BIOMETRIC AUTHENTICATION METHOD AND SYSTEM

• US 20110185176A1
• Filed: 08/21/2009
• Published: 07/28/2011
• Est. Priority Date: 10/31/2008
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Isobe, Yoshiaki, Takahashi, Kenta, Hirata, Shinji
• Granted Patent: US 8,412,940 B2
• Time in Patent Office: Days
• US Class Current: 713/168
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/83 input devices, e.g. keyboards, mice or controllers thereof
• CPC Class Codes: G06F 2221/2153 Using hardware token as a secondary aspect
• CPC Class Codes: G06V 40/53 Measures to keep reference information secret, e.g. cancellable biometrics
• CPC Class Codes: G07C 2209/12 Comprising means for protecting or securing the privacy of biometric data, e.g. cancellable biometrics
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G07C 9/38 with central registration
• CPC Class Codes: H04L 2209/043 of tables, e.g. lookup, substitution or mapping
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 9/3231 Biological data, e.g. fingerprint, voice or retina network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861

Abstract

At a registration time, a feature data array for registration is generated from biometric information acquired by a client, and a position correction template and a comparison template obtained by converting the feature data array for registration are registered in a server.

At an authentication time, a feature data array for authentication is generated from biometric information acquired by the client, and converted feature data for position correction obtained by converting the feature data array for authentication is transmitted to the server. The server detects a position correction amount of the feature data array for authentication relative to the feature data array for registration using the position correction template and the converted feature data for position correction, and transmits the position correction amount to the client. The client corrects the feature data array for authentication using the position correction amount and transmits the converted feature data array for comparison to the server. The server calculates a distance between the comparison template and the converted feature data array for comparison and determines success or failure of the authentication on the basis of the distance.

Claims

1. A biometric authentication method comprising the steps of:

extracting a feature data array for registration from biometric information of a registration applicant at a biometric information registration time by using a client;

generating a first conversion parameter for comparison at the biometric information registration time by using the client, the first conversion parameter for comparison being used to convert the feature data array for registration;

generating a position correction template from the feature data array for registration at the biometric information registration time by using the client;

generating a comparison template by converting the feature data array for registration using the first conversion parameter for comparison at the biometric information registration time by using the client;

transmitting the position correction template and the comparison template to a server at the biometric information registration time by using the client;

extracting a feature data array for authentication from biometric information of a user at an authentication time by using the client;

generating a second conversion parameter for comparison at the authentication time by using the client, the second conversion parameter for comparison being used to convert the feature data array for authentication;

generating converted feature data for position correction from the feature data array for authentication at the authentication time by using the client;

transmitting the converted feature data for position correction to the server at the authentication time by using the client;

storing the position correction template and the comparison template transmitted by the client in a database coupled to the server by using the server;

calculating a position correction amount between the feature data array for registration and the feature data array for authentication using the position correction template stored in the database and the converted feature data for position correction transmitted by the client by using the server;

transmitting the position correction amount to the client by using the server;

generating a corrected feature data array by performing position correction on the feature data array for authentication on the basis of the position correction amount by using the client;

generating a converted feature data array for comparison by converting the corrected feature data array using the second conversion parameter for comparison by using the client;

transmitting the converted feature data array for comparison to the server by using the client;

calculating the distance between the comparison template stored in a database and the converted feature data array for comparison transmitted by the client by using the server; and

determining success or failure of authentication of the user as the registration applicant on the basis of comparison between the distance and a predetermined authentication threshold by using the server.

2. The biometric authentication method according to claim 1,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having a predetermined size L,

the generation of the first conversion parameter for comparison includes randomly generating a mask bit string having the size L,

the first conversion parameter for comparison includes the mask bit string,

the comparison template is an array obtained by calculating the exclusive OR between the feature data array for registration and the mask bit string,

the converted feature data array for comparison is an array obtained by calculating the exclusive OR between the corrected feature data array and the mask bit string, and

the distance is a Hamming distance.

