WO2004068413A1 - 生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム - Google Patents
生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム Download PDFInfo
- Publication number
- WO2004068413A1 WO2004068413A1 PCT/JP2003/000774 JP0300774W WO2004068413A1 WO 2004068413 A1 WO2004068413 A1 WO 2004068413A1 JP 0300774 W JP0300774 W JP 0300774W WO 2004068413 A1 WO2004068413 A1 WO 2004068413A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- registration
- matching
- information
- feature information
- unit
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Definitions
- Biometric information registration device biometric information verification device, biometric information registration / verification system, and biometric information registration program
- the present invention provides biological information (piometric information) such as fingerprint, palm print, iris (iris muscle pattern), voice, face image, blood vessel pattern (retinal retinal vascular network, venous vascular network), dynamic signature, and keystroke.
- biological information such as fingerprint, palm print, iris (iris muscle pattern), voice, face image, blood vessel pattern (retinal retinal vascular network, venous vascular network), dynamic signature, and keystroke.
- piometritus authentication using human biometric information has been widely used as a more reliable means of identity verification than ID card / password.
- fingerprints, palm prints, irises, face images, voices, blood vessel patterns, dynamic signatures, keystrokes, and the like are used as living body information.
- biometric authentication technology using fingerprints is the most practical.
- the person to be authenticated inputs an ID such as a user name and a fingerprint, reads registered fingerprint data registered in advance corresponding to the ID, and then authenticates the registered fingerprint data.
- ID such as a user name and a fingerprint
- One-to-one authentication is used, in which personal authentication is performed by comparing fingerprint data entered by the subject.
- one-to-one authentication requires a keyboard and a keypad for inputting IDs, in addition to the fingerprint sensor, and thus requires equipment costs.
- One-to-many authentication is an authentication technology that identifies a person by entering only their fingerprint without entering their ID. Called.
- this one-to-many authentication generally, all the registered fingerprint data registered in advance are compared with the fingerprint data input by the person to be authenticated, and a fingerprint matching the input fingerprint data is identified from the registered fingerprint data.
- the person to be certified is specified, and the person to be certified is authenticated.
- the time required for the collation processing between all the registered fingerprint data and the input fingerprint data naturally increases. Therefore, it is desired to reduce the collation processing time. It is rare.
- Patent Document 1 Japanese Patent Application Laid-Open No. 2002-133416
- attribute information other than fingerprint data used for matching for example, fingerprint pattern type; see FIGS. 6A to 6H
- a registered fingerprint is detected based on the attribute information.
- the data is classified in advance, and registered fingerprint data having the same attribute information as the attribute information (pattern type) obtained from the person to be authenticated at the time of matching is compared with the input fingerprint data.
- fingerprint pattern types are used as attribute information
- registered fingerprint data cannot be classified into groups of the number n of pattern types (eight types in the examples shown in FIGS. 6A to 6H) and cannot be classified. Therefore, the matching processing time can be reduced only to about 1 / n.
- the present invention has been devised in view of such a problem, and when performing one-to-many authentication using biometric information, realizes a considerable reduction in the time required for the matching process between registered feature information and input feature information.
- the purpose is to: Disclosure of the invention
- a biometric information registration device of the present invention includes a registration biometric information input unit that collects and inputs registration biometric information used for one-to-many authentication from a registration target person; A registration feature information extraction unit that extracts registration feature information from the registration biometric information input by the registration unit; and the registration feature information from the registration biometric information input by the registration biometric information input unit.
- a registration attribute information extraction unit for extracting a plurality of types of registration attribute information different from the registration attribute information extracted by the registration attribute information extraction unit and the registration attribute information extraction unit Is And a registration unit for registering the plurality of types of registration attribute information in association with each other.
- the biometric information matching device of the present invention includes a matching biometric information input unit that collects and inputs matching biometric information for performing one-to-many authentication from a person to be authenticated, and a matching biometric information input unit.
- a matching feature information extracting unit that extracts matching feature information from the matching biometric information that has been input, and the matching feature information from the matching biometric information input by the matching biometric information input unit.
- a matching attribute information extracting unit that extracts a plurality of different types of matching attribute information, and a plurality of registration feature information items to be matched with the matching feature information extracted by the matching feature information extracting unit.
- the collation priority is divided into a plurality of types of registration attribute information associated with each of the plurality of registration characteristic information and the plurality of types of collation attribute information extracted by the collation attribute information extraction unit. Based The matching priority calculating unit to be calculated, and the matching feature information extracted by the matching feature information extracting unit are sequentially registered in accordance with the matching priority calculated by the matching priority calculating unit.
- a feature is provided in which a matching unit is provided which can identify, from the plurality of pieces of registration feature information, one that matches the matching feature information by matching with the matching feature information.
- the biometric information registration / verification system of the present invention includes a registration biometric information input unit that collects and inputs registration biometric information used for one-to-many authentication from a registration target person, and a registration biometric information input unit.
- the registration feature information extraction unit that extracts the registration feature information from the registration biometric information input as described above, and the registration feature information from the registration biometric information input by the registration biometric information input unit
- a registration attribute information extraction unit for extracting a plurality of different types of registration attribute information; the registration feature information extracted by the registration feature information extraction unit; and the plurality of types extracted by the registration attribute information extraction unit
- a registration unit for registering the registration attribute information in association with the registration attribute information, and the registration feature information and the plurality of types of registration attribute information registered and associated with the registration unit.
- a registration data storage unit a verification biometric information input unit that collects and inputs verification biometric information for performing the one-to-many authentication from a person to be authenticated, and the verification biometric information input unit input by the verification biometric information input unit.
- a matching feature information extraction unit for extracting matching feature information from the matching biometric information; and the reference input by the matching biometric information input unit.
- a matching attribute information extracting unit that extracts a plurality of types of matching attribute information different from the matching feature information from the combined biometric information; and a pre-speech matching feature extracted by the matching feature information extracting unit.
- the collation priority order of the plurality of registration feature information stored in advance in the registration data storage unit to be collated with the information is set to the plurality of registration feature information associated with each of the plurality of registration feature information.
- a matching priority calculating unit that calculates based on the type of registration attribute information and the plurality of types of matching attribute information extracted by the matching attribute information extracting unit; and a matching feature information extracting unit. By sequentially comparing the extracted matching feature information with the plurality of registration feature information in accordance with the matching priority calculated by the matching priority calculation unit, the plurality of registration features are obtained.
- a matching unit that can identify a match with the matching feature information from.
- the biometric information registration program of the present invention is for registering registration biometric information collected from a registration target person in a registration data storage unit for use in one-to-many authentication.
- the computer functions as an extraction unit, a registration attribute information extraction unit, and a registration unit.
- biometric information registration device when performing one-to-many authentication using biometric information, matching of a plurality of registration feature information is performed.
- the priority is calculated based on a plurality of types of registration attribute information associated with each of the registration feature information and a plurality of types of matching attribute information extracted from the biometric information of the person to be authenticated.
- the matching feature information extracted from the biometric information of the authentication target is sequentially matched with the registration feature information according to the calculated matching priority, and the matching feature information is selected from a plurality of registration feature information. Those that match the information are identified.
- the registration feature information of the target person can be determined, and the time required for the matching process (number of times of matching) can be significantly reduced, and the accuracy of matching can be improved.
- FIG. 1 is a block diagram showing a functional configuration of a fingerprint data registration device (biological information registration device) as one embodiment of the present invention.
- FIG. 2 is a block diagram showing a functional configuration of a fingerprint data matching device (biological information matching device) as one embodiment of the present invention.
- FIG. 3 is a block diagram illustrating a hardware configuration of the fingerprint authentication device (biological information registration Z matching device) according to the present embodiment.
- FIG. 4 is a block diagram illustrating a hardware configuration of the fingerprint authentication system (biological information registration / collation system) according to the present embodiment.
- FIG. 5 is a diagram for explaining data contents in the registration data storage unit of the present embodiment.
- 6A to 6H are diagrams each showing a specific example of a fingerprint in order to explain a fingerprint pattern type as attribute information in the present embodiment.
- FIG. 7 is a diagram for explaining the shape of a finger as attribute information in the present embodiment.
