Biometric registration system and method

Abstract

This makes it easier to register highly accurate biological characteristics and reduces the time required for registration. [Solution] The biometric registration system receives input of the user's personal information from a terminal, controls a first acquisition device to acquire the user's first biometric data, extracts a first feature from the first biometric data, registers the personal information and the first feature in association with a storage device, and when a registration procedure using the registration device is started, controls a second acquisition device to acquire from the user performing the registration procedure a second biometric data for extracting a feature used for matching with the first feature, and a third biometric data for extracting a feature used when using the service, extracts a second feature and a third feature from the second biometric data and the third biometric data respectively, compares the first feature and the second feature, and registers registration data in a storage device that associates the personal information corresponding to the first feature that matches the second feature with the third feature.

Description

Technical Field

[0004]

[0001] The present invention relates to a biometric registration system and a biometric registration method.

Background Art

[0002] As background art in this technical field, there is the following prior art. In Patent Document 1, there is described an application information storage means for storing application information of a registrant, a determination means for reading registrant information included in a medium presented by the registrant and determining whether or not the registrant information matches the application information stored in the application information storage means, and a registration means for obtaining the biometric information of the registrant and registering the biometric information in association with the application information when the registrant information and the application information match (see the abstract).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, biometric authentication has started to be used in payment services and the like where authentication performance has improved due to the development of biometric authentication technology and high security is required. Biometric authentication for identifying the user himself / herself from among many people requires a dedicated biometric information acquisition device in order to acquire biometric features with high accuracy.

[0005] A biometric information acquisition device is equipped with a light source that irradiates light of a specific wavelength and an imaging unit that images the light of that wavelength. Therefore, it is rare for a biometric information acquisition device to be owned by an individual, and in most cases, it is installed in a store or the like that provides a service. The user needs to go to a store or the like to perform biometric information registration and authentication operations.

[0006] Restricting the locations where registration can be performed in this way impairs user convenience. Furthermore, when users register their biometric information, they often become confused because they are unfamiliar with the methods of presenting their biometric data, which can lead to delays in registration.

[0007] The present invention aims to simplify the registration process and reduce the time required for registration. [Means for solving the problem]

[0008] A representative example of the invention disclosed in this application is as follows: A biometric registration system comprising a computing device, a storage device connected to the computing device, and a network interface connected to the computing device, which is connected to a terminal owned by a user and a registration device installed in a store of a business operator providing services using biometric authentication, wherein the terminal includes a first acquisition device for acquiring the user's biometric data, the registration device includes a second acquisition device for acquiring the user's biometric data, the biometric registration system receives input of the user's personal information from the terminal, controls the first acquisition device to acquire first biometric data of the user who has entered the personal information, extracts first features from the first biometric data, and associates the personal information and the first features. The pre-registered data is registered in the storage device, and when the registration procedure using the registration device is started, the second acquisition device is controlled to acquire from the user performing the registration procedure second biometric data for extracting features to be used for matching with the first feature and third biometric data for extracting features to be used when using the service, the second feature and third feature are extracted from the second biometric data and the third biometric data respectively, the first feature and the second feature included in the pre-registered data are compared, and registration data is registered in the storage device associating the personal information included in the pre-registered data corresponding to the first feature that matches the second feature with the third feature. [Effects of the Invention]

[0009] According to the present invention, the process of registering highly accurate biological characteristics becomes easier, and the time required for registration can be reduced. Other problems, configurations, and effects will be clarified by the following description of the embodiments. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the overall configuration of the biometric registration system in Example 1. [Figure 2] This is a block diagram showing an example of the functional configuration of the biological registration device of Example 1. [Figure 3] This figure shows an example of the registration process in the biometric registration system of Example 1. [Figure 4] This figure shows an example of the registration process in the biometric registration system of Example 1. [Figure 5] This figure shows an example of the registration process in the biometric registration system of Example 1. [Figure 6] This flowchart shows an example of the pre-registration process in Example 1. [Figure 7] This flowchart shows an example of the registration process in Example 1. [Figure 8A] This flowchart shows an example of the registration process in Example 1. [Figure 8B] This flowchart shows an example of the registration process in Example 1. [Figure 9] This figure shows an example of a finger posture pattern in Example 2. [Figure 10] This figure shows an example of a finger posture pattern in Example 2. [Figure 11A] This figure shows an example of a method for imaging fingers in Example 2. [Figure 11B] This figure shows an example of a method for imaging fingers in Example 2. [Modes for carrying out the invention]

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The following description and drawings are examples for explaining the present invention, and for the sake of clarity of explanation, omissions and simplifications are made as appropriate. The present invention can be implemented in various other forms. Unless otherwise particularly limited, each component may be in a single or plural number.

[0012] In the configuration of the invention described below, the same or similar configurations or functions are denoted by the same reference numerals, and duplicate explanations are omitted.

[0013] The notations such as "first", "second", "third", etc. in this specification and the like are attached to identify components, and do not necessarily limit the number or order.

[0014] In this specification, biometric features are information indicating features of anatomically different living bodies such as finger veins, fingerprints, joint patterns, skin patterns, faces, ears, or irises. Further, it may be information indicating features emitted from a living body such as voice. It may be information extracted from information in which a plurality of anatomically classified living body parts are mixed and indicating a plurality of features divided by an arbitrary method.

[0015] Conventionally, in order to perform a settlement service or the like using biometric authentication, a user has to go to a store where a biometric information acquisition device is installed in advance and register biometric information and personal information such as name and address. Since the registration work as described above is restricted by location and time, it has been a barrier to the expansion of users.

[0016] In the present invention, biometric information and personal information are registered in the following procedure. First, the user registers personal information in a pre-registration database using a terminal such as a smartphone and a PC at home or the like. Next, the user goes to a store where a biometric information acquisition device is installed and registers the biometric information acquired at the store and the personal information already registered in the pre-registration database in the main registration database. According to this invention, the user can set personal information without being restricted by time and location, and only needs to register biometric information at the store, so the labor of the registration work can be reduced.

[0017] In order to realize the registration operation as described above, it is necessary to confirm that the user who registers personal information in the pre-registration database and the user who performs the registration operation at the store are the same person. Therefore, when acquiring personal information, the registration system acquires biometric information captured using a terminal. The acquired biometric information is registered in the pre-registration database in association with the personal information. At the time of the registration operation at the store, the biometric information associated with the personal information is compared with the biometric information acquired using the biometric information acquisition device to confirm the identity of the person.

[0018] There is a problem that it is difficult to compare the biometric information captured by the terminal and the biometric information captured by the biometric information acquisition device because the imaging environment and imaging method are different. Therefore, the registration system uses the biometric information acquisition device to acquire biometric information for registration and biometric information for verification. The biometric information for verification is acquired in an imaging environment and imaging method similar to the imaging environment and imaging method of the terminal. By using the biometric information for verification, it becomes easier to compare with the biometric information associated with the personal information.