3. The biometric authentication method according to claim 2,

wherein the feature data array for registration, the corrected feature data array, and the mask bit string are each a bit string containing a Don'"'"'t care bit “

*”

,

the exclusive OR between the feature data array for registration and the mask bit string for obtaining the comparison template and the exclusive OR between the corrected feature data array and the mask bit string for obtaining the converted feature data array for comparison are each calculated under a rule that if at least one of bits is a Don'"'"'t care bit “

*”

, the exclusive OR between the bits is a Don'"'"'t care bit “

*”

, and

the Hamming distance between the comparison template and the converted feature data array for comparison is the number of bits of “

1”

contained in a bit string obtained by calculating the exclusive OR between the comparison template and the converted feature data array for comparison.

4. The biometric authentication method according to claim 1,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having the predetermined size L,

the generation of the first conversion parameter for comparison includes:

randomly generating a concatenation array having a size M; and

generating a substitution pattern, the substitution pattern being used to substitute positions of elements of an array for each other, the array having a size of the sum of L and M,

the generation of the comparison template includes;

generating a concatenation array for registration having a size of the sum of L and M by concatenating the feature data array for registration and the concatenation array; and

generating the comparison template by substituting the concatenation array for registration in accordance with the substitution pattern,

the generation of the converted feature data array for comparison includes;

generating a modified concatenation array that is distant from the concatenation array by a predetermined offset Hamming distance δ and

has the size M;

generating a concatenation array for authentication having the size of the sum of L and M by concatenating the feature data array for authentication and the modified concatenation array; and

generating the converted feature data array for comparison by substituting the concatenation array for authentication in accordance with the substitution pattern,

the calculation of the distance between the comparison template and the converted feature data array for comparison is calculation of a corrected Hamming distance (d-δ

) by subtracting the offset Hamming distance δ

from the Hamming distance d between the comparison template and the converted feature data array for comparison, and

the distance for determining the success or failure of authentication is the corrected Hamming distance.

5. The biometric authentication method according to claim 1,

wherein the generation of the position correction template includes generating a local feature data array for registration by cutting a part of the feature data array for registration,

the generation of the converted feature data for position correction includes generating a partial feature data array for authentication by cutting a part of the feature data array for registration,

in the calculation of the position correction amount, a distance is calculated while the partial feature data array for authentication is repeatedly shifted relative to the local feature data array for registration, and a shift amount with which the distance is minimized is defined as the position correction amount, and

in the generation of the corrected feature data array, the feature data array for authentication is shifted by the position correction amount.

6. The biometric authentication method according to claim 1, further comprising the steps of:

generating a conversion parameter for position correction at the biometric information registration time, the conversion parameter for position correction being used to convert the feature data array for registration,

the generation of the position correction template includes;

cutting a local feature data array for registration from the feature data array for registration; and

generating the position correction template by converting the local feature data array for registration using the conversion parameter for position correction, and

the generation of the converted feature data for position correction includes;

cutting a partial feature data array for authentication from the feature data array for authentication; and

generating the converted feature data for position correction by converting the partial feature data array for authentication using the conversion parameter for position correction.

7. The biometric authentication method according to claim 6,

wherein the conversion parameter for position correction is a randomly generated reversible filter,

the conversion of the local feature data array for registration using the conversion parameter for position correction includes:

generating an encoded local feature data array for registration by replacing values 0, 1, and * of elements of the local feature data array for registration with values a, b, and c of any one of predetermined integers and real numbers,

inversely sorting the encoded local feature data array for registration; and

convoluting the filter into the inversely sorted array,

the conversion of the partial feature data array for authentication using the conversion parameter for position correction includes;

generating an encoded partial feature data array for authentication by replacing values 0, 1, and * of elements of the partial feature data array for authentication with values a′

, b′

, and c′

of any one of predetermined integers and real numbers; and

deconvoluting the filter into the encoded partial feature data array for authentication, and

the calculation of the position correction amount includes;

calculating a correlation array between the encoded partial feature data array for authentication and the encoded partial feature data array for authentication, from the position correction template and the converted feature data for position correction;

retrieving the position of an array element having the largest value in the correlation array; and

determining the position correction amount on the basis of the position.