- Figures 8A, 9A, and 10A show examples of fingerprint images of fingers with different water contents (low, medium, and high), respectively.
- FIGS. 8B, 9B, and 10B are graphs showing the luminance of the fingerprint image examples of FIGS. 8A, 9A, and 10A, respectively.
- FIG. 11 is a flowchart for explaining the fingerprint data registration procedure (operation of the fingerprint data registration device) in the present embodiment.
- FIG. 12 is a flowchart for explaining the fingerprint data collation procedure (operation of the fingerprint data collation device) in the present embodiment.
- FIG. 13 and FIG. 14 are diagrams for explaining the comparison priority calculating procedure in the present embodiment.
- FIG. 15 is a flowchart for explaining a modification of the fingerprint data collation procedure (operation of the fingerprint data collation device) in the present embodiment.
- FIG. 16 is a flowchart for explaining a modification of the collation priority calculation procedure in the present embodiment.
- FIG. 17 and FIG. 18 are diagrams for explaining a modification of the collation priority calculation procedure in the present embodiment.
- FIG. 19 is a block diagram showing a functional configuration of a modification of the fingerprint data matching device (biological information matching device) in the present embodiment.
- the present invention is realized, for example, as a fingerprint authentication device (biological information registration / verification device) 10 as shown in FIG. 3 or a fingerprint authentication system (biometric information registration / verification system) as shown in FIG. .
- FIGS. 3 and 4 are block diagrams showing a hardware configuration of the fingerprint authentication device and the fingerprint authentication system, respectively.
- the fingerprint authentication device 10 shown in FIG. 3 has a function as a fingerprint data registration device (biological information registration device) described later with reference to FIG. 1 and a fingerprint data verification device (biological information registration device) described later with reference to FIG. It has a function as an information collating device) and is configured by connecting a fingerprint sensor 14 to a personal computer.
- This personal computer is configured by connecting at least CPU 11, memory (ROM, RAM) 12, input / output interface 13, and storage device (hard disk etc.) 15 via path 16.
- the fingerprint sensor 14 is also connected to the CPU 11 via the bus 16.
- any type such as a capacitance type, an optical type, and a thermal type may be used.
- the storage device 15 of the fingerprint authentication device 10 stores a fingerprint registration / verification program (biological information registration / verification program) 15a, and the storage device 15 is shown in FIG.
- a registration data storage unit 15b the registered fingerprint data (characteristic information for registration) extracted from the fingerprint registrant and the registration attribute information are stored in association with the ID of the fingerprint registrant. Plays a function.
- the CPU 11 of the fingerprint authentication device 10 reads out and executes the fingerprint registration Z matching program 15a stored in the storage device 15 so that the fingerprint data registration device (biological information) described later with reference to FIG.
- the function as an information registration device) and the function as a fingerprint data matching device (biological information matching device) described later with reference to FIG. 2 are realized.
- the registration data extracted from the registration target person using the fingerprint sensor 14 is registered and stored in the storage device 15 (registration data storage unit 15b). While the registration process (details will be described later) is performed, the matching data extracted from the person to be authenticated using the fingerprint sensor 14 and the registration data in the storage device 15 (registration data storage unit 15b) are used.
- a collation process personal authentication; details will be described later is performed based on the collation process.
- the fingerprint authentication system (biological information registration / verification system) shown in FIG. 4 includes a fingerprint authentication device 10 A that functions as a fingerprint data registration device (biological information registration device) described later with reference to FIG.
- the fingerprint authentication server 20 which functions as a fingerprint data collation device (biological information collation device) described later with reference to FIG. 2 and the fingerprint authentication device 10A and the fingerprint authentication server 20 can communicate with each other. It is configured with a LAN (Local Area Network) 30 to be connected.
- LAN Local Area Network
- the fingerprint authentication device 10 A has at least a CPU 11, a memory (ROM, RAM) 12, an input / output interface 13, and a storage device (such as a hard disk) 15, similarly to the fingerprint authentication device 10 shown in FIG.
- a CPU 11 a central processing unit (CPU)
- ROM read-only memory
- RAM random access memory
- storage device such as a hard disk
- This is configured by connecting a fingerprint sensor 14 of a capacitance type, an optical type, a thermal type, or the like to a general personal computer configured by connecting each other by a path 16.
- a fingerprint registration program (biological information registration program) 15c is stored in the storage device 15 of the fingerprint authentication device 1OA, and the CPU 11 of the fingerprint authentication device 10A reads out the fingerprint registration program 15c.
- a function as a fingerprint data registration device (biological information registration device) described later with reference to FIG. 1 is realized.
- the fingerprint authentication server 20 has at least a CPU 21, a memory (ROM, RAM) 22, an input / output interface 23, and a storage device (such as a hard disk) 25. It consists of a general server device (personal computer) configured by connecting each other by a path 26, and a fingerprint sensor 24 such as a capacitance type, optical type, or thermal type. .
- the storage device 25 of the fingerprint authentication server 20 stores a fingerprint collation program (biological information collation program) 25a.
- the storage device 25 is similar to the storage device 15 shown in FIG. As will be described later with reference to FIG. 5, enrollment data for storing enrolled fingerprint data (enrollment feature information) and enrollment attribute information extracted from an enrolled fingerprint in association with the ID of the enrolled fingerprint. It functions as the storage unit 25b.
- the CPU 21 of the fingerprint authentication server 20 reads out and executes the fingerprint collation program 25a stored in the storage device 25, so that fingerprint data collation described later with reference to FIG.
- the function as a device biological information matching device
- the fingerprint authentication device 10A sends the registration data extracted from the registration target using the fingerprint sensor 14 via the RAN 30 to the fingerprint.
- a registration process (details will be described later) for registering and storing in the storage device 25 (registration data storage unit 25b) of the authentication server 20 is executed.
- the person to be authenticated inputs a fingerprint image using the fingerprint sensor 14 connected to the fingerprint authentication device 1 OA or the fingerprint sensor 24 connected to the fingerprint authentication server 20.
- the fingerprint authentication server 20 sends the collation data extracted from the fingerprint image of the person to be authenticated and the registration data in the storage device 25 (registration data storage unit 25 b).
- the collation processing (details will be described later) is performed based on the.
- the functional configuration of the fingerprint data registration device (biological information registration device) and the fingerprint data matching device (biometric information matching device) of the present embodiment which is realized by the hardware configuration shown in FIGS. Will be described with reference to the block diagrams shown in FIGS. 1 and 2, respectively.
- the symbols without parentheses are realized by the hardware configuration (fingerprint authentication device 10) shown in FIG.
- the parenthesized code is added to the functional configuration realized by the hardware configuration (fingerprint authentication system) shown in FIG. If the code without parentheses and the code with parentheses are the same, the notation of the code with parentheses may be omitted.
- the fingerprint data registration device of the present embodiment shown in FIG. 1 includes a fingerprint sensor 14 (14), a fingerprint data extraction unit for registration 1 la (11a), a registration attribute information extraction unit 1 lb (lib), a registration unit lie. (lie) and a registration data storage unit 15b (25b).
- the functions of the fingerprint data extraction unit for registration 1 la (11a), the attribute information extraction unit for registration lib (lib) and the registration unit lie (lie) are as follows. This is realized by executing (fingerprint registration program 15c).
- the fingerprint sensor 14 is a sensor of a capacitance type, an optical type, a thermal type, or the like as described above.
- the fingerprint sensor 14 is obtained by collecting a fingerprint image for registration as biometric information for registration used for one-to-many authentication from a person to be registered. It functions as a biometric information input section for registration (fingerprint information input section) to be input to 11.
- the fingerprint data extracting unit for registration (characteristic information extracting unit for registration) 11a is a fingerprint image for registration input by the fingerprint sensor 14 using, for example, the minutia method disclosed in Japanese Patent Laid-Open No. 1-195119. Then, as the registered fingerprint data (characteristic information for registration), the information about the characteristic points of the ridges in the fingerprint image is extracted. Specifically, the information on the feature points includes the position, type (end point, branch point) and direction of the feature point, and the position of the projected feature point obtained by projecting the feature point on a ridge.