Example

[0019] In Example 1, a method of associating and registering personal information acquired in advance using a terminal or the like and registration biometric data acquired at a store that provides a service will be described.

[0020] FIG. 1 is a block diagram showing the overall configuration of the biometric registration system 1000 of Example 1.

[0021] The biometric registration system 1000 of Example 1 includes a pre-registration device 3, a main registration device 4, an image input device 7, an input device 14, a speaker 15, a display device 16, an auxiliary storage device 17, and a biometric registration device 20.

[0022] The biometric registration device 20 consists of a storage medium 10, an interface (IF) 11, memory 12, and a processor 13. The biometric registration device 20 may also include a main registration device 4, an image input device 7, an input device 14, a speaker 15, a display device 16, and an auxiliary storage device 17.

[0023] The processor 13 is an arithmetic unit that executes programs stored in the memory 12. The various functions provided by the biometric registration device 20 are realized by the execution of various programs by the processor 13.

[0024] Memory 12 includes a non-volatile memory element called ROM and a volatile memory element called RAM. ROM stores immutable programs (e.g., BIOS). RAM is a high-speed, volatile memory element such as DRAM (Dynamic Random Access Memory) and temporarily stores programs executed by the processor and data used during program execution. Memory 12 also temporarily stores images and other data input from the image input device 7.

[0025] The program executed by the processor 13 is provided to the biometric registration device 20 via removable media (such as a CD-ROM or flash memory) or a network, and stored in the non-volatile auxiliary storage device 17, which is a non-temporary storage medium. For this reason, the storage medium 10 should have an interface for reading data from the removable media.

[0026] Interface 11 functions as an input interface that accepts information input from an external device and / or an output interface that outputs information to an external device. In other words, interface 11 has ports for connecting the biometric registration device 20 with external devices such as the pre-registration device 3, the main registration device 4, the image input device 7, the input device 14, the speaker 15, the display device 16, and the auxiliary storage device 17.

[0027] Interface 11 also functions as a communication interface for the biometric registration device 20 to communicate with external devices via a communication network (not shown). The communication interface is, for example, a device that performs communication in accordance with the IEEE 802.3 standard if the communication network is a wired LAN (Local Area Network), and a device that performs communication in accordance with the IEEE 802.11 standard if the communication network is a wireless LAN.

[0028] The auxiliary storage device 17 is a high-capacity, non-volatile storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive), which stores the program executed by the processor. In other words, the program is read from the auxiliary storage device 17, loaded into memory 12, and executed by the processor to realize each function of the biometric registration device 20.

[0029] Furthermore, the auxiliary storage device 17 stores a pre-registration database 32 that stores the user's pre-registration data and a main registration database 31 that stores the registration data.

[0030] Pre-registration data and registered data are, for example, data that associates features (biometric features) extracted from images of faces, fingers, or finger vein patterns with personal information.

[0031] The display device 16 is, for example, a liquid crystal display and is an output device that displays information such as information acquired from the biological registration device 20, biological posture guidance information, and posture determination results.

[0032] The input device 14 is, for example, a keyboard or a touch panel, and receives information input from the user and outputs it to the biometric registration device 20.

[0033] Speaker 15 is an output device that transmits information received from the biometric registration device 20 as an acoustic signal, such as voice.

[0034] The biometric registration device 20 is a computer system configured on a single physical computer or on multiple computers configured logically and physically, and may operate on a virtual computer built on multiple physical computer resources. For example, each functional unit may operate on a separate physical or logical computer, or multiple units may be combined and operate on a single physical or logical computer.

[0035] The pre-registration device 3 captures images of specific body parts (biological body parts) of the registrant 1, such as their fingers 2 and face 9. In this embodiment, the images of the biological body parts become the biological data. The pre-registration device 3 is a terminal such as a smartphone or PC, and captures images of the biological body parts using an internal or externally connected imaging device. The biological body parts captured by the pre-registration device 3 may also be the iris, the back of the hand, or the palm.

[0036] The image input device 7 acquires images captured by the pre-registration device 3 and the main registration device 4, and outputs the acquired images to the biometric registration device 20. The image input device 7 is, for example, various reader devices for reading images (e.g., a video capture board).

[0037] This registration device 4 captures images of biological parts such as the fingers 2 or face 9 of the registrant 1. The biological parts captured by the bio-imaging device 6 may also be the iris, back of the hand, and palm. This registration device 4 includes multiple light sources 5 and bio-imaging devices 6. This registration device 4 may also include multiple bio-imaging devices 6.

[0038] The bioimaging device 6 captures images of living tissue. The bioimaging device 6 is an optical sensor capable of capturing light of one or more wavelengths, and may be a monochrome camera or a color camera. It may also be a multispectral camera capable of simultaneously capturing ultraviolet or infrared light in addition to visible light. Furthermore, the bioimaging device 6 may be a distance camera capable of measuring the distance to the subject, or it may be a stereo camera combining multiple cameras.

[0039] Furthermore, if the biological body part to be imaged is the fingers 2, the bio-imaging device 6 may image one finger or multiple fingers.

[0040] The light source 5 is a light-emitting element such as an LED (Light Emitting Diode), and it irradiates light onto the biological site of the registrant 1 presented on the registration device 4. The light source 5 may be capable of irradiating various wavelengths, or it may be capable of irradiating multiple wavelengths simultaneously. The light source 5 may be capable of irradiating transmitted light from the biological site, or it may be capable of irradiating reflected light from the biological site. Furthermore, the light source 5 may be composed of multiple light-emitting elements, and it may have a function that allows the biological registration device 20 to adjust the light emission intensity of each of the multiple light-emitting elements.

[0041] In this embodiment, examples are described in which the fingers 2 and face 9 are used as biological tissues. Therefore, although the registration device 4 includes a light source 5 and a biological imaging device 6, if other biological tissues are used, the registration device 4 will include sensors and the like for acquiring those other biological characteristics.

[0042] In this embodiment, a biometric information registration system including multiple components is described, but instead of the biometric information registration system, a biometric authentication device in which some of the multiple components are mounted in a housing may perform the function. The pre-registration device 3 and the main registration device 4 may be personal authentication devices that perform registration processing or authentication processing. The registration processing, authentication processing, or feature generation and extraction processing may be performed by an external device connected to the pre-registration device.

[0043] Figure 2 is a block diagram showing an example of the functional configuration of the biometric registration device 20 in Example 1. The functional parts of the biometric registration device 20 are realized by a program stored in the memory 12.

[0044] The memory 12 of the biometric registration device 20 includes a pre-registration processing unit 200 and a main registration processing unit 300.

[0045] The pre-registration processing unit 200 includes a personal information input unit 201, an imaging control unit 202, an appropriateness determination unit 203, a feature extraction unit 204, a matching processing unit 205, a registration processing unit 206, and a pre-registration code output unit 207.

[0046] The personal information input unit 201 accepts the input of personal information that registrants apply for during pre-registration. Personal information includes the registrant's name and address, and is entered using the pre-registration device 3, etc.