8. A biometric authentication system comprising:

a client including;

a feature data extraction unit that extracts a feature data array for registration from biometric information of a registration applicant at a biometric information registration time and extracts a feature data array for authentication from biometric information of a user at a authentication time;

a conversion-parameter-for-comparison generation unit that generates a first conversion parameter for comparison by converting the feature data array for registration at the registration time and generates a second conversion parameter for comparison by converting the feature data array for authentication at the authentication time;

a conversion-parameter-for-position-correction generation unit that generates a position correction template by converting the feature data array for registration at the registration time;

a feature-data-conversion-for-position-correction unit that generates converted feature data for position correction from the feature data array for authentication at the authentication time; and

a feature-data-conversion-for-comparison unit that generates a comparison template by converting the feature data array for registration using the first conversion parameter for comparison at the registration time, generates a corrected feature data array by performing position correction on the feature data array for authentication on the basis of a position correction amount at the authentication time, and generates a converted feature data array for comparison by converting the corrected feature data array using the second conversion parameter for comparison; and

a server coupled with the client, the server including;

a position correction amount calculation unit that calculates the position correction amount between the feature data array for registration and the feature data array for authentication using the position correction template and the converted feature data for position correction; and

a comparison and determination unit that calculates a distance between the comparison template and the converted feature data array for comparison and determines success or failure of authentication of the user as the registration applicant on the basis of comparison between the distance and a predetermined authentication threshold.

9. The biometric authentication system according to claim 8,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having a predetermined size L,

the first conversion parameter for comparison generated by the conversion-parameter-for-comparison generation unit includes a random mask bit string having the size L,

the comparison template is an array obtained by calculating the exclusive OR between the feature data array for registration and the mask bit string,

the converted feature data array for comparison is an array obtained by calculating the exclusive OR between the corrected feature data array and the mask bit string, and

the distance is a Hamming distance.

10. The biometric authentication system according to claim 9,

wherein the feature data array for registration, the corrected feature data array, and the mask bit string are each a bit string containing a Don'"'"'t care bit “

*”

,

the exclusive OR between the feature data array for registration and the mask bit string for obtaining the comparison template and the exclusive OR between the corrected feature data array and the mask bit string for obtaining the converted feature data array for comparison are each calculated under a rule that if at least one of bits is a Don'"'"'t care bit “

*”

, the exclusive OR between the bits is a Don'"'"'t care bit “

*”

, and

the Hamming distance between the comparison template and the converted feature data array for comparison is the number of bits of “

1”

contained in a bit string obtained by calculating the exclusive OR between the comparison template and the converted feature data array for comparison.

11. The biometric authentication system according to claim 8,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having the predetermined size L,

the generation of the first conversion parameter for comparison by the conversion-parameter-for-comparison generation unit includes:

randomly generating a concatenation array having a size M; and

generating a substitution pattern, the substitution pattern being used to substitute positions of elements of an array for each other, the array having a size of the sum of L and M,

the generation of the comparison template by the feature-data-conversion-for-comparison unit includes;

generating a concatenation array for registration having a size of the sum of L and M by concatenating the feature data array for registration and the concatenation array; and

generating the comparison template by substituting the concatenation array for registration in accordance with the substitution pattern,

the generation of the converted feature data array for comparison by the feature data-conversion-for-comparison unit includes;

generating a modified concatenation array that is distant from the concatenation array by a predetermined offset Hamming distance δ and

has the size M;

generating a concatenation array for authentication having the size of the sum of L and M by concatenating the feature data array for authentication and the modified concatenation array; and

generating the converted feature data array for comparison by substituting the concatenation array for authentication in accordance with the substitution pattern,

the calculation of the distance between the comparison template and the converted feature data array for comparison by the position correction amount calculation unit is calculation of a corrected Hamming distance (d-δ

) by subtracting the offset Hamming distance δ

from the Hamming distance d between the comparison template and the converted feature data array for comparison, and

the distance for determination of the success or failure of authentication by the comparison and determination unit is the corrected Hamming distance.

12. The biometric authentication system according to claim 8,

wherein the generation of the position correction template by the feature-data-conversion-for-position-correction unit includes generating a local feature data array for registration by cutting a part of the feature data array for registration,

the generation of the converted feature data for position correction by the feature-data-conversion-for-position-correction unit includes generating a partial feature data array for authentication by cutting a part of the feature data array for authentication,

in the calculation of the position correction amount by the position correction amount calculation unit, a distance is calculated while the partial feature data array for authentication is repeatedly shifted relative to the local feature data array for registration, and a shift amount with which the distance is minimized is defined as the position correction amount, and

in the generation of the corrected feature data array, the feature data array for authentication is shifted by the position correction amount.

