User identity verification method, apparatus and system

1. A user identity verification method, comprising:

sending a facial quality score threshold and a number of eye-print collection steps corresponding to an identity verification mode to a client to obtain facial images based on the facial quality score threshold and obtain eye-print pair images corresponding to the number of eye-print collection steps;

receiving a facial image and one or more eye-print pair images corresponding to an identity verification object from the client, wherein the facial image meets the facial quality score threshold and a number of the one or more eye-print pair images corresponds to the number of eye-print collection steps;

comparing the facial image to a preset facial image, and comparing the one or more eye-print pair images to preset eye-print templates corresponding to the identity verification object; and

when comparison results for the facial image and the one or more eye-print pair images meet preset conditions, sending successful identity verification information to the client.

2. The method according to claim 1 , wherein before sending the facial quality score threshold and the number of eye-print collection steps, the method further comprises:

receiving a user identity verification request;

obtaining a number of preset eye-print templates corresponding to the identity verification object from a preset storage location, wherein the preset storage location stores eye-print templates corresponding to different identity verification objects; and

when the number of eye-print templates corresponding to the identity verification object is no less than a preset threshold, determining a current mode as the identity verification mode.

3. The method according to claim 2 , wherein after obtaining the number of eye-print templates corresponding to the identity verification object, the method further comprises:

when the number of eye-print templates is less than the preset threshold, determining the current mode as an eye-print enrollment mode;

sending a facial quality score threshold and a number of eye-print collection steps corresponding to the eye-print enrollment mode to the client to obtain facial images based on the facial quality score threshold and obtain eye-print pair images corresponding to the number of eye-print collection steps; and

storing the obtained eye-print pair images in the preset storage location as the eye-print templates corresponding to the identity verification object.

4. The method according to claim 1 , wherein comparing the facial image to the preset facial image comprises:

using the facial image and the preset facial image as input to a preset facial algorithm; and

obtaining a facial comparison score corresponding to the identity verification object from the preset facial algorithm.

5. The method according to claim 4 , wherein comparing the one or more eye-print pair images to the preset eye-print templates comprises:

using the one or more eye-print pair images and the eye-print templates corresponding to the identity verification object as input to a preset eye-print algorithm; and

obtaining multiple eye-print liveness scores and an eye-print match score from the preset eye-print algorithm, the number of the multiple eye-print liveness scores corresponding to the number of eye-print collection steps.

6. The method according to claim 5 , wherein the preset conditions include:

the facial comparison score, the multiple eye-print liveness scores, and the eye-print match score are greater than respective preset threshold scores.

7. The method according to claim 4 , further comprising:

when the comparison results for the facial image and the one or more eye-print pair images meet the preset conditions, updating the eye-print templates corresponding to the identity verification object.

8. A user identity verification method, comprising:

receiving a facial quality score threshold and a number of eye-print collection steps corresponding to a current mode;

obtaining a facial image and one or more eye-print pair images corresponding to an identity verification object, the facial image being obtained based on the facial quality score threshold and a number of the one or more eye-print pair images corresponding to the number of eye-print collection steps; and

sending the obtained facial image and the one or more eye-print pair images to a server to perform identity verification of the identity verification object.

9. The user identity verification method according to claim 8 , wherein sending the obtained facial image to a server comprises:

determining an image quality of the obtained facial image is no less than the facial quality score threshold; and

sending the obtained facial image to the server.

10. The user identity verification method according to claim 8 , wherein before sending the obtained one or more eye-print pair images to the server, the method further comprises:

determining the one or more eye-print pair images meet preset eye-print liveness conditions.

11. A non-transitory computer-readable storage medium for user identity verification, storing instructions executable by one or more processors causing the one or more processors to perform operations comprising:

sending a facial quality score threshold and a number of eye-print collection steps corresponding to an identity verification mode to a client to obtain facial images based on the facial quality score threshold and obtain eye-print pair images corresponding to the number of eye-print collection steps;

receiving a facial image and one or more eye-print pair images corresponding to an identity verification object from the client, wherein the facial image meets the facial quality score threshold and a number of the one or more eye-print pair images corresponds to the number of eye-print collection steps;

comparing the facial image to a preset facial image, and comparing the one or more eye-print pair images to preset eye-print templates; and

when comparison results for the facial image and the one or more eye-print pair images meet preset conditions, sending successful identity verification information to the client.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein before sending the facial quality score threshold and the number of eye-print collection steps, the operations further comprise:

receiving a user identity verification request;

obtaining a number of preset eye-print templates corresponding to the identity verification object from a preset storage location, wherein the preset storage location stores eye-print templates corresponding to different identity verification objects; and

when the number of eye-print templates corresponding to the identity verification object is no less than a preset threshold, determining a current mode as the identity verification mode.

13. The non-transitory computer-readable storage medium according to claim 12 , wherein after obtaining the number of eye-print templates corresponding to the identity verification object, the operations further comprise:

when the number of eye-print templates corresponding to the identity verification object is less than the preset threshold, determining the current mode as an eye-print enrollment mode;

sending a facial quality score threshold and a number of eye-print collection steps corresponding to the eye-print enrollment mode to the client to obtain facial images based on the facial quality score threshold and obtain eye-print pair images corresponding to the number of eye-print collection steps; and

storing the obtained eye-print pair images in the preset storage location as the eye-print templates corresponding to the identity verification object.

14. The non-transitory computer-readable storage medium according to claim 11 , wherein comparing the facial image to the preset facial image comprises:

using the facial image and the preset facial image as input to a preset facial algorithm; and

obtaining a facial comparison score corresponding to the identity verification object from the preset facial algorithm.

15. The non-transitory computer-readable storage medium according to claim 14 , wherein comparing the one or more eye-print pair images to the preset eye-print templates comprises:

using the one or more eye-print pair images and the eye-print templates corresponding to the identity verification object as input to a preset eye-print algorithm; and

obtaining multiple eye-print liveness scores and an eye-print match score from the preset eye-print algorithm, the number of the multiple eye-print liveness scores corresponding to the number of eye-print collection steps.

16. The non-transitory computer-readable storage medium according to claim 15 , wherein the preset conditions include:

the facial comparison score, the multiple eye-print liveness scores, and the eye-print match score are greater than respective preset threshold scores.

17. The non-transitory computer-readable storage medium according to claim 14 , wherein the operations further comprise:

when the comparison results for the facial image and the one or more eye-print pair images meet the preset conditions, updating the eye-print templates corresponding to the identity verification object.