[0047] The imaging control unit 202 controls the pre-registration device 3 to image the biological tissue under appropriate conditions.

[0048] The suitability determination unit 203 analyzes various attribute information, such as the posture of the biological body parts in the captured image, and determines the suitability of the image.

[0049] The feature extraction unit 204 extracts features from the image acquired from the pre-registered device 3.

[0050] The matching processing unit 205 performs image matching using the feature quantities extracted by the feature extraction unit 204.

[0051] The registration processing unit 206 associates personal information with feature quantities extracted from images captured by the pre-registration device 3 and registers it in the pre-registration database 32.

[0052] The pre-registration code output unit 207 outputs a pre-registration code to identify the pre-registration data.

[0053] The registration processing unit 300 includes an input unit 301, an imaging control unit 302, an appropriateness determination unit 303, a feature extraction unit 304, a matching processing unit 305, a cross-matching processing unit 306, and a registration processing unit 307.

[0054] The input unit 301 accepts input of a pre-registration code to identify the pre-registration data of the registrant.

[0055] The imaging control unit 302 controls the registration device 4 to image the biological tissue under appropriate conditions.

[0056] The suitability determination unit 303 analyzes various attribute information, such as the posture of the biological body parts in the captured image, and determines the suitability of the image.

[0057] The feature extraction unit 304 extracts feature quantities from the image acquired from the registration device 4.

[0058] The matching processing unit 305 performs image matching using the feature quantities extracted by the feature extraction unit 304.

[0059] The cross-referencing processing unit 306 performs a comparison of feature quantities extracted from the image captured by the pre-registration device 3 and the image acquired from the main registration device 4.

[0060] The registration processing unit 307 associates personal information with feature quantities extracted from images captured by the registration device 4 and registers it in the registration database 31.

[0061] Figure 3 shows an example of the registration process in the biological registration system 1000 of Example 1.

[0062] The biometric registration device 20 accepts the input of personal information and controls the pre-registration device 3 to acquire images of the registrant's fingers 2 or face 9, etc. The biometric registration device 20 extracts features (pre-registered biometric data) from the acquired images. The biometric registration device 20 registers the pre-registration data, which associates the personal information with the pre-registered biometric data, into the pre-registration database 32.

[0063] The biometric registration device 20 controls the main registration device 4 to acquire an image of the biometric body part used during biometric authentication as the first biometric data, and acquires an image of the same biometric body part as the pre-registered biometric data as the second biometric data. The biometric registration device 20 compares the features extracted from the acquired second biometric data with the pre-registered biometric data. If the features extracted from the second biometric data match the pre-registered biometric data, the biometric registration device 20 registers the registered data in the main registration database 31, which associates the features extracted from the first biometric data (registered biometric data) with the personal information associated with the pre-registered biometric data.

[0064] The first and second biological data are obtained from the same biological body part. The biological body parts may be the same or different. If obtained from the same biological body part, the images obtained using different imaging methods, such as changing the wavelength of the light emitted from the light source of this registration device 4 to the biological body part, shall be designated as the first and second biological data.

[0065] Figure 4 shows an example of the registration process in the biological registration system 1000 of Example 1.

[0066] Figure 4 illustrates the detailed registration process when acquiring first and second biological data from the same biological site.

[0067] The biometric registration device 20 accepts the input of personal information and controls the pre-registration device 3 to irradiate with visible light and take an image, thereby acquiring a visible light image of the fingers 2 of the registrant 1. The biometric registration device 20 extracts features (pre-registered biometric data) from the acquired image. The biometric registration device 20 registers the pre-registration data, which associates the personal information with the pre-registered biometric data, in the pre-registration database 32. In addition, the biometric registration device 20 issues a pre-registration code to identify the pre-registered biometric data at the time of main registration.

[0068] When registrant 1 completes the registration, the biometric registration device 20 accepts a pre-registration code. If the biometric registration device 20 can identify registrant 1's pre-registration data, it controls the main registration device 4 to irradiate with infrared light and take an image, acquiring an infrared image of registrant 1's fingers 2 as the first biometric data, and then controls the main registration device 4 to irradiate with visible light and take an image, acquiring a visible light image of registrant 1's fingers 2 as the second biometric data. The biometric registration device 20 compares the features extracted from the acquired second biometric data with the pre-registered biometric data. If the features extracted from the second biometric data match the pre-registered biometric data, the biometric registration device 20 registers the registration data in the main registration database 31, associating the features extracted from the first biometric data (registered biometric data) with the personal information associated with the said pre-registered biometric data.

[0069] The first biometric data is used to verify the identity of the individual when providing biometric authentication services after biometric registration. In Figure 4, the first biometric data is an infrared image taken by shining infrared light onto the fingers.

[0070] For the second set of biometric data, images captured under the same conditions (same wavelength) as those used during pre-registration are easier to match. In Figure 4, a visible light image is acquired using the pre-registration device 3. Therefore, for the second set of biometric data, a visible light image captured using visible light is easier to match than an infrared image used in actual authentication, thus reducing the time required for registration.

[0071] The biometric registration device 20 may acquire the first and second biometric data by controlling the wavelength of light emitted by the light source 5 of the registration device 4, or it may acquire the first and second biometric data by controlling the simultaneous irradiation of infrared and visible light and performing spectroscopic processing on the acquired biometric data. Spectroscopic processing is an image processing technique that can separate a single image into multiple images corresponding to specific wavelength bands of light. By acquiring the first and second biometric data at the same time in this way, problems such as identity theft can be solved.

[0072] The pre-registration code may, for example, be displayed on the registration device 4 as a QR code (QR Code is a registered trademark, the same applies hereinafter) that directs users to the pre-registration app, or as a QR code that directs users to the pre-registration site. Alternatively, the device may accept the email address of the registrant 1 and send the URLs of the pre-registration app and site to that email address.

[0073] Figure 5 shows an example of the registration process in the biological registration system 1000 of Example 1.

[0074] Figure 5 illustrates the registration process when acquiring first and second biological data from different biological sites of registrant 1.

[0075] The biometric registration device 20 accepts the input of personal information and controls the pre-registration device 3 to irradiate with visible light and take an image, thereby acquiring an image of the registrant's face 9. The biometric registration device 20 extracts features (pre-registered biometric data) from the acquired image. The biometric registration device 20 registers the pre-registration data, which associates the personal information with the pre-registered biometric data, in the pre-registration database 32, and issues a pre-registration code to identify the pre-registered biometric data at the time of main registration.

[0076] When registrant 1 completes the registration, the biometric registration device 20 accepts a pre-registration code. If the biometric registration device 20 can identify registrant 1's pre-registered biometric data, it controls the main registration device 4 to irradiate with infrared light and take an image, acquiring an infrared image of registrant 1's fingers 2 as the first biometric data, and controls the main registration device 4 to irradiate with visible light and take an image, acquiring a visible light image of registrant 1's face 9 as the second biometric data. The biometric registration device 20 compares the features extracted from the acquired second biometric data with the pre-registered biometric data. If the features extracted from the second biometric data match the pre-registered biometric data, the biometric registration device 20 registers the registration data in the main registration database 31, associating the features extracted from the first biometric data (registered biometric data) with the personal information associated with the said pre-registered biometric data.