- the registration attribute information extraction unit 11b includes a plurality of types of registration attribute information different from the registration fingerprint data extracted by the registration fingerprint data extraction unit 11a from the registration fingerprint image input by the fingerprint sensor 14. Is extracted.
- the attribute information extraction unit for registration 11b includes, for each type of attribute information for registration to be extracted, attribute information extraction units 11b—1, lib—2, and lib—3 for extracting the attribute information. , ... are provided.
- the registration attribute information for example, two or more of the following (1) to (4) are extracted.
- the fingerprint pattern types in the fingerprint image for registration in 1 are, for example, the eight types shown in Figs. 6A to 6H (that is, right bag type, left bag type, twin type, wave type, vortex type, left flow type). Type, right-flow type, Katsura type).
- Such a pattern type extraction method is disclosed, for example, in Japanese Patent Application Laid-Open No. 2002-133334.
- 6A to 6H are diagrams each showing a specific example of a fingerprint to explain the fingerprint pattern type as the attribute information in the present embodiment.
- the shape of the finger in 2 is defined as shown in Fig. 7, for example. That is, as shown in FIG. 7, the shape of the finger in contact with the sensor surface of the fingerprint sensor 14 is defined and extracted as the horizontal length X and the vertical length y of the rectangle circumscribing the fingerprint image. .
- FIG. 7 is a diagram for explaining the shape of the finger as the attribute information in the present embodiment.
- the number of feature points of (3) can be obtained by counting the number of feature points extracted from the registered fingerprint image using the minutiae method by the fingerprint data extracting unit for registration 11a.
- the data amount of 4 is obtained by measuring the registered fingerprint data extracted by the registration fingerprint data extraction unit 11 a using the minutiae method
- the processing time of 5 is determined by the registration fingerprint data. It is obtained by measuring the time required for extracting the registered fingerprint data by the extracting unit 11a using the above-mentioned Mauscha method.
- a capacitance-type fingerprint sensor is used as the fingerprint sensor 14, the brightness of the output image changes according to the water content on the finger surface.
- FIGS. 8A, 9A, and 10A show examples of fingerprint images of fingers having different water contents (low, medium, and high), respectively.
- Figure 10B is the fingerprint of Figure 8A, Figure 9A and Figure 10A, respectively.
- 9 is a graph showing the luminance of an image example.
- a fingerprint image with a low brightness level is collected as shown in FIGS. 8A and 8B, while in the case of a finger with a high water content, as shown in FIGS. 10A and 10B.
- a fingerprint image with a high luminance level is collected.
- a fingerprint image with a medium (standard) brightness level is collected as shown in Figs. 9A and 9B.
- the gain of the output from the fingerprint sensor 14 is generally corrected in accordance with the luminance state.
- the gain correction amount calculated at the time of such correction is a value equivalent to the moisture amount on the finger surface, and the moisture amount on the finger surface of 6 can be extracted as the gain correction amount.
- Input environment information of the fingerprint image for registration can be obtained as registration attribute information.
- the input environment information is, specifically, the IP (Internet Protocol) address of the personal computer, the user name of the user who is logged in, and the like.
- the registration unit 11e associates the registered fingerprint data extracted by the registration fingerprint data extraction unit 11a with a plurality of types of registration attribute information extracted by the registration attribute information extraction unit 11b, and registers the registration data. It is registered in storage unit 15b (25b). More specifically, as shown in FIG. 5, in the registration data storage unit 15b (25b), the registered fingerprint data extracted from the registered fingerprint image of the fingerprint registrant and a plurality of types (in FIG. 5, The three types of registration attribute information are associated with the fingerprint registrant's ID, registered in a table format, and stored.
- FIG. 5 is a diagram for explaining the data contents in the registration data storage unit 15b (25b) of the present embodiment.
- the ID ID1, ID2, ID3
- registered fingerprint data fingerprint data
- three types of attribute information a for example, pattern type; attribute a1, a2, a3)
- b eg, number of feature points; attributes b1, b2, b3)
- c eg, water content; attributes
- the registration unit 11 e stores registration fingerprint data and a plurality of types of registration data in a storage device 15 (registration data storage unit 15 b) built in the same personal computer.
- the registration unit 11 e communicates with the storage device 25 (the registration data storage unit 25 b) in the fingerprint authentication server 20 via the communication line (LAN 30). In), register fingerprint data and multiple types of registration attribute information.
- the fingerprint data matching device of the present embodiment shown in FIG. 2 includes a fingerprint sensor 14 (24), a matching fingerprint data extracting unit 11a (21a), a matching attribute information extracting unit 11b (21b), a registration data It consists of a read control unit 11c (21c), a collation processing unit lid (2Id), a collation result output unit 13 (23), and a registration data storage unit 15b (25b).
- a fingerprint data extraction unit for verification 11a (21a), the attribute information extraction unit for verification 11b (21b), the registration data readout control unit 11c (21c), and the verification processing unit lid ( The function as 2Id) is realized by the CPU 11 (21) executing the fingerprint registration Z matching program 15a (fingerprint matching program 25a).
- the fingerprint sensor 14 (24) is a sensor of the capacitance type, optical type, thermal type, etc., and obtains a fingerprint image for verification as biometric information for verification for one-to-many authentication from a person to be authenticated.
- the fingerprint data extraction unit for collation (characteristic information extraction unit for collation) 11a (21a) is input by the fingerprint sensor 14 (24) using, for example, the minutiae method disclosed in Japanese Patent Application Laid-Open No. H11-195119.
- collation fingerprint data (characteristic information for collation) is extracted.
- the collated fingerprint data extracted here is of the same type as the registered fingerprint data registered in advance in the registration data storage unit 15b (25b).
- the ridges in the fingerprint image are Information on feature points The position, type (end point, bifurcation point) and direction of the feature point, and the position of the projected feature point obtained by projecting the feature point on the ridge].
- the matching attribute information extracting unit 11 b (21 b) extracts the matching fingerprint extracted by the matching fingerprint data extracting unit 1 la (21 a) from the matching fingerprint image input by the fingerprint sensor 14 (24). It extracts multiple types of matching attribute information different from data.
- the matching attribute information extracting unit 11b (21b) includes, for each type of matching attribute information to be extracted, an attribute information extracting unit 1lb-1 (21b-1) for extracting the attribute information. , Lib-2 (21 b-2), lib-3 (21 b-3), ... are provided.
- the matching attribute information for example, of the following (1) to (4), the same type as the registration attribute information extracted by the registration attribute information extracting unit 11a shown in FIG. 1 is extracted.
- the method for extracting the attribute information for matching 1 to 7 is the same as the method for extracting the attribute information for registration 1 to ⁇ described in item [2-1], and a description thereof will be omitted.
- the registration data read control unit 11c (21c) has a function as a collation priority calculation unit described later, and registers the registered fingerprint data according to the collation priority calculated by the function as the collation priority calculation unit.
- the data is sequentially read from the registration data storage unit 15b (25b) and input to the matching processing unit 11d (2Id).
- the collation priority calculating section includes a registration data storage section 15b (25) to be collated with the collation fingerprint data extracted by the collation fingerprint data extraction section 1la (21a).
- the comparison priority of the plurality of registered fingerprint data stored in advance in b) is stored in the registration data storage unit 15b (25b) in association with each of these registered fingerprint data. This is calculated based on the type of registration attribute information and the plurality of types of matching attribute information extracted by the matching attribute information extracting unit 11b (21b).
- the collation priority calculation unit calculates and determines the collation priority by one of the following two methods (1) and (2).
- Method (1) First, a plurality of types of matching attribute information and a plurality of types of registration attribute information associated with each registered fingerprint data are compared with each other to judge whether or not they match. Then, for each of the registered fingerprint data, of the plurality of types of registration attribute information associated with the registered fingerprint data, the weighting factors previously assigned to those determined to match the matching attribute information are summed up, The total value is calculated as the attribute information matching score for the registered fingerprint data. The matching priority is determined according to the order of the attribute information matching score calculated for each registered fingerprint data in this way. This method (1) will be specifically described with reference to FIGS. 13 and 14.
