Method and apparatus for user authentication based on feature information

1. A method for user authentication based on feature information, comprising:

judging whether a user to be authenticated belongs to a similar user group, wherein the similar user group comprises at least two similar users, and the similar users are users whose reference feature information meets a preset similarity condition and a preset distinguishability condition; and

authenticating the user to be authenticated according to reference feature information in the similar user group when the user to be authenticated belongs to the similar user group,

wherein the preset distinguishability condition comprises: based on comparisons of similarity degrees between sample feature information of a similar user and each piece of reference feature information in the similar user group to which the similar user belongs, a ratio of a number of successful similarity degree comparisons is greater than a preset ratio value.

2. The method according to claim 1 , wherein the authenticating the user to be authenticated according to reference feature information in the similar user group comprises:

acquiring feature information collected for the user to be authenticated;

comparing the collected feature information with each piece of reference feature information in the similar user group to obtain a first comparison result; and

determining whether the user to be authenticated passes the authentication according to the first comparison result.

3. The method according to claim 2 , wherein the comparing the collected feature information with each piece of reference feature information in the similar user group to obtain a first comparison result comprises:

calculating a first similarity degree between the collected feature information and reference feature information corresponding to a first similar user in the similar user group, and calculating a second similarity degree between the collected feature information and reference feature information corresponding to a second similar user in the similar user group, wherein the first similar user is a similar user having the same identifier information as that of the user to be authenticated, and the second similar user is a similar user whose identifier information is different from that of the user to be authenticated, and

wherein the determining whether the user to be authenticated passes the authentication according to the first comparison result comprises:

determining that the user to be authenticated passes the authentication if the first similarity degree is greater than the second similarity degree; and

determining that the user to be authenticated does not pass the authentication if the first similarity degree is not greater than the second similarity degree.

4. The method according to claim 1 , wherein the judging whether a user to be authenticated belongs to a similar user group comprises:

acquiring identifier information of the user to be authenticated; and

judging whether the identifier information of the user to be authenticated matches identifier information of a similar user in the similar user group that is pre-stored; if yes, determining that the user to be authenticated belongs to the similar user group; otherwise, determining that the user to be authenticated does not belong to the similar user group.

5. The method according to claim 4 , wherein the feature information comprises at least one piece of the following information: a face feature, an iris feature, a fingerprint, or an eyeprint, and the identifier information comprises at least one of an ID number, a communication number, a name, or predetermined identifier information.

6. The method according to claim 1 , wherein the preset similarity condition comprises: a similarity degree of the reference feature information reaches a preset threshold.

7. The method according to claim 1 , further comprising:

acquiring reference feature information and sample feature information corresponding to each one of at least two sample users, wherein the reference feature information of the at least two sample users meets the preset similarity condition;

calculating, for any of the at least two sample users, similarity degrees between the sample feature information corresponding to the sample user and the reference feature information corresponding to each sample user of the at least two sample users;

judging whether the at least two sample users meet the preset distinguishability condition according to the calculated similarity degrees; and

adding the at least two sample users to the same similar user group when the at least two sample users meet the preset distinguishability condition.

8. The method according to claim 7 , wherein the judging whether the at least two sample users meet the preset distinguishability condition according to the calculated similarity degrees comprises:

comparing a third similarity degree between the sample feature information corresponding to any one of the at least two sample users and the reference feature information corresponding to the sample user with a fourth similarity degree between the sample feature information corresponding to the sample user and the reference feature information corresponding to other sample users of the at least two sample users, to obtain a second comparison result;

judging whether the third similarity degree is greater than the fourth similarity degree according to the second comparison result;

if yes, determining that a comparison of similarity degrees between the sample feature information corresponding to the sample user and the reference feature information corresponding to each sample user is successful; otherwise, determining that the comparison of similarity degrees between the sample feature information corresponding to the sample user and the reference feature information corresponding to each sample user is failed; and

collecting statistics on a ratio of a number of successful similarity degree comparisons, and determining that the at least two sample users meet the preset distinguishability condition when the ratio of the number is greater than a preset ratio value.

9. The method according to claim 1 , further comprising:

acquiring a global user information database when the user to be authenticated does not belong to the similar user group, the global user information database comprising reference feature information and identifier information corresponding to each one of users in excess of a preset number;

determining reference feature information corresponding to the user to be authenticated in the global user information database according to identifier information corresponding to the user to be authenticated; and

authenticating the user to be authenticated according to the reference feature information corresponding to the user to be authenticated.

10. The method according to claim 1 , further comprising:

receiving an authentication request of the user to be authenticated, the authentication request comprising identifier information of the user to be authenticated;

when the user to be authenticated belongs to the similar user group, acquiring feature information collected for the user to be authenticated, calculating a first similarity degree between the collected feature information and reference feature information corresponding to a first similar user in the similar user group, and calculating a second similarity degree between the collected feature information and reference feature information corresponding to a second similar user in the similar user group, wherein the first similar user is a similar user having the same identifier information as that of the user to be authenticated, and the second similar user is a similar user whose identifier information is different from that of the user to be authenticated; and

determining that the user to be authenticated passes the authentication if the first similarity degree is greater than the second similarity degree.