[0077] The biological registration device 20 may acquire the first biological data and the second biological data from different biological sites at the same time, or at different times.

[0078] If the first and second biometric data are acquired at different times, the biometric registration device 20 uses an imaging device externally connected to the registration device 4 to image the registrant's entire body at the same time as the first and second biometric data are acquired. By acquiring this whole-body image, it is possible to confirm that the first and second biometric data belong to the same person, thereby preventing fraud such as impersonation.

[0079] Figure 6 is a flowchart showing an example of the pre-registration process in Example 1. Figure 6 explains the registration of pre-registration data using a finger image as an example.

[0080] The pre-registration processing unit 200 accepts requests from registrants to launch a pre-registration application pre-installed on the pre-registration device 3, or to access a pre-registration site via the internet, and initiates pre-registration.

[0081] The personal information input section 201 accepts personal information from registered users, such as their name, address, and other membership information (S601).

[0082] The imaging control unit 202 displays the preview image from the camera of the pre-registration device 3 and guidance for aligning fingers on the screen of the pre-registration device 3 or on a display device connected to the pre-registration device 3 (S602).

[0083] The imaging control unit 202 controls the camera parameters and light source intensity of the pre-registered device 3 to acquire a hand image (S603).

[0084] The suitability determination unit 203 determines whether the finger image acquired from the pre-registration device 3 is suitable for the pre-registered biometric data (S604). This determination is made based on the presence or absence of fingers, finger posture, brightness of the finger image, and amount of biometric information contained in the finger region, which are determined from the acquired finger image through image processing, etc. The criteria for suitability are predetermined.

[0085] If the acquired finger image is determined to be unsuitable for the pre-registered biometric data (S604 is NO), the pre-registration processing unit 200 returns to S602 and displays the imaging guidance again.

[0086] If the acquired hand image is determined to be suitable for pre-registered biometric data (if S604 is YES), the feature extraction unit 204 extracts features for pre-registration (S605).

[0087] The feature extraction unit 204 extracts features from the finger image so that feature quantities are generated that can be mutually authenticated with the second biometric data captured by the registration device 4 with high accuracy. For example, if the second biometric data of the registration device 4 is a finger image captured by irradiating the finger with green visible light, the feature extraction unit 204 extracts features from the R component image, which is close to the second biometric data, among the RGB component images of the visible light finger image captured by the pre-registration device 3.

[0088] The feature extraction unit 204 may be configured to extract features at high speed by utilizing a computer equipped with a GPU.

[0089] After extracting the features, the pre-registration processing unit 200 records the features as candidate data in the work area (S606).

[0090] The pre-registration processing unit 200 determines whether the number of candidate data matches a predetermined number N (S607).

[0091] If the number of candidate data does not match the predetermined number N (if S607 is NO), the pre-registration processing unit 200 returns to S602 and displays the imaging guidance again.

[0092] If the number of candidate data matches the predetermined number N (if S607 is YES), the matching processing unit 205 matches multiple candidate data, confirms whether reproducible data has been obtained, and determines whether pre-registered biological data can be selected from the multiple candidate data (S608).

[0093] This process is for confirming that candidate data has been acquired reliably. For example, the matching processing unit 205 compares N candidate data and confirms that the matching results match sufficiently. If it does, the candidate data that best matches the other candidate data can be selected as the pre-registered biometric data.

[0094] Furthermore, having multiple candidate data sets allows for the selection of the candidate data that best matches the other candidate data, based on the amount of information about the biological features included in the posture and hand region of the living organism used in the S604 suitability judgment process, as the pre-registered biological data.

[0095] Furthermore, one pre-registered biological data set may be selected from among multiple candidate data sets, or multiple pre-registered biological data sets with different postures and other characteristics may be selected as candidate data sets. Having multiple pre-registered biological data sets makes it easier to match the second biological data acquired using the main registration device 4 during registration, thereby shortening the registration time.

[0096] If pre-registered biometric data could not be selected (S608 is NO), the pre-registration processing unit 200 determines whether a predetermined time (timeout period) has elapsed since the start of the pre-registration process (S611).

[0097] If it is determined that the timeout period has elapsed (if S611 is YES), the pre-registration processing unit 200 displays a failure of the pre-registration process (S612) and terminates the pre-registration process.

[0098] If it is determined that the timeout period has not elapsed (S611 is NO), the pre-registration processing unit 200 returns to S602 and displays the imaging guidance again. At this time, the pre-registration processing unit 200 erases all or part of the candidate data recorded in the work area.

[0099] If pre-registered biometric data can be selected (S608 is YES), the registration processing unit 206 registers pre-registered data in the pre-registration database 32, associating the personal information and the pre-registered biometric data (S609). At this time, the registration processing unit 206 issues a pre-registration code and assigns it to the registered data.

[0100] The pre-registration code output unit 207 outputs the pre-registration code to the pre-registration device 3 (S611), and the pre-registration process ends.

[0101] Furthermore, the process of determining the appropriateness of the finger image (S604) may be performed by the pre-registration device 3. This reduces the communication time required for transmitting the finger image and receiving the determination result, thus reducing the time required for the pre-registration process. In addition, the feature extraction process (S606) may also be performed by the pre-registration device 3.

[0102] Figure 7 is a flowchart showing an example of the registration process in Example 1. In Figure 7, the feature quantities extracted from the finger image are registered as pre-registered biometric data, and the registration of registration data using the finger image as the first biometric data and second biometric data will be explained as an example.

[0103] The input unit 301 accepts a pre-registration code from the main registration device 4 or an input device externally connected to the main registration device 4 (S701).

[0104] The registration processing unit 300 searches the pre-registration database 32 based on the pre-registration code and determines whether or not pre-registration data corresponding to the pre-registration code exists (S702).

[0105] If no pre-registration data exists (S702 is NO), the main registration processing unit 300 displays to the main registration device 4 that pre-registration processing is required (S710), and terminates the main registration processing. For example, the main registration device 4 may display a QR code that directs users to the pre-registration app or a QR code that directs users to the pre-registration site, or it may accept the email address of the registrant 1 and send the URLs of the pre-registration app and site to that email address.

[0106] If pre-registered data exists (if S702 is YES), the imaging control unit 302 controls the camera parameters and light source intensity of the registration device 4 to acquire a finger image as the first biological data (S703).

[0107] The imaging control unit 302 controls the camera parameters and light source intensity of the registration device 4 to facilitate matching with pre-registered biometric data, and acquires the finger image as second biometric data (S704).