- Method (2) Similar to method (1), first, a plurality of types of matching attribute information and a plurality of types of registration attribute information associated with each registered fingerprint data are compared and matched. Determine whether or not. Then, of the plurality of types of registration attribute information, the collation priority is determined according to the priority given in advance to the one determined to match the collation attribute information, and the registered fingerprint data is rearranged according to the collation priority. Perform This method (2) will be specifically described with reference to FIGS.
- the collation processing unit (collation unit) lid (21 d) calculates the collation fingerprint data extracted by the collation fingerprint data extraction unit 11a (21a) by the function as the collation priority calculation unit.
- a matching fingerprint data is identified from the plurality of registered fingerprint data, and the matching result (specific result) is output to a matching result output unit. 13 (23).
- the collation processing unit 1 I d (21 d) reads the collation fingerprint data by the enrollment data reading control unit 11 c (21 c).
- the collation priority is given by sequentially collating with the issued registered fingerprint data.
- the collation according to is automatically performed.
- the fingerprint matching method by the matching processing unit 1 I d (21 d) for example, a general method such as a mushy method or a pattern patching method is used, but it is particularly limited to these methods. Instead, any fingerprint matching method may be adopted.
- the matching processing unit l id (2 I d) specifies the fingerprint data to be matched by one of the following two methods (i) and (ii).
- the matching result output unit 13 (23) is realized by the input / output interface 13 (23) shown in Fig. 3 (Fig. 4), and the matching result notified from the matching processing unit 1 I d (21 d). (Specific result) is output.
- the function as the biometric information input unit for registration and the biometric information input unit for verification is realized by one fingerprint sensor (biometric information input unit) 14, and the features for registration are
- the function of the information extraction unit and the matching feature information extraction unit is realized by a single fingerprint data extraction unit (feature information extraction unit) 11a, and the function of the registration attribute information extraction unit and the matching attribute information extraction unit is realized.
- the function is realized by one attribute information extraction unit 11b.
- Fingerprint registration Z verification program (biometric registration / verification program) 15 a, fingerprint registration program (biometric registration program) 15 c and fingerprint verification program Mum ((Biological information information collation verification program)) 2255 aa is, for example, ffrerexixibururudisuisukukku, CCDD RR ,, CCDD--in the form recorded on a recording medium such as RRWW, DDVVDD, etc., which can be read and read by a computer. Will be provided. . In this case, the computer ((CCPPUU1111 ,, 2211)) will generate the program 1155 aa ,, 1155 cc ,, from its recording medium.
- the program 1155 aa , 1155 cc, 2255 aa for example, magneto-optical disk, optical-optical disk, optical-optical magnetic disk, etc. Record it in the storage device ((recording medium)), and connect the communication line to the storage device. It may be provided to the computer user ((CCPPUU1111)) via the Internet. .
- computer includes the term “hardware” and "operating rate”.
- the above-mentioned application program is installed in a device such as the one shown here, and the fingerprint fingerprint authentication device 1100 ,, 1100 It includes a program code that enables the functions of the AA and Fingerprint Authentication Server 2200 to be realized. . Also, part of the functionality is that it is not an application, but rather an operating system. It may be actually realized by the system. .
- CD-ROM compact disc
- CD-R compact disc
- CD-RW digital versatile disk
- DVD magnetic disk
- optical disk In addition to magneto-optical disks, IC cards, ROM cartridges, magnetic tapes, punch cards, computer internal storage devices (RAM, ROM, etc.)
- RAM random access memory
- ROM read-only memory
- a printed material on which codes such as a par code are printed can be used.
- step S11 to S17 The operation of the fingerprint data registration device (that is, the fingerprint data registration procedure) will be described.
- the person to be registered inputs a fingerprint image through the fingerprint sensor 14 (step S11).
- the registered fingerprint data extraction unit 11a extracts the registered fingerprint data (step S12), and the registration attribute information extraction unit 11b extracts a plurality of registration attribute information. (Steps S13 to S16).
- the first attribute information item (attribute item) is called (step S13), and the registration attribute information corresponding to the item is extracted by the attribute extraction unit 11b-1. Then, it determines whether or not the attribute item is the last one (step S15). If it is not the last one (NO route in step S15), the next attribute item is called (step S16), and the attribute information for registration corresponding to the attribute item is extracted from the attribute extraction unit 11b—2, lib — Extract by 3, ... (Step S14). .
- the registration unit 11e extracts the registration attribute data and the registration fingerprint data extraction unit 11a extracts it.
- the registered fingerprint data registered and the multiple types of registration attribute information extracted by the registration attribute information extraction unit 11b are correlated with the ID of the registration target to form a database in a table format as shown in Fig. 5. Is registered in the registration data storage unit 15b (25b) (step S17).
- the fingerprint data matching device shown in FIG. 2 that is, the fingerprint data matching procedure
- the person to be authenticated inputs a fingerprint image through the fingerprint sensor 14 (24) (step S21).
- matching fingerprint data is extracted by the matching fingerprint data extracting unit 11a (21a) and input to the matching processing unit 11d (21d) (step S22).
- a plurality of matching attribute information is extracted by the information extracting unit 11b (21b).
- Step S23 to S2 When extracting the matching attribute information, the first attribute information item (attribute item) is called.
- Step S23 the attribute information for matching corresponding to the item is extracted by the attribute extracting unit 11b-1 (21b-1) (Step S24), and the attribute item is the last one. It is determined whether or not there is a certain force (step S25). If it is not the last one (NO route in step S25), the next attribute item is called (step S26), and the matching attribute information corresponding to the attribute item is extracted from the attribute extraction unit lib—2 (21b—2) , Lib-3 (2 lb-3), ... (step S24).
- the collation priority of the registration data read control unit 11c is obtained.
- the function as the rank calculating unit the matching of the attribute information is performed by using the above method (1), and the attribute information matching score is calculated (step S27; details will be described later).
- the collation priority is calculated and determined (step S28).
- the registered fingerprint reading data is sequentially read from the registered data storage unit 15b (25b) by the registration data read control unit 11c (21c) in accordance with the above-mentioned collation priority order, and the collation processing unit 1I d (21 d), and the matching processing unit 11 d (2 I d) uses the above-mentioned method (i) and matches the matching fingerprint data from a plurality of registered fingerprint data as follows. Are identified (steps S29 to S33).
- the registration data readout control unit 11c stores the first registration fingerprint data, that is, the registration fingerprint data having the highest attribute information matching score and the highest matching priority, in the registration data storage unit 15c. b (25b) (step S29), and the collation processing unit lid (2Id) extracts the first registered fingerprint data and the collation extracted by the collation fingerprint data extraction unit 11a (21a). Collation with fingerprint data is performed (step S30).
- the matching processing unit 1 Id determines whether or not the matching fingerprint data and the registered fingerprint data match and satisfy predetermined criteria, that is, the fingerprint of the authentication target person. It is determined whether is the fingerprint of the person who registered the registered fingerprint data (step S31).
- step S31 If it is determined that the fingerprint is not the user's own fingerprint (NO route in step S31), It is determined whether the registered fingerprint data to be collated is the last fingerprint data.
- Step S32 if it is determined that the fingerprint data is not the last fingerprint data (NO route in Step S32), the registered fingerprint data having the next highest matching priority is registered by the registration data readout control unit 11c (21c). Is read from the registration data storage unit 15b (25b) (step S33), and the same processing as described above (steps S30 to S32) is executed.
- step S31 If it is determined in step S31 that the fingerprint is the user's own fingerprint (YES route).
- the matching fingerprint data is identified from a plurality of registered fingerprint data, and the verification is performed on the assumption that the person to be authenticated is the registrant.
- the result is output from the collation result output unit 13 (23) (step S34), and the collation processing ends.
- the matching processing unit 1 la performs the matching when the registered fingerprint data that satisfies the matching fingerprint data and satisfies the predetermined criterion appears, that is, when the YES determination is made in step S31.
- the collation of the fingerprint data with each registered fingerprint data is completed, and the registered fingerprint data that satisfies the predetermined criterion is specified as matching the collated fingerprint data.