13. The biometric authentication system according to claim 8,

wherein the conversion-parameter-for-position-correction generation unit generates a conversion parameter for position correction at the registration time, the conversion parameter for position correction being used to convert the feature data array for registration,

the generation of the position correction template by the conversion-parameter-for-position-correction generation unit includes:

cutting a local feature data array for registration from the feature data array for registration; and

generating the position correction template by converting the local feature data array for registration using the conversion parameter for position correction, and

the generation of the converted feature data for position correction by the feature-data-conversion-for-position-correction unit includes;

cutting a partial feature data array for authentication from the feature data array for authentication; and

generating the converted feature data for position correction by converting the partial feature data array for authentication using the conversion parameter for position correction.

14. The biometric authentication system according to claim 13,

wherein the conversion parameter for position correction is a randomly generated reversible filter,

the conversion of the local feature data array for registration using the conversion parameter for position correction includes:

generating an encoded local feature data array for registration by replacing values 0, 1, and * of elements of the local feature data array for registration with values a, b, and c of any one of predetermined integers and real numbers,

inversely sorting the encoded local feature data array for registration; and

convoluting the filter into the inversely sorted array,

the conversion of the partial feature data array for authentication using the conversion parameter for position correction includes;

generating an encoded partial feature data array for authentication by replacing values 0, 1, and * of elements of the partial feature data array for authentication with values a′

, b′

, and c′

of any one of predetermined integers or real numbers; and

deconvoluting the filter into the encoded partial feature data array for authentication, and

the calculation of the position correction amount includes;

calculating a correlation array between the encoded partial feature data array for registration and the encoded partial feature data array for authentication, from the position correction template and the converted feature data for position correction;

retrieving the position of an array element having the largest value in the correlation array; and

determining the position correction amount on the basis of the position.

15. A biometric authentication system comprising:

a registration client including;

a first feature data extraction unit that extracts a feature data array for registration from biometric information of a registration applicant at a biometric information registration time;

a first conversion-parameter-for-comparison generation unit that generates a first conversion parameter for comparison, the first conversion parameter for comparison being used to convert the feature data array for registration;

a conversion-parameter-for-position-correction generation unit that generates a position correction template by converting the feature data array for registration; and

a first feature-data-conversion-for-comparison unit that generates a comparison template by converting the feature data array for registration using the first conversion parameter for comparison;

an authentication client including;

a second feature data extraction unit that extracts a feature data array for authentication from biometric information of a user at an authentication time;

a second conversion-parameter-for-comparison generation unit that generates a second conversion parameter for comparison, the second conversion parameter for comparison being used to convert the feature data array for authentication;

a feature-data-conversion-for-position-correction unit that generates converted feature data for position correction from the feature data array for authentication; and

a second feature-data-conversion-for-comparison unit that generates a corrected feature data array by performing position correction on the feature data array for authentication on the basis of the position correction amount and generates a converted feature data array for comparison by converting the corrected feature data array using the second conversion parameter for comparison; and

a server coupled with the registration and authentication clients, the server including;

a position correction amount calculation unit that calculates the position correction amount between the feature data array for registration and the feature data array for authentication using the position correction template and the converted feature data for position correction; and

comparison and determination unit that calculates a distance between the comparison template and the converted feature data array for comparison and determines success or failure of authentication of the user as the registration applicant on the basis of comparison between the distance and a predetermined authentication threshold.

16. The biometric authentication system according to claim 15,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having a predetermined size L,

the first conversion parameter for comparison generated by the first conversion-parameter-for-comparison generation unit includes a random mask bit string having the size L,

the comparison template is an array obtained by calculating the exclusive OR between the feature data array for registration and the mask bit string,

the converted feature data array for comparison is an array obtained by calculating the exclusive OR between the corrected feature data array and the mask bit string, and

the distance is a Hamming distance.

17. The biometric authentication system according to claim 16,

wherein the feature data array fcr registration, the corrected feature data array, and the mask bit string are each a bit string containing a Don'"'"'t care bit “

*”

,

the exclusive OR between the feature data array for registration and the mask bit string for obtaining the comparison template and the exclusive OR between the corrected feature data array and the mask bit string for obtaining the converted feature data array for comparison are each calculated under a rule that if at least one of bits is a Don'"'"'t care bit “

*”

, the exclusive OR between the bits is a Don'"'"'t care bit “

*”

, and

the Hamming distance between the comparison template and the converted feature data array for comparison is the number of bits of “

1”

contained in a bit string obtained by calculating the exclusive OR between the comparison template and the converted feature data array for comparison.