[0108] The finger images captured by the pre-registered device 3 often show the veins of the fingers in an obscured manner, with wrinkles and melanin patterns on the finger surface being more prominent. In this case, the imaging control unit 302 refers to imaging information such as brightness, exposure, white balance, and light intensity at the time of capturing the finger image extracted from the pre-registered biological data, and performs light source control and camera parameter adjustments in the acquisition of the second biological data, irradiating only visible light so that the veins are less visible and wrinkles of the epidermis are more prominent.

[0109] The suitability determination unit 303 determines whether the data is suitable for registration based on the presence or absence of fingers, the posture of the fingers, the brightness of the fingers image, and the amount of biometric information contained in the finger region, which are obtained from the acquired finger image through image processing, etc. (S705).

[0110] If the acquired finger image is determined to be unsuitable for registration biometric data (S705 is NO), the registration processing unit 300 determines whether a predetermined time (timeout period) has elapsed since the start of the registration process (S711).

[0111] If it is determined that the timeout period has not elapsed (S711 is NO), the registration processing unit 300 returns to S703 and attempts to acquire the biometric data again.

[0112] If it is determined that the timeout period has elapsed (if S711 is YES), the registration processing unit 300 displays a registration failure (S712) and terminates the registration process.

[0113] In S705, if it is determined that the acquired finger image is suitable for registered biometric data (if S705 is YES), the feature extraction unit 304 extracts features from the second biometric data to facilitate matching with the pre-registered biometric data (S706).

[0114] For example, the feature extraction unit 304 extracts patterns such as wrinkles and melanin in the epidermis, and performs feature extraction in a way that does not extract features that are difficult to see, such as blood vessels.

[0115] The cross-referencing processing unit 306 compares the pre-registered biometric data contained in the retrieved pre-registered data with the features extracted from the second biometric data, and determines whether the features match the pre-registered biometric data (S707). For example, if the similarity of the features is greater than a threshold, it is determined that the features match the pre-registered data. The threshold can be set arbitrarily. For example, the threshold is 80 percent.

[0116] If the features extracted from the second biometric data do not match the pre-registered biometric data (if S707 is NO), the registration processing unit 300 determines whether the timeout period has elapsed (S711).

[0117] If it is determined that the timeout period has not elapsed (S711 is NO), the registration processing unit 300 returns to S703 and attempts to acquire the biometric data again.

[0118] If it is determined that the timeout period has elapsed (if S711 is YES), the registration processing unit 300 displays a registration failure (S712) and terminates the registration process.

[0119] In S707, if the features extracted from the second biometric data match those of the pre-registered biometric data (if S707 is YES), the feature extraction unit 304 extracts features from the first biometric data (S708).

[0120] The registration processing unit 307 registers the registration data, which associates the extracted features with the personal information contained in the retrieved pre-registered data, into the main registration database 31 (S714), and terminates the registration process. Features extracted from the second biometric data may also be included in the registration data. A high-performance authentication system can be realized by performing authentication using different biometric data.

[0121] (Variation 1) By using a pre-registration code, pre-registration data, including personal information entered by registrant 1, can be easily identified. However, problems may arise such as forgetting the pre-registration code or losing the storage medium on which it was recorded.

[0122] Therefore, the biometric registration device 20 may not accept the input of a pre-registration code, but instead use the main registration device 4 to acquire the second biometric data and compare it with multiple pre-registered biometric data recorded in the pre-registration database 32 to search for the pre-registered data. In this case, the biometric registration device 20 performs the aforementioned comparison in S705.

[0123] Since it eliminates the need to enter a pre-registration code, the registration process can be performed with simpler operations, which is expected to shorten the registration time.

[0124] Furthermore, by setting a limited retention period for pre-registered biometric data, the increase in the number of pre-registered data entries recorded in the pre-registration database 32 can be suppressed, and the matching process with pre-registered biometric data can be sped up even when a pre-registration code is not used.

[0125] (Variation 2) Figure 7 illustrates an example in which the first and second biological data are imaged at the same time, and the features extracted from the second biological data are registered only when they match the pre-registered biological data. This processing procedure may be modified so that the first biological data is acquired again only when the features extracted from the second biological data match the pre-registered biological data.

[0126] If a second set of biometric data is captured in a way that makes it easier to match pre-registered biometric data, the first set of biometric data captured at the same time may not be acquired under optimal conditions and in an optimal environment for the biometric authentication system. Therefore, if the features extracted from the second set of biometric data match those of the pre-registered biometric data, the first set of biometric data can be acquired again using imaging methods such as light source irradiation control for the biometric authentication system, enabling operation with a higher-performance biometric authentication system.

[0127] (Variation 3) In Figure 7, if the acquired first biometric data is suitable for registration, the registration data is registered using the first biometric data. This processing procedure may be changed so that if the first biometric data is determined to be unsuitable for registration, the first biometric data is acquired again until it is determined to be suitable. Even if the first biometric data acquired at the same time as the second biometric data cannot be registered as is, by acquiring additional first biometric data and continuing the registration process, a flexible registration process that maintains convenience and biometric authentication performance can be achieved.

[0128] (Variation 4) If the first and second biometric data are captured at different times, there is a concern about impersonation. Therefore, by acquiring both the first and second biometric data at different times and comparing the first or second biometric data acquired at different times, it is possible to guarantee that the person whose biological data was captured at different times is the same person. Alternatively, an imaging device externally connected to the registration device 4 may be used to capture the entire body of the person, and this image may be used to determine whether or not the person presenting the biological data to the registration device 4 is the same person.

[0129] (Variation 5) In Figure 7, registration of the registration data is not completed unless the features extracted from the pre-registered biometric data and the second biometric data match. This processing procedure may be modified so that, when the entered pre-registration code matches the personal information on the biometric registration device 20, the person who performed the pre-registration and the person presenting the biometric data to the main registration device 4 are considered to be the same person, and the main registration device 4 acquires the first biometric data and performs the registration process. In this case, the imaging of the pre-registered biometric data during pre-registration and the imaging of the second biometric data on the main registration device can be omitted, thus reducing the amount of work required for registration, making it simpler and shortening the time required for registration.

[0130] Figures 8A and 8B are flowcharts showing an example of the registration process in Example 1.

[0131] The biometric registration device 20 accepts a pre-registration code from the main registration device 4 or an input device externally connected to the main registration device 4 (S801).

[0132] The registration processing unit 300 searches the pre-registration database 32 based on the pre-registration code and determines whether or not pre-registration data corresponding to the pre-registration code exists (S802).

[0133] If no pre-registration data exists (S802 is NO), the main registration processing unit 300 displays to the main registration device 4 that pre-registration processing is required (S813), and terminates the main registration processing. For example, the main registration device 4 may display a QR code that directs users to the pre-registration app or a QR code that directs users to the pre-registration site, or it may accept the email address of the registrant 1 and send the URLs of the pre-registration app and site to that email address.

[0134] If pre-registered data exists (if S802 is YES), the imaging control unit 302 controls the camera parameters and light source intensity of the registration device 4 to acquire a finger image as the first biological data (S803).