- the registered fingerprint data and the matched fingerprint data are compared in the order of matching priority, and the registered fingerprint data that satisfies the matching criterion is first recognized as belonging to the person to be authenticated. It certifies that the person to be certified is the registrant.
- step S32 determines whether the registered fingerprint data is the last fingerprint data (YES route). If it is determined in step S32 that the registered fingerprint data is the last fingerprint data (YES route), from among the plurality of registered fingerprint data, one that satisfies the predetermined criterion and matches the verification fingerprint data is determined. Since it could not be identified, the verification result output unit 13 (23) outputs that the fingerprint of the person to be authenticated is not registered as registered fingerprint data (failure of personal authentication) (step S23). 3 5), end the collation processing.
- a comparison priority calculation procedure in the present embodiment that is, a procedure executed by the function of the registration data read control unit 11c (21c) as a comparison priority calculation unit.
- the processing procedure in Step S27 of Step 12 will be described more specifically.
- the registered fingerprint data (fingerprint data 1, fingerprint data 2, fingerprint data 3) and registration attribute information a (eg, pattern type; attribute a 1, a2, a3)
- registration attribute information b eg, the number of feature points; attributes b1, b2, b3)
- registration attribute information c eg, water content; attributes c1, c2, c3)
- weighting factors 3, 2, and 1 are assigned to registration attribute information a, b, and c, respectively. These weighting factors are determined in consideration of the detection accuracy of each attribute information, the variation of data, and the like.
- the comparison attribute information and the registration attribute information are compared, and a determination of match Z mismatch is made.
- three attributes a 2, b 2 and c 2 of ID 2 match the matching attribute information a, b and c, respectively, and two attributes a 1 and c 1 of ID 1 are It is assumed that the matching attribute information a and c match, and the attribute b3 for ID 3 matches the matching attribute information b.
- the underlined attributes match the matching attribute information.
- the person to be authenticated inputs a fingerprint image through the fingerprint sensor 14 (24) (step S 21) From the input fingerprint image, matching fingerprint data is extracted by the matching fingerprint data extracting unit 11a (21a) and input to the matching processing unit 1Id (21d). (Step S22), a plurality of pieces of matching attribute information are extracted by the matching attribute information extracting unit 11b (21b) (Steps S23 to S26).
- Step S50 When all of a plurality of types of attribute information for collation specified in advance are extracted (YES route in step S25), the function as a collation priority calculation unit of the registration data readout control unit 11c (21c) is used as described above.
- the matching of attribute information is determined using method (2), and the matching priority of multiple registered fingerprint data is calculated based on the matching determination result (actually, the registered fingerprint data is rearranged). (Step S50).
- the matching processing unit 1 Id (21 d) registers the registered fingerprint data (the arrangement of the registered fingerprint data) in which the matching priority calculated by the registration data read control unit 11 c (21 c) is higher than the reference order.
- the higher-order registered fingerprint data of the replacement result is grouped as a group to be collated, and the number of registered fingerprint data belonging to the group to be collated is set as a specified value n (step S51).
- the registered fingerprint data belonging to the group to be verified is sequentially read from the registered data storage unit 15b (25b) by the registered data readout control unit 11c (21c).
- the data is input to the matching processing unit 1 Id (21 d), and the matching processing unit 1 1 d (2 Id) uses the above method (ii) to perform matching from a plurality of registered fingerprint data as follows.
- the data that matches the fingerprint data is specified (steps S52 to S6).
- the registration data readout control unit 11c sets the first registered fingerprint data, that is, the attribute information matching score
- the collation processing unit lid (2 Id) extracts the first registered fingerprint data and the fingerprint data for collation.
- the collation with the collation fingerprint data extracted by the output unit 11a (21a) is performed (step S54).
- the matching score obtained as a result of the matching which indicates the matching degree between the registered fingerprint data and the matching fingerprint data, is the highest score, whether it is force or not. Is higher than the highest value of the matching score) (step S55). If it is the highest score (YES route in step S55; the first registered fingerprint data naturally becomes the highest score), the matching score is stored as the highest score (step S56).
- step S57 It is determined whether or not there is a certain force, that is, whether or not the matching has been completed for all the registered fingerprint data belonging to the matching target group (step S57).
- N + 1 is set as N (step S58), and the collation is performed by the registration data read control unit 11c (2 1c).
- the next registered fingerprint data belonging to the target group is read from the registered data storage unit 15b (25b) (step S59), and the same processing as described above (steps S54 to S57) is executed.
- step S57 If it is determined in step S57 that N is equal to or larger than the specified value n, that is, if the collation has been completed for all the registered fingerprint data belonging to the collation target group (YES route in step S57), the collation processing unit 11d (2Id) is whether the final highest score held in step S56 is equal to or higher than a certain score that can be authenticated as the person to be authenticated, that is, the fingerprint of the person to be authenticated is Then, it is determined whether or not the power which is the fingerprint of the registrant of the registered fingerprint data that has obtained the highest score is> (step S60).
- step S60 If it is determined in step S60 that the fingerprint is the user's own fingerprint (YES route), a matching fingerprint data is identified from the plurality of registered fingerprint data (verification target groups), and the person to be authenticated is the registrant himself. Is output from the collation result output unit 13 (23) (step S61), and the collation processing ends.
- step S60 when it is determined that the final highest score held in step S56 is less than the above-mentioned fixed score (NO route), the matching fingerprint data is selected from the matching target groups. Matching registered fingerprint data could not be identified, discarding the stored highest score, and the fact that the fingerprint of the person to be authenticated was not registered as registered fingerprint data (personal authentication failed. did This is output from the collation result output unit 13 (23) (step S62), and the collation processing ends.
- the collation fingerprint data is collated with all the registered fingerprint data belonging to the collation target group, and the registered fingerprint with the highest matching degree obtained as a result of the collation is obtained. If the data satisfies the specified collation criteria, it is determined that the data belongs to the person to be certified, and that the person to be certified is the registrant.
- the degree of coincidence is represented by a score as described above, and if the score is equal to or greater than a certain score, the user is authenticated.
- collation is performed according to collation priority, and when the collation is successful, the person to be authenticated has been authenticated as a person.
- the probability that the identified registered fingerprint data is the fingerprint of the individual is extremely high. There is a small possibility that the identified registered fingerprint data will be accepted by someone else.
- the registered fingerprint data is grouped and the The group with the highest score is set as the collation target group, and the registered fingerprint data with the highest score in the collation target group is identified as that of the person to be authenticated, greatly reducing the probability of mistakenly accepting others. I can do it.
- the same data contents as those shown in FIGS. 5, 13 and 14 are registered in the registration data storage unit 15b (25b). .
- the registered fingerprint data fingerprint data 1, fingerprint data 2, fingerprint data 3
- the registration attribute information a attributes al, a 2, a3)
- registration attribute information b attributes bl, b2, b3
- registration attribute information c attributes cl, c2, c3
- the attribute information for registration a, b, c has It is assumed that 2, 1, and 3 are assigned in advance. The priority order is determined in consideration of the detection accuracy of each attribute information, data variation, and the like.
- the attribute information of the first priority item (attribute information b in the example shown in FIG. 17) is read from the registration data storage unit 15b (25b) (step S71), and the attribute information b for collation is read. Is compared with the registration attribute information b1, b2, and b3 to determine the match Z mismatch (step S72), and sort the registered fingerprint data based on the determination result (step S73).
- step S74 it is determined whether or not the attribute information item that has been subjected to the matching determination this time is the last item (the lowest priority item) (step S74). If not, the attribute information item is not the last item (step S74). 74 NO route), the attribute information of the next priority item is read from the registration data storage unit 15b (25b) (step S75), and the same processing as described above (steps S72 to S74) is performed. Execute repeatedly. Then, when it is determined in step S74 that the attribute information item is the last item (NO in step S74), the rearrangement process ends.
- the top-level group is a registration in which all of the attribute information a, b, and c match.
- the second group is a group of registered fingerprint data with two attribute information a and b matched
- the third group is a group of registered fingerprint data with two attribute information b and c matched
- the fourth-ranking group is a group of registered fingerprint data that matches only the attribute information b
- the fifth-ranking group is a group of registered fingerprint data that matches two of the attribute information a and c
- the sixth-ranking group is the attribute information
- the registered fingerprint data group where only a matched, the 7th group was the group of registered fingerprint data where only the attribute information c matched, and the 8th group did not match the attribute information at all.
