A biometric authentication system, authentication client terminal, and biometric authentication method are provided to reduce an expected value of the number of inputs of biometric data for authentication, while effectively preventing forgery. In a biometric authentication system, prior probabilitie
A biometric authentication system, authentication client terminal, and biometric authentication method are provided to reduce an expected value of the number of inputs of biometric data for authentication, while effectively preventing forgery. In a biometric authentication system, prior probabilities of enrolled users un and non-enrolled user u0 are previously set. 1:N matching is performed between feature data of a claimant v and matching feature data. The matching score is calculated for each enrolled user un. A ratio of the likelihood v=un to the likelihood v≠un is calculated for each enrolled user un using the calculated matching scores. Posterior probabilities of the enrolled users un and non-enrolled user u0 are calculated, using the likelihood ratios, and the prior probabilities of both the enrolled users un and the non-enrolled user u0. Then, determination is made by comparing each posterior probability with a first threshold.
대표청구항▼
1. A biometric authentication system comprising: a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N);each time biometric data is inputted from a claimant v, a feature extraction unit for extracting feature data of the claimant v based on the biometric data a
1. A biometric authentication system comprising: a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N);each time biometric data is inputted from a claimant v, a feature extraction unit for extracting feature data of the claimant v based on the biometric data acquired from the claimant v;a prior probability setting unit for setting prior probabilities of the enrolled users un and a prior probability of a non-enrolled user u0;a 1:N matching unit for performing 1:N matching between the extracted claimant feature data of the claimant and the enrolled feature data held in the database and calculating a matching score of each of the enrolled users un;a likelihood ratio calculation unit for calculating a ratio of the likelihood v=un to the likelihood v≠un with respect to each of the enrolled users un, by using the calculated matching scores according to input times of the biometric data;a posterior probability calculation unit for calculating posterior probabilities of the enrolled users un and a posterior probability of the non-enrolled user u0, using the calculated likelihood ratios, the prior probabilities of the enrolled users un, and the prior probability of the non-enrolled user u0; anda determination unit for comparing each of the calculated posterior probabilities with a first threshold, when a maximum value of the posterior probability is larger than the first threshold, and when the posterior probability showing the maximum value is one of the posterior probabilities of the enrolled users un, determining that the corresponding enrolled user and the claimant v are identical, while when the posterior probability showing the maximum value is the posterior probability of the non-enrolled user u0, determining that the claimant v is a non-enrolled user u0, when the maximum value of the posterior probability is equal to or less than the first threshold, and when the number of acquisitions of the biometric data from the claimant v is less than a predetermined value, requesting to reacquire the biometric data of the claimant v, and while when the number of acquisitions is equal to or more than the predetermined value, determining “authentication failure”. 2. The biometric authentication system according to claim 1, further comprising an enrolled user pruning unit, wherein, when the determination unit requests to reacquire the biometric data from the claimant v, the enrolled user pruning unit compares each of the posterior probabilities calculated by the posterior calculation unit with a second threshold, and excludes an enrolled user un corresponding to the posterior probability smaller than the second threshold, from the target to be matched to the claimant v. 3. The biometric authentication system according to claim 1, wherein the posterior probability calculation unit compares the posterior probability of the non-enrolled user u0 calculated in the current acquisition of the biometric data from the claimant v with the prior probability of the non-enrolled user u0 when the number of acquisitions is one, or with the posterior probability of the non-enrolled user u0 calculated in the previous acquisition of the biometric data when the number of acquisitions is two or more, andwherein, when the posterior probability of the non-enrolled user u0 calculated in the current acquisition is higher, the posterior probability calculation unit does not use the feature data extracted in the current acquisition in the calculation of posterior probabilities in the subsequent acquisitions of the biometric data from the claimant v. 4. The biometric authentication system according to claim 1, wherein the database holds a plurality of different types of feature data belonging to a plurality of modalities with respect to each of the users un, andwherein the biometric authentication system further comprises a biometric information input sensor that allows for acquisition of the biometric data only once with respect to each of modalities. 