11. An apparatus for user authentication based on feature information, comprising:

a processor; and

a memory configured to store computer executable instructions, wherein when executing the computer executable instructions, the processor performs:

judging whether a user to be authenticated belongs to a similar user group, wherein the similar user group comprises at least two similar users, and the similar users are users whose reference feature information meets a preset similarity condition and a preset distinguishability condition; and

authenticating the user to be authenticated according to reference feature information in the similar user group if the user to be authenticated belongs to the similar user group,

wherein the preset distinguishability condition comprises: based on comparisons of similarity degrees between sample feature information of a similar user and each piece of reference feature information in the similar user group to which the similar user belongs, a ratio of a number of successful similarity degree comparisons is greater than a preset ratio value.

12. The apparatus according to claim 11 , wherein when executing the computer executable instructions, the processor further perform:

acquiring feature information collected for the user to be authenticated;

comparing the collected feature information with each piece of reference feature information in the similar user group to obtain a first comparison result; and

determining whether the user to be authenticated passes the authentication according to the first comparison result.

13. The apparatus according to claim 12 , wherein when executing the computer executable instructions, the processor further performs:

calculating a first similarity degree between the collected feature information and reference feature information corresponding to a first similar user in the similar user group, and calculating a second similarity degree between the collected feature information and reference feature information corresponding to a second similar user in the similar user group, wherein the first similar user is a similar user having the same identifier information as that of the user to be authenticated, and the second similar user is a similar user whose identifier information is different from that of the user to be authenticated;

determining that the user to be authenticated passes the authentication if the first similarity degree is greater than the second similarity degree; and

determining that the user to be authenticated does not pass the authentication if the first similarity degree is not greater than the second similarity degree.

14. The apparatus according to claim 11 , wherein when executing the computer executable instructions, the processor further performs:

acquiring identifier information of the user to be authenticated; and

judging whether the identifier information of the user to be authenticated matches identifier information of a similar user in the similar user group that is pre-stored; if yes, determining that the user to be authenticated belongs to the similar user group; otherwise, determining that the user to be authenticated does not belong to the similar user group.

15. The apparatus according to claim 11 , wherein when executing the computer executable instructions, the processor further performs:

acquiring reference feature information and sample feature information corresponding to each one of at least two sample users, wherein the reference feature information of the at least two sample users meets the preset similarity condition;

calculating, for any of the at least two sample users, similarity degrees between the sample feature information corresponding to the sample user and the reference feature information corresponding to each sample user of the at least two sample users;

judging whether the at least two sample users meet the preset distinguishability condition according to the calculated similarity degrees; and

adding the at least two sample users to the same similar user group when the at least two sample users meet the preset distinguishability condition.

16. The apparatus according to claim 11 , wherein when executing the computer executable instructions, the processor further performs:

receiving an authentication request of the user to be authenticated, the authentication request comprising identifier information of the user to be authenticated;

when the user to be authenticated belongs to the similar user group, acquiring feature information collected for the user to be authenticated, calculating a first similarity degree between the collected feature information and reference feature information corresponding to a first similar user in the similar user group, and calculating a second similarity degree between the collected feature information and reference feature information corresponding to a second similar user in the similar user group, wherein the first similar user is a similar user having the same identifier information as that of the user to be authenticated, and the second similar user is a similar user whose identifier information is different from that of the user to be authenticated; and

determining that the user to be authenticated passes the authentication if the first similarity degree is greater than the second similarity degree.

17. A non-transitory storage medium storing computer executable instructions that, when executed by a processor of a device, cause the device to perform a method for user authentication based on feature information, the method comprising:

judging whether a user to be authenticated belongs to a similar user group, wherein the similar user group comprises at least two similar users, and the similar users are users whose reference feature information meets a preset similarity condition and a preset distinguishability condition; and

authenticating the user to be authenticated according to reference feature information in the similar user group if the user to be authenticated belongs to the similar user group,

wherein the preset distinguishability condition comprises: based on comparisons of similarity degrees between sample feature information of a similar user and each piece of reference feature information in the similar user group to which the similar user belongs, a ratio of a number of successful similarity degree comparisons is greater than a preset ratio value.

18. The non-transitory storage medium according to claim 17 , wherein the method further comprises:

receiving an authentication request of the user to be authenticated, the authentication request comprising identifier information of the user to be authenticated;

when the user to be authenticated belongs to the similar user group, acquiring feature information collected for the user to be authenticated, calculating a first similarity degree between the collected feature information and reference feature information corresponding to a first similar user in the similar user group, and calculating a second similarity degree between the collected feature information and reference feature information corresponding to a second similar user in the similar user group, wherein the first similar user is a similar user having the same identifier information as that of the user to be authenticated, and the second similar user is a similar user whose identifier information is different from that of the user to be authenticated; and

determining that the user to be authenticated passes the authentication if the first similarity degree is greater than the second similarity degree.