- the matching processing unit 1 Id may select only the highest-order group as the matching target group, or May be selected as the group to be compared.
- FIG. 19 is a block diagram showing a functional configuration of a modification of the fingerprint data matching device (biological information matching device) according to the present embodiment.
- the fingerprint data collation device shown in FIG. 19 is also configured in substantially the same manner as the fingerprint data collation device shown in FIG. 2, but the fingerprint data collation device shown in FIG. ) And the data management unit 11 g (21 g) are further added.
- the attribute information changing unit 1 If (21 f) identifies the matching fingerprint data from the plurality of registered fingerprint data by the matching processing unit 11 d (21 d). (If the verification is successful and the user is authenticated), the registration attribute information in the registration data storage unit 15b (25b) is extracted by the verification attribute information extraction unit 11b (21b). It functions as a change unit that can be changed and updated with the collated attribute information.
- Some attribute information has universal properties (for example, pattern type and number of feature points) and others that change depending on the situation (for example, moisture content on the finger surface and input environment information). is there. Therefore, if the attribute value is different from that at the time of registration at the time of comparison, the attribute information change unit 1If (21f) stores the registration attribute information in the registration data storage unit 15b (25b). By changing and updating the value at the time of collation, the accuracy of determining the collation priority can be further improved. However, as described above, such a change / update process is executed only when the verification is successful and the user is authenticated.
- the data management unit 11g manages and monitors the number of registered fingerprint data in the registration data storage unit 15b (25b), and controls the registration data readout control according to the number.
- the section 11c (21c) functions as a management section for changing the number of types of registration attribute information used for calculating the matching priority order.
- the data management unit 11g controls the number of types of attribute information used to calculate the collation priority according to the number of registered fingerprint data, thereby optimizing the processing time. It is possible. Specifically, when the number of registered fingerprint data is small, the number of types of attribute information used to calculate the matching priority is also reduced.
- the matching priority of a plurality of registered fingerprint data is Multiple types of data associated with each registered fingerprint data Matching fingerprint data calculated from the registration attribute information and the multiple types of matching attribute information extracted from the fingerprint image of the person to be authenticated and extracted from the fingerprint image of the person to be authenticated
- the registered fingerprint data can be determined, and the time required for the matching process (the number of times of matching) can be greatly reduced, and the matching accuracy can be improved.
- one-to-many fingerprint matching is performed.
- the matching fingerprint data is compared with the registered fingerprint data in order from the registered fingerprint data having the highest matching probability according to the matching priority determined by the plurality of pieces of attribute information.
- the number of times of collation can be greatly reduced, and the fingerprint data and multiple pieces of attribute information can be used to perform practical personal authentication with extremely high accuracy.
- the registered fingerprint data is grouped, and the group with the highest collation priority is the group to be collated. Since the registered fingerprint data with the highest score in the group to be verified is identified as that of the person to be verified, the probability of accepting another person by mistake can be greatly reduced, and the verification accuracy can be reduced. Can be higher.
- the biological information is a fingerprint image.
- the present invention is not limited to this.
- the plurality of types of attribute information are, for example, three types: pattern type, number of feature points, and water content.
- the present invention is not limited to this. If two or more of these are used, the same operation and effect as the above-described embodiment can be obtained.
- the attribute information match Z mismatch determination is actually performed as follows. Matching of pattern type and input environment information Z determination of mismatch is performed based on whether or not the matching attribute information and the registration attribute information completely match. The determination of whether the shapes X and y match or not match is performed, for example, by determining whether the difference between the matching x and y and the registration X and y is within a predetermined range, respectively, or the matching ratio x Z y and the registration The determination is made based on whether the difference from the ratio x / y is within a predetermined range.
- the Z mismatch determination is performed, for example, based on whether or not the difference between the matching attribute value and the registration attribute value is within a predetermined range. .
- the present invention when performing one-to-many authentication using biometric information, matching is performed in accordance with the matching priority even if matching feature information is not matched with all registered feature information in a round-robin manner. If a certain degree of matching is obtained, the registration feature information of the person to be authenticated can be determined, and the time required for the verification process (verification time) ) Can be greatly reduced, and the matching accuracy can be improved. Therefore, the present invention is suitable for use in a system for performing personal authentication based on biological information such as a fingerprint, a palm print, an iris, a voice, a face image, a blood vessel pattern, a dynamic signature, and a keystroke. It is considered.
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
Description
Claims
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2003/000774 WO2004068413A1 (ja) | 2003-01-28 | 2003-01-28 | 生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム |
AU2003303835A AU2003303835A1 (en) | 2003-01-28 | 2003-01-28 | Biometrics information registration apparatus, biometrics information matching apparatus, biometrics information registration/matching system, and biometrics information registration program |
EP03815576.8A EP1589480B1 (en) | 2003-01-28 | 2003-01-28 | Biometrics information registration apparatus, biometrics information matching apparatus, biometrics information registration/matching system, and biometrics information registration program |
JP2004567514A JP4128570B2 (ja) | 2003-01-28 | 2003-01-28 | 生体情報照合装置 |
CNB03824537XA CN100388312C (zh) | 2003-01-28 | 2003-01-28 | 生物测量信息登记装置、校验装置、登记/校验系统和登记方法 |
