological part is a living organism (determination of falsification / counterfeiting), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of biological parts (fingerprints) used for biometric authentication. In other words, processors 11 and 21 can perform a finger forgery (counterfeiting) detection process, which is easier to perform by capturing biological parts in a non-contact manner.

[0072] (Technology 8) The second abnormality detection process includes a process for detecting the number or type of the biological parts (number determination or type determination), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of a biological part (fingerprint) used for biometric authentication. In other words, processors 11 and 21 can perform a finger count determination as a process to detect one of the anomalies that are likely to occur in a non-contact state, that is, when the degree of freedom of the posture of the biological part is high.

[0073] (Technology 9) The second anomaly detection process includes a process for detecting the position of each biological part (coordinate determination), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of a biological part (fingerprint) used for biometric authentication. In other words, processors 11 and 21 can perform finger coordinate determination as a process to detect one of the anomalies that are likely to occur in a non-contact state, that is, when the degree of freedom of the orientation of the biological part is high.

[0074] (Technology 10) The third anomaly detection process includes a detection process to determine whether or not the biological part has been disguised or forged (fingerprint forgery determination), Method for acquiring biological data as described in (Technology 1). This allows processors 11 and 21 to determine whether the acquired finger images IMG11 to IMG14 are images of biological parts (fingerprints) used for biometric authentication. In other words, processors 11 and 21 can perform fingerprint forgery detection as a process to detect one of the anomalies that becomes easier to perform by capturing biological parts in a non-contact manner.

[0075] Although various embodiments have been described above with reference to the attached drawings, this disclosure is not limited to such examples. It will be clear to those skilled in the art that various modifications, alterations, substitutions, additions, deletions, and equivalents can be conceived within the scope of the claims, and these will also be understood to fall within the technical scope of this disclosure. Furthermore, the components of the various embodiments described above can be combined arbitrarily without departing from the spirit of the invention. [Industrial applicability]

[0076] This disclosure is useful as a presentation of a method for acquiring biometric data that more efficiently performs the generation of biometric data used for biometric authentication and the detection of anomalies in biometric data. [Explanation of symbols]

[0077] 10,10A,20 Communications Department 11,11A,21 processor 12.22 memory 13 Cameras 100 Biometric Data Acquisition Systems 111,211 Anomaly detection unit AR11, AR12, AR13, AR14 detection area IMG11,IMG12,IMG13,IMG14 Hand and finger images IMG21, IMG22, IMG23 Fingertip images P1, P1A Biometric Data Acquisition Device P2 Processing Unit

Claims

1. A method for acquiring biometric data performed by at least one processor, First information is obtained, which includes images of the body parts of the person being authenticated. Based on the first information described above, the first anomaly detection process is executed. Based on the second information generated using the first information, a second anomaly detection process different from the first anomaly detection process is executed. Based on the third information generated using the second information, a third anomaly detection process different from the first anomaly detection process and the second anomaly detection process is executed. When an anomaly is detected in any of the first anomaly detection process, the second anomaly detection process, or the third anomaly detection process, a notification indicating that the anomaly has been detected is generated and output. If no abnormality is detected in any of the first, second, or third abnormality detection processes, the third information is used to generate and output the biometric data of the person to be authenticated for use in biometric authentication. Methods for acquiring biometric data.

2. The first piece of information is a finger image of the fingers of the person being authenticated. A method for acquiring biological data according to claim 1.

3. The second piece of information is the detection result of detecting the fingertips of the person being authenticated from the hand image. The method for acquiring biological data according to claim 2.

4. The third piece of information is a fingertip image generated based on the fingertip detection result. A method for acquiring biological data as described in claim 3.

5. The first anomaly detection process includes a process for detecting whether the biological part is on the palm side or not. A method for acquiring biological data according to claim 1.

6. The first anomaly detection process includes a process for detecting whether the biological part is the right hand or the left hand. A method for acquiring biological data according to claim 1.

7. The first abnormality detection process includes a process for detecting whether the biological part is a living organism. A method for acquiring biological data according to claim 1.

8. The second anomaly detection process includes a process for detecting the number or type of the biological parts. A method for acquiring biological data according to claim 1.

9. The second abnormality detection process includes a process for detecting the location of each biological part. A method for acquiring biological data according to claim 1.

10. The third abnormality detection process includes a process for detecting whether or not the biological part has been disguised or forged. A method for acquiring biological data according to claim 1.

Images