[0135] The imaging control unit 302 controls the camera parameters and light source intensity of the registration device to facilitate matching with pre-registered biometric data, and acquires the finger image as second biometric data (S804).

[0136] The finger images captured by the pre-registered device 3 often show the veins of the fingers in an obscured manner, with wrinkles and melanin patterns on the finger surface being more prominent. In this case, the imaging control unit 302 refers to imaging information such as brightness, exposure, white balance, and light intensity at the time of capturing the finger image extracted from the pre-registered biological data, and performs light source control and camera parameter adjustments in the acquisition of the second biological data, such as irradiating only visible light so that the veins are less visible and the wrinkles of the epidermis are more prominent.

[0137] The suitability determination unit 303 determines whether the data is suitable for registration based on the presence or absence of fingers, the posture of the fingers, the brightness of the fingers image, and the amount of biometric information contained in the finger region, which are obtained from the acquired finger image through image processing, etc. (S805).

[0138] If the acquired finger image is determined to be unsuitable for registration biometric data (S805 is NO), the registration processing unit 300 determines whether a predetermined time (timeout period) has elapsed since the start of the registration process (S814).

[0139] If it is determined that the timeout period has not elapsed (S814 is NO), the registration processing unit 300 returns to S803 and attempts to acquire the biometric data again.

[0140] If it is determined that the timeout period has elapsed (if S814 is YES), the registration processing unit 300 displays a registration failure (S815) and terminates the registration process.

[0141] In S805, if it is determined that the acquired finger image is suitable for registered biometric data (if S805 is YES), the feature extraction unit 304 extracts features from the first biometric data and records the features of the first biometric data as candidate data in the work area (S806).

[0142] The registration processing unit 300 determines whether or not matching using the features of the second biological data has been performed (S807). If the process in S807 is performed for the first time, it is determined that matching has not been performed because the features of the second biological data have not been extracted.

[0143] If it is determined that matching using the features of the second biometric data is being performed (if S807 is YES), the registration processing unit 300 proceeds to S810.

[0144] If it is determined that matching using the features of the second biometric data has not been performed (S807 is NO), the features of the second biometric data are extracted (S808).

[0145] The matching processing unit 305 compares the pre-registered biometric data contained in the retrieved pre-registered data with the features extracted from the second biometric data and determines whether the features match the pre-registered biometric data (S809).

[0146] If the features extracted from the second biometric data do not match the pre-registered biometric data (S809 is NO), the registration processing unit 300 determines whether the timeout period has elapsed (S814).

[0147] If it is determined that the timeout period has not elapsed (S814 is NO), the registration processing unit 300 returns to S803 and attempts to acquire the biometric data again.

[0148] If it is determined that the timeout period has elapsed (if S814 is YES), the registration processing unit 300 displays a registration failure (S815) and terminates the registration process.

[0149] In S809, if the features extracted from the second biometric data match those of the pre-registered biometric data (if S809 is YES), the registration processing unit 307 determines whether the number of candidate data matches a predetermined number N' (S810).

[0150] If the number of candidate data does not match the predetermined number N' (if S810 is NO), the registration processing unit 300 determines whether the timeout period has elapsed (S814).

[0151] If it is determined that the timeout period has not elapsed (S814 is NO), the registration processing unit 300 returns to S803 and attempts to acquire the biometric data again.

[0152] If it is determined that the timeout period has elapsed (if S814 is YES), the registration processing unit 300 displays a registration failure (S815) and terminates the registration process.

[0153] In S810, if the number of candidate data matches the predetermined number N' (if S810 is YES), the matching processing unit 305 matches multiple candidate data, confirms whether reproducible data has been obtained, and determines whether registered biological data can be selected from among the multiple candidate data (S811).

[0154] In this process, registered biometric data that enables stable authentication is selected. For example, N′ candidate data are compared against each other, and if it is confirmed that the comparison results match sufficiently, the candidate data that best matches the other candidate data is selected as the registered biometric data.

[0155] If the registered biometric data cannot be selected (S811 is NO), the registration processing unit 300 determines whether the timeout period has elapsed (S814).

[0156] If it is determined that the timeout period has not elapsed (S814 is NO), the registration processing unit 300 returns to S803 and attempts to acquire the biometric data again.

[0157] If it is determined that the timeout period has elapsed (if S814 is YES), the registration processing unit 300 displays a registration failure (S815) and terminates the registration process.

[0158] If the registration biometric data can be determined in S811 (if S811 is YES), the registration processing unit 307 registers the registration data, which associates the selected registration biometric data with the personal information contained in the retrieved pre-registered data, in the pre-registration database 32 (S812), and terminates the registration process.

[0159] In Figure 8, a predetermined number of first biometric data points are acquired. If the features extracted from the second biometric data points, acquired at the same time as the first biometric data points, match those of the pre-registered biometric data points, the first biometric data points are selected, and registered data is created by associating the features extracted from that first biometric data point with personal information. Therefore, registrants have the significant advantage of being able to register their pre-registered personal information simply by performing the usual first biometric data registration process.

[0160] (Variation 1) In Figure 8, registration is not completed unless the feature quantities extracted from the second biometric data match the pre-registered biometric data. This processing procedure may be modified so that if data corresponding to the entered pre-registration code exists, the main registration processing unit 300 proceeds with the main registration process with the consent of the registrant. For example, if S809 is NO, a series of processes similar to S810-S812 are performed, with a process for receiving consent information between S811 and S812. In the process for receiving consent information, the personal information to be registered may be displayed on the display device 16 so that the registrant can confirm the contents such as name and address before entering the consent information. [Examples]

[0161] Example 2 describes a method for registering multiple pre-registered biometric data, including various posture patterns, in the biometric registration system 1000. In Example 2, a smartphone is used as the pre-registration device 3.

[0162] The posture of the biological body part significantly influences the matching of features in biological data. By comparing features extracted from a second set of biological data with multiple pre-registered biological data sets capturing various posture patterns of a given biological body part, the matching of biological data features becomes easier, and the time required for the matching process can be reduced.

[0163] First, let me explain the pre-registration process.

[0164] The personal information input unit 201 accepts personal information input from registered users using their smartphones.

[0165] Next, the imaging control unit 202 displays guidance on the smartphone so that various posture patterns of finger images can be acquired during biomedical imaging. Examples of various posture patterns include the finger posture patterns shown in Figure 9.

[0166] In the guidance display, the biometric registration device 20 may, in real time after acquiring a finger image, display guidance indicating which finger postures have already been acquired and which postures should be acquired for the remaining fingers. This encourages the registrant to more consciously present and acquire images of fingers in various postures.

[0167] The imaging control unit 202 acquires hand images in various posture patterns while controlling the smartphone.

[0168] The suitability determination unit 203 determines whether the acquired finger image is suitable for the pre-registered biometric data.