US11/082,936 US7636458B2 (en) | 2003-01-28 | 2005-03-18 | Biometric information registration apparatus, biometric information verification apparatus, biometric information registration/verification system, and biometric information registration program |
US12/453,694 US7634118B2 (en) | 2003-01-28 | 2009-05-19 | Biometric information registration apparatus, biometric information verification apparatus, biometric information registration/verification system, and biometric information registration program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2003/000774 WO2004068413A1 (ja) | 2003-01-28 | 2003-01-28 | 生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/082,936 Continuation US7636458B2 (en) | 2003-01-28 | 2005-03-18 | Biometric information registration apparatus, biometric information verification apparatus, biometric information registration/verification system, and biometric information registration program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2004068413A1 true WO2004068413A1 (ja) | 2004-08-12 |
Family
ID=32800799
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2003/000774 WO2004068413A1 (ja) | 2003-01-28 | 2003-01-28 | 生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム |
Country Status (6)
Country | Link |
---|---|
US (2) | US7636458B2 (ja) |
EP (1) | EP1589480B1 (ja) |
JP (1) | JP4128570B2 (ja) |
CN (1) | CN100388312C (ja) |
AU (1) | AU2003303835A1 (ja) |
WO (1) | WO2004068413A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006293608A (ja) * | 2005-04-08 | 2006-10-26 | Sony Corp | 認証装置、認証方法及びプログラム並びに認証システム、端末装置及び情報処理装置 |
JP2007206941A (ja) * | 2006-02-01 | 2007-08-16 | Konica Minolta Business Technologies Inc | 生体認証装置、生体認証システム及び生体データ管理方法 |
JP2019121188A (ja) * | 2018-01-05 | 2019-07-22 | 富士通株式会社 | 生体認証装置、生体認証方法および生体認証プログラム |
JP2019124974A (ja) * | 2018-01-11 | 2019-07-25 | 富士通株式会社 | 生体認証装置、生体認証方法、および生体認証プログラム |
CN110513762A (zh) * | 2018-10-30 | 2019-11-29 | 永康市道可道科技有限公司 | 浴霸灯体自动开关平台 |
Families Citing this family (59)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7593550B2 (en) | 2005-01-26 | 2009-09-22 | Honeywell International Inc. | Distance iris recognition |
US8098901B2 (en) | 2005-01-26 | 2012-01-17 | Honeywell International Inc. | Standoff iris recognition system |
US8705808B2 (en) | 2003-09-05 | 2014-04-22 | Honeywell International Inc. | Combined face and iris recognition system |
US8064647B2 (en) | 2006-03-03 | 2011-11-22 | Honeywell International Inc. | System for iris detection tracking and recognition at a distance |
US8090157B2 (en) | 2005-01-26 | 2012-01-03 | Honeywell International Inc. | Approaches and apparatus for eye detection in a digital image |
US8049812B2 (en) | 2006-03-03 | 2011-11-01 | Honeywell International Inc. | Camera with auto focus capability |
US8442276B2 (en) | 2006-03-03 | 2013-05-14 | Honeywell International Inc. | Invariant radial iris segmentation |
US8306277B2 (en) * | 2005-07-27 | 2012-11-06 | Canon Kabushiki Kaisha | Image processing apparatus and image processing method, and computer program for causing computer to execute control method of image processing apparatus |
US8260008B2 (en) | 2005-11-11 | 2012-09-04 | Eyelock, Inc. | Methods for performing biometric recognition of a human eye and corroboration of same |
WO2007101276A1 (en) | 2006-03-03 | 2007-09-07 | Honeywell International, Inc. | Single lens splitter camera |
KR101308368B1 (ko) | 2006-03-03 | 2013-09-16 | 허니웰 인터내셔널 인코포레이티드 | 홍채 품질 측정을 갖는 홍채 인식 시스템 |
WO2007103834A1 (en) | 2006-03-03 | 2007-09-13 | Honeywell International, Inc. | Indexing and database search system |
GB2450023B (en) | 2006-03-03 | 2011-06-08 | Honeywell Int Inc | An iris image encoding method |
JP2009529197A (ja) | 2006-03-03 | 2009-08-13 | ハネウェル・インターナショナル・インコーポレーテッド | モジュールバイオメトリクス収集システムアーキテクチャ |
JP2007249556A (ja) * | 2006-03-15 | 2007-09-27 | Fujitsu Ltd | 生体情報を用いた個人認証システム,方法およびプログラム |
JP4946126B2 (ja) * | 2006-03-27 | 2012-06-06 | 富士通株式会社 | データ記録方法及びデータ記録装置 |
US20080256613A1 (en) * | 2007-03-13 | 2008-10-16 | Grover Noel J | Voice print identification portal |
US8063889B2 (en) | 2007-04-25 | 2011-11-22 | Honeywell International Inc. | Biometric data collection system |
JP5139716B2 (ja) * | 2007-05-16 | 2013-02-06 | キヤノン株式会社 | 画像検索装置及び画像検索方法 |
US8436907B2 (en) | 2008-05-09 | 2013-05-07 | Honeywell International Inc. | Heterogeneous video capturing system |
US8213782B2 (en) | 2008-08-07 | 2012-07-03 | Honeywell International Inc. | Predictive autofocusing system |
US8090246B2 (en) | 2008-08-08 | 2012-01-03 | Honeywell International Inc. | Image acquisition system |
JP5277804B2 (ja) * | 2008-09-05 | 2013-08-28 | 富士通株式会社 | 指紋認証装置、指紋認証プログラムおよび指紋認証方法 |
US8280119B2 (en) | 2008-12-05 | 2012-10-02 | Honeywell International Inc. | Iris recognition system using quality metrics |
US8502644B1 (en) | 2009-01-29 | 2013-08-06 | Bank Of American Corporation | Physical item security: tracking device activation |
US8749347B1 (en) * | 2009-01-29 | 2014-06-10 | Bank Of America Corporation | Authorized custodian verification |
CN101894423A (zh) * | 2009-05-18 | 2010-11-24 | 张剑 | 一种银行客户交易系统 |
JP2010286937A (ja) * | 2009-06-10 | 2010-12-24 | Hitachi Ltd | 生体認証方法、及び、生体認証に用いるクライアント端末、認証サーバ |
US8472681B2 (en) | 2009-06-15 | 2013-06-25 | Honeywell International Inc. | Iris and ocular recognition system using trace transforms |
US8630464B2 (en) | 2009-06-15 | 2014-01-14 | Honeywell International Inc. | Adaptive iris matching using database indexing |
CN102474498B (zh) * | 2009-07-14 | 2013-12-18 | 深圳市永盛世纪科技有限公司 | 用户识别设备认证方法 |
US8384514B2 (en) * | 2009-08-07 | 2013-02-26 | At&T Intellectual Property I, L.P. | Enhanced biometric authentication |
TWI406190B (zh) * | 2010-03-04 | 2013-08-21 | Maishi Electronic Shanghai Ltd | 存取控制系統與電腦系統 |
JP5135384B2 (ja) * | 2010-06-02 | 2013-02-06 | 日立オムロンターミナルソリューションズ株式会社 | 生体認証サーバ、および生体認証システム |
US8742887B2 (en) | 2010-09-03 | 2014-06-03 | Honeywell International Inc. | Biometric visitor check system |
EP2579182B1 (en) | 2011-10-03 | 2019-08-28 | Accenture Global Services Limited | Biometric matching engine |
EP2579183B1 (en) * | 2011-10-03 | 2019-05-01 | Accenture Global Services Limited | Biometric training and matching engine |
EP2584491A1 (en) | 2011-10-18 | 2013-04-24 | Accenture Global Services Limited | Biometric matching system |
US9258299B2 (en) * | 2011-12-29 | 2016-02-09 | Intel Corporation | Biometric cloud communication and data movement |
JP6064392B2 (ja) * | 2012-06-29 | 2017-01-25 | 株式会社リコー | 検索装置、検索方法、検索プログラムおよび検索システム |
US9901298B2 (en) * | 2012-11-01 | 2018-02-27 | Quaerimus Medical Incorporated | System and method for prevention of diabetic foot ulcers using total internal reflection imaging |
AU2014297265A1 (en) * | 2013-07-30 | 2016-02-18 | Nec Corporation | Information processing device, authentication system, authentication method, and program |
EP3080786A1 (en) * | 2013-12-11 | 2016-10-19 | Unicredit S.p.A. | Method for biometric recognition of a user amongst a plurality of registered users to a service, employing user localization information |
CN104055521B (zh) * | 2014-06-05 | 2017-10-27 | 胡宝华 | 用户身份识别方法、识别系统及健康仪 |
US9652061B2 (en) | 2014-08-28 | 2017-05-16 | Dell Products, Lp | System and method for utilizing fingerprints as user inputs |
CN105631278A (zh) * | 2015-06-24 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | 身份验证方法及装置 |