18. The biometric authentication system according to claim 15,

wherein the feature data array for registration and the feature data array for authentication are each a bit string having the predetermined size L,

the generation of the first conversion parameter for comparison by the first conversion-parameter-for-comparison generation unit includes:

randomly generating a concatenation array having a size M; and

generating a substitution pattern,

substitution pattern being used to substitute the positions of elements of an array for each other, the array having a size of the sum of L and M,

the generation of the comparison template by the first feature-data-conversion-for-comparison unit includes;

generating a concatenation array for registration having a size of the sum of L and M by concatenating the feature data array for registration and the concatenation array; and

generating the comparison template by substituting the concatenation array for registration in accordance with the substitution pattern,

the generation of the converted feature data array for comparison by the second feature-data-conversion-for-comparison unit includes;

generating a modified concatenation array that is distant from the concatenation array by a predetermined offset Hamming distance δ and

has the size M;

generating a concatenation array for authentication having a size of the sum of L and M by concatenating the feature data array for authentication and the modified concatenation array; and

generating the converted feature data array for comparison by substituting the concatenation array for authentication in accordance with the substitution pattern,

the calculation of the distance between the comparison template and the converted feature data array for comparison by the position correction amount calculation unit is calculation of a corrected Hamming distance (d-δ

) by subtracting the offset Hamming distance δ

from the Hamming distance d between the comparison template and the converted feature data array for comparison, and

the distance for the determination of the success or failure of authentication by the comparison and determination unit is the corrected Hamming distance.

19. The biometric authentication method according to claim 15,

wherein the generation of the position correction template by the feature-data-conversion-for-position-correction unit includes generating a local feature data array for registration by cutting a part of the feature data array for registration,

the generation of the converted feature data for position correction by the feature-data-conversion-for-position-correction unit includes generating a partial feature data array for authentication by cutting a part of the feature data array for authentication,

in the calculation of the position correction amount by the position correction amount calculation unit, a distance is calculated while the partial feature data array for authentication is repeatedly shifted relative to the local feature data array for registration, and a shift amount with which the distance is minimized is defined as the position correction amount, and

in the generation of the corrected feature data array, the feature data array for authentication is shifted by the position correction amount.

20. The biometric authentication system according to claim 15,

wherein the conversion-parameter-for-position-correction generation unit generates a conversion parameter for position correction at the registration time, the conversion parameter for position correction being used to convert the feature data array for registration,

the generation of the position correction template by the conversion-parameter-for-position-correction generation unit includes:

cutting a local feature data array for registration from the feature data array for registration; and

generating the position correction template by converting the local feature data array for registration using the conversion parameter for position correction, and

the generation of the converted feature data for position correction by the feature-data-conversion-for-position-correction unit includes;

cutting a partial feature data array for authentication from the feature data array for authentication; and

generating the converted feature data for position correction by converting the partial feature data array for authentication using the conversion parameter for position correction.

21. The biometric authentication system according to claim 20,

wherein the conversion parameter for position correction is a randomly generated reversible filter,

the conversion of the local feature data array for registration using the conversion parameter for position correction includes:

generating an encoded local feature data array for registration by replacing values 0, 1, and * of elements of the local feature data array for registration with values a, b, and c of any one of predetermined integers or real numbers,

inversely sorting the encoded local feature data array for registration; and

convoluting the filter into the inversely sorted array,

the conversion of the partial feature data array for authentication using the conversion parameter for position correction includes;

generating an encoded partial feature data array for authentication by replacing values 0, 1, and * of elements of the partial feature data array for authentication with values a′

, b′

, and c′

of any one of predetermined integers or real numbers; and

deconvoluting the filter into the encoded partial feature data array for authentication, and

the calculation of the position correction amount includes;

calculating a correlation array between the encoded partial feature data array for registration and the encoded partial feature data array for authentication, from the position correction template and the converted feature data for position correction;

retrieving the position of an array element having the largest value in the correlation array; and

determining the position correction amount on the basis of the position.