5. The biometric authentication system according to claim 1, wherein the database holds a plurality of different types of feature data belonging to the same modality with respect to each of the enrolled users un, andwherein the 1:N matching unit determines “authentication failure” when the best matching score is obtained several times for the same biometric information until acquisition of the biometric data in this time. 6. The biometric authentication system according to claim 1, wherein the database holds a plurality of different types of feature data belonging to the same modality with respect to each of the enrolled users un, andwherein, when the best matching score is obtained several times for the same biometric information until acquisition of the biometric information in this time, the 1:N matching unit does not use among the matching score above the matching scores calculated in acquisitions other than the acquisition with the best matching score for the calculation of likelihood ratios by the likelihood ratio calculation unit. 7. The biometric authentication system according to claim 1, wherein, when the determination unit determines that the claimant v is a non-enrolled users u0, the prior probability setting unit increases the prior probabilities of the non-enrolled users u0. 8. The biometric authentication system according to claim 1, wherein the first threshold is larger than 0.5. 9. The biometric authentication system according to claim 1, wherein the determination unit outputs forgery warning information about the forgery when it is determined that the claimant v is the non-enrolled users u0. 10. The biometric authentication system according to claim 1, further comprising: a loss calculation unit; anda prior probability and threshold setting unit,wherein, each time authentication is performed, the loss calculation unit calculates a loss W1 when the claimant v is an enrolled user and is identified as another enrolled user, and a loss W0 when the claimant v is a non-enrolled user and is identified as a certain enrolled user, andwherein the prior probability and threshold setting unit sets the prior probabilities of the enrolled users un and a corresponding threshold, as well as the prior probability of the non-enrolled user u0 and a corresponding threshold, using the losses W1 and W0, respectively, so that EFRR as well as an expected value Rn of the loss when the claimant v is identified as the n-th enrolled user are equal to or less than respective desired values. 11. A biometric authentication system comprising: a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N);each time biometric data is inputted from a claimant v, a feature extraction unit for extracting feature data of the claimant v based on biometric data acquired from the claimant v;a 1:N matching unit for performing 1:N matching between the extracted feature data of the claimant and the enrolled feature data held in the database, and calculating a matching score of each of the enrolled users un;a likelihood ratio calculation unit for calculating a ratio of the likelihood v=un to the likelihood v≠un with respect to each of the enrolled users un, by using the calculated matching scores according to input times of the biometric data; anda determination unit for comparing each of the likelihood ratios with a first threshold, when a maximum value of the likelihood ratio is larger than the first threshold, determining that the enrolled user corresponding to the likelihood ratio showing the maximum value is identical to the claimant v, while when the maximum value of the likelihood ratio is equal to or less than the first threshold, and when the number of acquisitions of the biometric data from the claimant v is less than a predetermined value, requesting to reacquire the biometric data of the claimant v, and when the number of acquisitions is equal to or more than the predetermined value, determining “authentication failure”. 12. The biometric authentication system according to claim 11, further comprising an enrolled user pruning unit, wherein, when the determination unit requests to reacquire the biometric data, the enrolled user pruning unit compares each of the likelihood ratios calculated by the likelihood ratio unit with a second threshold, and excludes an enrolled user un corresponding to the likelihood ratio smaller than the second threshold, from the target to be matched to the claimant v. 13. An authentication client terminal capable of communicating with an authentication server terminal, the authentication server terminal including a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N), and a prior probability setting unit for setting prior probabilities of the enrolled users un and a prior probability of a non-enrolled user u0, the authentication client terminal comprising:a feature extraction unit for extracting the feature data of a claimant v based on the biometric data acquired from the claimant v;an authentication request unit for transmitting the extracted feature data of the claimant to the authentication server terminal, calculating a ratio of likelihood v=un to likelihood v≠un with respect to each of the enrolled users un, based on the feature data of the claimant and the matching feature data held in the database, calculating the posterior probabilities of the enrolled users un and the posterior probability of the non-enrolled user u0, using