US10339178B2 (en) * | 2015-06-30 | 2019-07-02 | Samsung Electronics Co., Ltd. | Fingerprint recognition method and apparatus |
CN105550628B (zh) * | 2015-07-31 | 2019-10-11 | 宇龙计算机通信科技(深圳)有限公司 | 指纹录入方法及装置 |
CN105389565B (zh) * | 2015-11-13 | 2019-04-02 | Oppo广东移动通信有限公司 | 指纹注册方法、装置和终端设备 |
CN106022069B (zh) * | 2016-05-30 | 2019-08-20 | Oppo广东移动通信有限公司 | 一种解锁控制方法及移动终端 |
CN106096358B (zh) | 2016-05-30 | 2019-04-26 | Oppo广东移动通信有限公司 | 一种解锁控制方法及移动终端 |
SG10201605364XA (en) * | 2016-06-29 | 2018-01-30 | Mastercard Asia Pacific Pte Ltd | Method For Effecting An Authentication Procedure Associated With A Service Provider Or An Application |
CN106921655B (zh) * | 2017-01-26 | 2021-01-29 | 华为技术有限公司 | 一种业务授权方法及装置 |
US10607055B2 (en) * | 2017-02-06 | 2020-03-31 | Fingerprint Cards Ab | Method for authenticating a finger of a user of an electronic device |
JP6943087B2 (ja) * | 2017-09-01 | 2021-09-29 | コニカミノルタ株式会社 | 認証システム、認証制御装置、認証制御装置の制御方法、およびプログラム |
CN114758440B (zh) * | 2020-12-29 | 2023-07-18 | 成都启源西普科技有限公司 | 基于图像和文字混合识别的门禁系统 |
CN114758439B (zh) * | 2020-12-29 | 2023-07-18 | 成都启源西普科技有限公司 | 一种基于人工智能的多模态门禁系统 |
JP2023044276A (ja) * | 2021-09-17 | 2023-03-30 | トヨタ自動車株式会社 | 情報処理装置、及び情報処理方法 |
CN114493380B (zh) * | 2022-04-14 | 2022-07-05 | 深圳市宝安区石岩人民医院 | 一种基于大数据的标本生物信息分析验证系统 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000148985A (ja) * | 1998-11-17 | 2000-05-30 | Hitachi Ltd | 個人認証システム |
US20020048390A1 (en) * | 2000-10-20 | 2002-04-25 | Jun Ikegami | Personal authentication system using fingerprint information, registration-and-authentication method for the system, determination method for the system, and computer-readable recording medium |
JP2002163655A (ja) * | 2000-11-24 | 2002-06-07 | Omron Corp | 個人認証装置 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5224173A (en) * | 1991-10-29 | 1993-06-29 | Kuhns Roger J | Method of reducing fraud in connection with employment, public license applications, social security, food stamps, welfare or other government benefits |
US5420937A (en) * | 1993-09-01 | 1995-05-30 | The Phoenix Group, Inc. | Fingerprint information extraction by twin tracker border line analysis |
JP2827994B2 (ja) * | 1995-12-22 | 1998-11-25 | 日本電気株式会社 | 指紋特徴抽出装置 |
JP3705938B2 (ja) | 1997-10-20 | 2005-10-12 | 富士通株式会社 | 指紋登録装置、指紋照合装置及び指紋照合方法 |
US6233348B1 (en) | 1997-10-20 | 2001-05-15 | Fujitsu Limited | Fingerprint registering apparatus, fingerprint identifying apparatus, and fingerprint identifying method |
US6070159A (en) * | 1997-12-05 | 2000-05-30 | Authentec, Inc. | Method and apparatus for expandable biometric searching |
US6505193B1 (en) * | 1999-12-01 | 2003-01-07 | Iridian Technologies, Inc. | System and method of fast biometric database searching using digital certificates |
US6839453B1 (en) * | 2000-05-16 | 2005-01-04 | The Upper Deck Company, Llc | Method and apparatus for authenticating unique items such as sports memorabilia |
US7006673B2 (en) * | 2001-07-25 | 2006-02-28 | Activcard Ireland Limited | Method of hash string extraction |
US7274807B2 (en) * | 2002-05-30 | 2007-09-25 | Activcard Ireland Limited | Method and apparatus for supporting a biometric registration performed on a card |
-
2003
- 2003-01-28 EP EP03815576.8A patent/EP1589480B1/en not_active Expired - Lifetime
- 2003-01-28 CN CNB03824537XA patent/CN100388312C/zh not_active Expired - Fee Related
- 2003-01-28 JP JP2004567514A patent/JP4128570B2/ja not_active Expired - Fee Related
- 2003-01-28 AU AU2003303835A patent/AU2003303835A1/en not_active Abandoned
- 2003-01-28 WO PCT/JP2003/000774 patent/WO2004068413A1/ja active Application Filing
-
2005
- 2005-03-18 US US11/082,936 patent/US7636458B2/en not_active Expired - Fee Related
-
2009
- 2009-05-19 US US12/453,694 patent/US7634118B2/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000148985A (ja) * | 1998-11-17 | 2000-05-30 | Hitachi Ltd | 個人認証システム |
US20020048390A1 (en) * | 2000-10-20 | 2002-04-25 | Jun Ikegami | Personal authentication system using fingerprint information, registration-and-authentication method for the system, determination method for the system, and computer-readable recording medium |
JP2002163655A (ja) * | 2000-11-24 | 2002-06-07 | Omron Corp | 個人認証装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP1589480A4 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006293608A (ja) * | 2005-04-08 | 2006-10-26 | Sony Corp | 認証装置、認証方法及びプログラム並びに認証システム、端末装置及び情報処理装置 |
JP2007206941A (ja) * | 2006-02-01 | 2007-08-16 | Konica Minolta Business Technologies Inc | 生体認証装置、生体認証システム及び生体データ管理方法 |
JP2019121188A (ja) * | 2018-01-05 | 2019-07-22 | 富士通株式会社 | 生体認証装置、生体認証方法および生体認証プログラム |
JP7067061B2 (ja) | 2018-01-05 | 2022-05-16 | 富士通株式会社 | 生体認証装置、生体認証方法および生体認証プログラム |
JP2019124974A (ja) * | 2018-01-11 | 2019-07-25 | 富士通株式会社 | 生体認証装置、生体認証方法、および生体認証プログラム |
CN110513762A (zh) * | 2018-10-30 | 2019-11-29 | 永康市道可道科技有限公司 | 浴霸灯体自动开关平台 |
CN110513762B (zh) * | 2018-10-30 | 2021-04-23 | 新昌县馁侃农业开发有限公司 | 浴霸灯体自动开关平台 |
Also Published As
Publication number | Publication date |
---|---|
EP1589480B1 (en) | 2013-08-21 |
US20090226053A1 (en) | 2009-09-10 |
EP1589480A4 (en) | 2007-09-05 |
CN1689042A (zh) | 2005-10-26 |
JPWO2004068413A1 (ja) | 2006-05-25 |
AU2003303835A1 (en) | 2004-08-23 |
US7634118B2 (en) | 2009-12-15 |
EP1589480A1 (en) | 2005-10-26 |
CN100388312C (zh) | 2008-05-14 |
JP4128570B2 (ja) | 2008-07-30 |
US20050238214A1 (en) | 2005-10-27 |
US7636458B2 (en) | 2009-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2004068413A1 (ja) | 生体情報登録装置,生体情報照合装置および生体情報登録/照合システム並びに生体情報登録プログラム | |
JP4340618B2 (ja) | 生体情報認証装置及び方法,並びに生体情報認証プログラム及び生体情報認証プログラムを記録したコンピュータ読取可能な記録媒体 | |
JP4257250B2 (ja) | 生体情報照合装置並びに生体特徴情報絞込み装置,生体特徴情報絞込みプログラムおよび同プログラムを記録したコンピュータ読取可能な記録媒体 | |
KR100860954B1 (ko) | 바이오메트릭 영상들의 등록 및 인증 방법 및 장치 | |
JP4937607B2 (ja) | 生体認証方法及び生体認証装置 | |
US7007298B1 (en) | Apparatus and method for authenticating user according to biometric information | |
JP5660126B2 (ja) | 識別装置、識別方法、及びプログラム | |
JP2008009753A (ja) | 生体認証方法及び生体認証システム | |
Revett | A bioinformatics based approach to user authentication via keystroke dynamics | |
KR101618136B1 (ko) | 식별 또는 인증방법 및 관련 시스템과 보안 모듈 | |
JP2006085268A (ja) | 生体認証システムおよび生体認証方法 | |
JP2012238256A (ja) | 生体認証装置、生体認証方法および生体認証プログラム | |
JP2010108074A (ja) | 生体認証システム及び方法 | |
JP2003186836A (ja) | 複合認証システム | |
JP3499428B2 (ja) | 生体的特徴の認証装置及び記録媒体 | |
JP5895751B2 (ja) | 生体認証装置、リトライ制御プログラム及びリトライ制御方法 | |
US9412004B2 (en) | Biometric coding | |
JP4911132B2 (ja) | 個人認証装置および電子行政システム | |
KR100744595B1 (ko) | 생체 정보 등록 장치, 생체 정보 대조 장치, 생체 정보 등록/대조 시스템 및 생체 정보 등록 프로그램을 기록한 컴퓨터로 판독 가능한 기록 매체 | |
JP5320894B2 (ja) | 個人認証装置、個人認証方法および個人認証プログラム | |
JP2002297549A (ja) | 本人認証システム及びプログラム | |
JP2003044858A (ja) | 個人認証装置および方法 | |
TW202203055A (zh) | 生物特徵的辨識系統及辨識方法 | |
JP2005157746A (ja) | 本人認証装置 | |
JP2001092960A (ja) | 指紋認証方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SC SD SE SG SK SL TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2004567514 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11082936 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2003815576 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020057006821 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2003824537X Country of ref document: CN |
|
WWP | Wipo information: published in national office |
Ref document number: 1020057006821 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 2003815576 Country of ref document: EP |