[0169] If the acquired finger image is suitable for pre-registered biometric data, the feature extraction unit 204 extracts features from the finger image and records the extracted features as candidate data in the work area.

[0170] The pre-registration processing unit 200 determines whether the number of recorded candidate data matches a predetermined number N, and whether the acquired biological data includes a predetermined posture pattern.

[0171] If the number of candidate data points does not match the predetermined number N, or if the acquired biological data does not include a predetermined posture pattern, the pre-registration processing unit 200 performs imaging again.

[0172] If the number of candidate data matches a predetermined number N, and the acquired biometric data includes a predetermined posture pattern, the pre-registration processing unit 200 selects multiple pre-registered biometric data from the candidate data.

[0173] The pre-registration processing unit 200 registers pre-registration data, which associates selected pre-registration biometric data with personal information, into the pre-registration database 32.

[0174] The pre-registration code output unit 207 outputs the pre-registration code to the smartphone.

[0175] In addition to the finger posture patterns shown in Figure 9, images of posture patterns that are intermediate between each finger posture may also be acquired, as shown in Figure 10.

[0176] Figures 11A and 11B show an example of a method for imaging fingers in Example 2.

[0177] During pre-registration, registrants use the rear camera to capture images of their fingers while viewing the smartphone screen. The biometric registration device 20 captures images of the fingers held below the smartphone, as shown in Figure 11A. On the other hand, the main registration device 4 is often installed in stores. Therefore, the biometric registration device 20 captures images of the fingers held over the main registration device 4.

[0178] In this case, because the method of presenting fingers differs between the main registration and the pre-registration, there is a large difference in posture during imaging, and there is a high possibility that the features extracted from the pre-registered biometric data and the second biometric data will not match.

[0179] To minimize differences in posture during image capture, for example, as shown in Figure 11B, during pre-registration, the smartphone should be placed on a horizontal surface with the display facing upwards, and the built-in front camera should be used to capture images of the fingers held above the smartphone.

[0180] This approach ensures that the hand presentation methods during registration and pre-registration are similar, increasing the likelihood of similar hand postures in the biometric data acquired from each device. As a result, the features extracted from the pre-registered biometric data and the second biometric data are more likely to match.

[0181] As practice for presenting an ideal posture, the biometric registration device 20 may image the body while displaying guidance on the pre-registration device 3. Since it is expected that the ideal posture will be presented during actual registration through this practice, it is not necessary to select biometric data of the ideal posture using the pre-registered biometric data and the second biometric data, and to register the first biometric data captured at the same time as the second biometric data. In other words, even without acquiring the pre-registered biometric data and the second biometric data, the first biometric data of the ideal posture can be registered at the time of registration. However, this is limited to cases where the pre-registered data can be identified using the pre-registration code, as it is necessary to identify personal information.

[0182] As shown in Figure 11B, in order to image fingers with similar postures during pre-registration and main registration, the ideal posture is conveyed to the registrant as guidance information during the pre-registration imaging. This increases the likelihood that fingers with a more ideal posture will be presented to the main registration device 4 during registration.

[0183] For example, when a registrant presents their fingers as shown in Figure 11B during pre-registration, the pre-registration processing unit 200 displays on the pre-registration device 3 the result of its determination of whether the presented finger posture is ideal. While performing the pre-registration process, the registrant can learn how to present their fingers before the actual registration, increasing the likelihood of presenting the ideal posture during the actual registration. Therefore, the time required for the actual registration can be shortened.

[0184] Similar to the pre-registered biological data in Example 2, the biological registration device 20 may also acquire images of various posture patterns of a predetermined biological organism for the first biological data and the second biological data.

[0185] By acquiring various posture patterns of a predetermined organism as second-level biometric data, it becomes easier to match these with pre-registered biometric data during the main registration process.

[0186] Furthermore, if biometric data representing various posture patterns is acquired as either the first or second biometric data, the posture changes can be calculated by cross-referencing this data, and the posture of the organism in each data can be determined from this. For example, an image with fingers extended straight can be determined as the data representing the posture closest to the ideal.

[0187] In other words, it is possible to determine biometric data that is close to the ideal posture without referring to other biometric data. Therefore, even if the first biometric data is acquired at a different time, it is possible to register the first biometric data that is estimated to be close to the ideal posture, thereby realizing a highly accurate authentication system.

[0188] If we can determine pre-registered biometric data that closely matches the ideal posture, then the first biometric data acquired at the same time as the second biometric data with the highest degree of agreement with that pre-registered biometric data is expected to also represent an ideal posture, thus enabling a highly accurate authentication system.

[0189] The processing flow involves the biometric registration device 20 determining whether the features of the second biometric data in S815 match the pre-registered biometric data, and also calculating the degree of agreement between the pre-registered biometric data of an ideal posture and the features of the second biometric data. In selecting the registration data in S818, the device registers the first biometric data acquired at the same time as the features of the second biometric data that have the highest degree of agreement with the pre-registered biometric data of an ideal posture. [Examples]

[0190] Example 3 describes a registration method for the biometric registration system 1000 when there is a large difference in the feature quantities of the data acquired during pre-registration and during actual registration.

[0191] In this embodiment, we take as an example the case in which a visible light image of the fingers captured using a smartphone is used as pre-registered biometric data, an infrared light image captured by irradiating the fingers with infrared light using the registration device 4 is used as the first biometric data, and a visible light image captured by irradiating the fingers with visible light is used as the second biometric data.

[0192] In infrared imaging, blood vessels can sometimes be difficult to see due to factors such as cold. It is desirable to perform high-performance authentication even when blood vessels are difficult to see in infrared imaging.

[0193] Therefore, assuming that the blood vessels observable in visible light images are a pseudo-reproduction of blood vessels that are easily and stably observed in infrared light images even when blood vessels become difficult to see due to the effects of cold, the first biological data (infrared light image) is registered using the blood vessel pattern observed in visible light images.

[0194] For example, after determining whether the features extracted from the second biometric data (visible light image) acquired during registration match the previously recorded pre-registered biometric data, the blood vessel pattern is extracted from each visible light image.

[0195] The system compares vascular patterns extracted from visible light images with those extracted from multiple infrared images, and registers the infrared image containing the most vascular patterns extracted from the visible light images as the registered data. By registering infrared images that contain many stable vascular patterns also observed in visible light images, high-performance authentication can be achieved in practical use.

[0196] By registering vascular patterns extracted from visible light images, authentication can be performed even when vascular patterns are less visible. However, as mentioned above, vascular patterns are difficult to see in visible light images, making authentication difficult when vascular patterns are clearly visible. Therefore, as the first biometric data (infrared light image), vascular patterns extracted from infrared light images containing many vascular patterns and vascular patterns extracted from visible light images containing few vascular patterns are registered. By registering multiple vascular patterns in this way, highly accurate authentication can be achieved in both situations where vascular patterns are clearly visible and situations where they are not.