the calculated likelihood ratios, the prior probabilities of the enrolled users un, and the prior probability of the non-enrolled user u0, comparing each of the calculated posterior probabilities with a first threshold, when a maximum value of the posterior probability is larger than the first threshold, the authentication request unit requesting to transmit the information of the enrolled user un or non-enrolled user u0 corresponding to the posterior probability showing the maximum value, and acquiring the information transmitted from the authentication server terminal in response to the request; anda determination unit for determining that when the acquired information is of the enrolled users un, the enrolled user un and the claimant v are identical, and that when the acquired information is of the non-enrolled user u0, the claimant v is a user other than the enrolled users un. 14. The authentication client terminal according to claim 13, Wherein the authentication request unit requests to perform 1:N matching between the extracted feature data of the claimant and the feature data held in the database, calculates the matching score of each of the enrolled users un, and calculates the likelihood ratio of each of the enrolled users un by using the calculated matching scores. 15. A biometric authentication method using a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N) and prior probabilities of the enrolled users un and a prior probability of a non-enrolled user u0, comprising: each time biometric data is inputted from a claimant v, extracting feature data of the claimant v based on the biometric data acquired from the claimant v;performing 1:N matching between the extracted claimant feature data of the claimant and the enrolled feature data held in the database, and calculating a matching score of each of the enrolled user un;calculating a ratio of likelihood v=un to likelihood v≠un with respect to each of the enrolled users un, by using the calculated matching scores according to input times of the biometric data;calculating posterior probabilities of the enrolled users un and a posterior probability of the non-enrolled user u0, using the calculated likelihood ratios, the prior probabilities of the enrolled users un, and the prior probability of the non-enrolled user u0; andcomparing each of the calculated posterior probabilities with a first threshold, when a maximum value of the posterior probability is larger than the first threshold, and when the posterior probability showing the maximum value is one of the posterior probabilities of the enrolled users un, determining that the corresponding enrolled user and the claimant v are identical, while when the posterior probability showing the maximum value is the posterior probability of the non-enrolled user u0, determining that the claimant v is a non-enrolled users u0, when the maximum value of the posterior probability is equal to or less than the first threshold, and when the number of acquisitions of the biometric data from the claimant v is less than a predetermined value, requesting to reacquire the biometric data of the claimant v, and while when the number of acquisitions is equal to or more than the predetermined value, determining “authentication failure”. 16. An authentication client terminal capable of communicating with an authentication server terminal, the authentication server terminal including a database holding enrolled feature data with respect to each of enrolled users un (n=1 to N), and a prior probability setting unit for setting prior probabilities of the enrolled users un and a prior probability of a non-enrolled user u0, the authentication client terminal comprising:each time biometric data is inputted from a claimant v, a feature extraction unit for extracting the feature data of the claimant v based on the biometric data acquired from the claimant v;an authentication request unit for transmitting the extracted feature data of the claimant to the authentication server terminal, requesting to perform 1:N matching between the extracted claimant feature data of the claimant and the enrolled feature data held in the database, to calculate a matching score of each of the enrolled users un, to calculate a ratio of likelihood v=un to likelihood v≠un with respect to each of the enrolled users un, by using the calculated matching scores according to input times of the biometric data, to calculate posterior probabilities of the enrolled users un and the posterior probability of the non-enrolled user u0, using the calculated likelihood ratios, the prior probabilities of the enrolled users un, and the prior probability, of the non-enrolled user u0, to compare each of the calculated posterior probabilities with a first threshold, and when a maximum value of the posterior probability is larger than the first threshold, to transmit the information of the enrolled user un or non-enrolled user u0 corresponding to the posterior probability showing the maximum value, and acquiring the information transmitted from the authentication server terminal in response to the request; anda determination unit for determining that when the acquired information is of the enrolled users un, the enrolled user un and the claimant v are identical, and that when the acquired information is of the non-enrolled user u0, the claimant v is a user other than the enrolled users un.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.