[0197] When only a few blood vessels are observed in a visible light image, the number of extracted blood vessel patterns becomes very small. When there are few blood vessel patterns extracted from a visible light image, it becomes difficult to determine that the blood vessel patterns extracted from an infrared light image and the blood vessel patterns from a visible light image are the same biological information.

[0198] Therefore, in order to determine that the blood vessel pattern extracted from the visible light image matches the blood vessel pattern extracted from the infrared light image and that they belong to the same organism, the blood vessel region of the blood vessel pattern extracted from the visible light image is expanded using image processing or other methods.

[0199] By registering vascular patterns that have undergone vascular region expansion processing, rather than directly registering the vascular patterns extracted from visible light images, it is possible to ensure that multiple registered data points represent the same organism while allowing for variations in the amount of vascular patterns when registering multiple vascular patterns.

[0200] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. Furthermore, for example, the embodiments described above are detailed explanations of the configuration in order to clearly illustrate the present invention, and are not necessarily limited to those having all the configurations described. In addition, some of the configurations in each embodiment can be added to, deleted from, or replaced with other configurations.

[0201] Furthermore, some or all of the above-described configurations, functions, processing units, and processing means may be implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, and ROMs.

[0202] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, Python, and Java (registered trademark).

[0203] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium. [Explanation of symbols]

[0204] 1 Registered users 2 fingers 3. Pre-registration device 4. Main Registration Device 5 light source 6. Biomedical imaging device 7. Image input device 9 Faces 10 Storage medium 11 Interfaces 12 memory 13 processors 14 Input devices 15 speakers 16 Display device 17 Auxiliary storage 20 Biological Registration Device 31. Database for official registration 32 Pre-registration database 32 Databases 1000 Biometric Registration System

Claims

1. A biometric registration system, The system comprises a computing device, a storage device connected to the computing device, and a network interface connected to the computing device. It connects to the user's own device and to a registration device installed in the store of a business that provides biometric authentication services. The terminal includes a first acquisition device for acquiring the user's biometric data. The registration device includes a second acquisition device for acquiring the user's biometric data. The aforementioned biometric registration system is The terminal receives input of the user's personal information, controls the first acquisition device to acquire the first biometric data of the user who has entered the personal information, A first feature is extracted from the first biological data mentioned above. The pre-registered data relating the aforementioned personal information and the first feature quantity is registered in the storage device. When a registration procedure using the registration device is initiated, the second acquisition device is controlled to acquire from the user performing the registration procedure a second biometric data for extracting a feature to be used for matching with the first feature, and a third biometric data for extracting a feature to be used when using the service. The second and third features are extracted from the second and third biological data, respectively. The first feature and the second feature included in the pre-registered data are compared, A biometric registration system characterized by registering registration data in the storage device that associates the personal information contained in the pre-registered data corresponding to the first feature that matches the second feature with the third feature.

2. A biological registration system according to claim 1, A biological registration system characterized by controlling the second acquisition device in consideration of the acquisition conditions for the first biological data in the first acquisition device.

3. A biological registration system according to claim 2, A biological registration system characterized in that the first biological data, the second biological data, and the third biological data are images of biological body parts.

4. A biological registration system according to claim 3, The first acquisition device acquires an image of the biological site by irradiating it with visible light. The second acquisition device acquires an image of the biological site by irradiating it with at least one of visible light and infrared light. The aforementioned biometric registration system is The first acquisition device is controlled to acquire the image of the biological part acquired by the first acquisition device as first biological data. The second acquisition device is controlled to irradiate with visible light, and the image of the biological part acquired by the second acquisition device is acquired as the second biological data. A biological registration system characterized by controlling the second acquisition device to irradiate infrared light, and acquiring the image of the biological part acquired by the second acquisition device as the third biological data.

5. A biological registration system according to claim 3, The first acquisition device acquires an image of the biological site by irradiating it with visible light. The second acquisition device acquires an image of the biological site by irradiating it with at least one of visible light and infrared light. The aforementioned biometric registration system is The first acquisition device is controlled to acquire the image of the biological part acquired by the first acquisition device as first biological data. The second acquisition device is controlled to simultaneously irradiate with infrared light and visible light, and an image of the biological site acquired by the second acquisition device is obtained. A biological registration system characterized by performing wavelength separation processing on the image of the biological site acquired from the second acquisition device, thereby acquiring an image of the biological site in visible light as the second biological data, and an image of the biological site in infrared light as the third biological data.

6. A biological registration system according to claim 2, When registering the aforementioned pre-registration data, a pre-registration code is generated. The pre-registration data, which associates the personal information, the first feature quantity, and the pre-registration code, is registered in the storage device. The aforementioned pre-registration code is notified to the terminal, In the aforementioned registration procedure, the input of the aforementioned pre-registration code is accepted. Based on the pre-registration code entered, the pre-registration data stored in the storage device is searched. A biometric registration system characterized by comparing the first feature and the second feature contained in the pre-registration data corresponding to the pre-registration code that has been entered.

7. A biological registration system according to claim 2, Multiple first biological data are acquired, The pre-registered data, which associates the first feature quantities extracted from each of the multiple first biometric data sets with the personal information, is registered in the storage device. A biometric registration system characterized by comparing each of the multiple first features included in the pre-registered data with the second feature.

8. A biological registration system according to claim 7, A biological registration system characterized in that the multiple first biological data sets differ in the posture of the biological body in the image of the biological body.

9. A biological registration system according to claim 8, A biological registration system characterized by displaying guidance information on the terminal for presenting biological body parts in different postures.

10. A biological registration system according to claim 2, Multiple first biological data are acquired, A biometric registration system characterized by comparing each of a plurality of first biometric data and selecting one of the first biometric data based on the result of the comparison.

11. A biometric registration method performed by a biometric registration system, The aforementioned biometric registration system is It has a computing device, a storage device connected to the computing device, and a network interface connected to the computing device, It connects to the user's own device and to a registration device installed in the store of a business that provides biometric authentication services. The terminal includes a first acquisition device for acquiring the user's biometric data. The registration device includes a second acquisition device for acquiring the user's biometric data. The aforementioned biometric registration method is The biometric registration system receives input of the user's personal information from the terminal, controls the first acquisition device, and acquires the first biometric data of the user who has entered the personal information. The biometric registration system includes the step of extracting a first feature from the first biometric data, The biometric registration system includes the step of registering pre-registered data relating the personal information and the first feature quantity in the storage device, When a registration procedure using the registration device is initiated, the biometric registration system controls the second acquisition device to acquire from the user performing the registration procedure a second biometric data for extracting a feature to be used for matching with the first feature, and a third biometric data for extracting a feature to be used when using the service. The biometric registration system includes the steps of extracting a second feature and a third feature from the second biometric data and the third biometric data, The biometric registration system includes the step of comparing the first feature and the second feature included in the pre-registered data, A biometric registration method characterized in that the biometric registration system includes the step of registering registration data in the storage device that associates the personal information contained in the pre-registered data corresponding to the first feature that matches the second feature with the third feature.

Images