Method and apparatus for certificate identification

1. A method, comprising:

determining, by a processor, a target verification mode for verifying a certificate, wherein the target verification mode comprises one or more pieces of movement information of movements performed by a designated body part with respect to the certificate, and the one or more pieces of movement information include information of holding the certificate in one or more designated holding postures;

obtaining, by the processor, one or more images of the certificate;

verifying, by the processor, whether a first image of the one or more images of the certificate comprises the designated body part;

in response to that the first image comprises the designated body part, analyzing, by the processor, whether the first image comprises the one or more pieces of movement information to generate an analysis result, wherein the designated body part comprises a hand, and the analyzing comprises:

detecting an angle, a spatial location, and contours of each finger of the hand in the first image; and

determining whether the first image comprises the one or more pieces of movement information based on the angle, the spatial location, and the contours of each finger of the hand in the first image; and

determining, by the processor based on the analysis result, whether the certificate is a forged certificate.

2. The method of claim 1 , further comprising:

before the verifying whether a first image of the one or more images of the certificate comprises the designated body part:

segmenting, from the first image, a first image region in which the certificate is located; and

determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate.

3. The method of claim 2 , further comprising:

in response to determining that the certificate is not a forged certificate based on the image characteristic, verifying whether the first image comprises the designated body part.

4. The method of claim 2 , wherein

the image characteristic includes at least one of a light spot characteristic, a screen moire characteristic, or a certificate rim characteristic; and

the determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate comprises:

in response to that the image characteristic does not match a characteristic of a sample image, determining that the certificate is a forged certificate, wherein the characteristic of the sample image comprises an image characteristic in an image of the certificate obtained by imaging a sample certificate.

5. The method of claim 1 , wherein the determining a target verification mode for verifying a certificate comprises:

determining at least one verification mode from a verification mode set according to a preset method; and

determining the at least one verification mode as the target verification mode for verifying the certificate of a user;

wherein the verification mode set comprises a plurality of verification modes, and each of the plurality of verification modes respectively comprises movement information of different movements performed by the designated body part with respect to the certificate.

6. The method of claim 1 , further comprising:

in response to that the first image does not comprise the designated body part, or that the first image does not comprise the one or more pieces of movement information, determining that the certificate is a forged certificate.

7. The method of claim 1 , wherein

each of the one or more pieces of the movement information corresponds to a different first movement class; and

the analyzing whether the first image comprises the one or more pieces of movement information comprises:

identifying, from the first image, a second image region where the designated body part is located;

classifying, by a trained movement classification algorithm, body movements in the second image region to obtain one or more second movement classes of the user with respect to the certificate, wherein the trained movement classification algorithm is obtained based on a plurality of pieces of sample movement information of different classes of a designated body part with respect to a certificate; and

in response to that at least one of the one or more second movement classes is inconsistent with a corresponding first movement class, determining that the first image does not comprise the one or more pieces of movement information.

8. A device, comprising:

a processor; and

a memory, configured to store computer-executable instructions executable by the processor to cause the processor to perform operations including:

determining a target verification mode for verifying a certificate, wherein the target verification mode comprises one or more pieces of movement information of movements performed by a designated body part with respect to the certificate, and the one or more pieces of movement information include information of holding the certificate in one or more designated holding postures;

obtaining one or more images of the certificate;

verifying whether a first image of the one or more images of the certificate comprises the designated body part;

in response to that the first image comprises the designated body part, analyzing whether the first image comprises the one or more pieces of movement information to generate an analysis result, wherein the designated body part comprises a hand, and the analyzing comprises:

detecting an angle, a spatial location, and contours of each finger of the hand in the first image; and

determining whether the first image comprises the one or more pieces of movement information based on the angle, the spatial location, and the contours of each finger of the hand in the first image; and

determining, based on the analysis result, whether the certificate is a forged certificate.

9. The device of claim 8 , wherein the operations further comprise:

before the verifying whether a first image of the one or more images of the certificate comprises the designated body part:

segmenting, from the first image, a first image region in which the certificate is located; and

determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate.

10. The device of claim 9 , wherein the operations further comprise:

in response to determining that the certificate is not a forged certificate based on the image characteristic, verifying whether the first image comprises the designated body part.

11. The device of claim 9 , wherein

the image characteristic includes at least one of a light spot characteristic, a screen moire characteristic, or a certificate rim characteristic; and

the determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate comprises:

in response to that the image characteristic does not match a characteristic of a sample image, determining that the certificate is a forged certificate, wherein the characteristic of the sample image comprises an image characteristic in an image of the certificate obtained by imaging a sample certificate.

12. The device of claim 8 , wherein the determining a target verification mode for verifying a certificate comprises:

determining at least one verification mode from a verification mode set according to a preset method; and

determining the at least one verification mode as the target verification mode for verifying the certificate of a user;

wherein the verification mode set comprises a plurality of verification modes, and each of the plurality of verification modes respectively comprises movement information of different movements performed by the designated body part with respect to the certificate.

13. The device of claim 8 , wherein the operations further comprise:

in response to that the first image does not comprise the designated body part, or that the first image does not comprise the one or more pieces of movement information, determining that the certificate is a forged certificate.

14. The device of claim 8 , wherein

each of the one or more pieces of the movement information corresponds to a different first movement class; and

the analyzing whether the first image comprises the one or more pieces of movement information comprises:

identifying, from the first image, a second image region where the designated body part is located;

classifying, by a trained movement classification algorithm, body movements in the second image region to obtain one or more second movement classes of the user with respect to the certificate, wherein the trained movement classification algorithm is obtained based on a plurality of pieces of sample movement information of different classes of a designated body part on a certificate; and

in response to that at least one of the one or more second movement classes is inconsistent with a corresponding first movement class, determining that the first image does not comprise the one or more pieces of movement information.

15. A non-transitory computer-readable storage medium storing computer-executable instructions executable by at least one processor to cause the at least one processor to performs operations including:

determining a target verification mode for verifying a certificate, wherein the target verification mode comprises one or more pieces of movement information of movements performed by a designated body part with respect to the certificate, and the one or more pieces of movement information include information of holding the certificate in one or more designated holding postures;

obtaining one or more images of the certificate;

verifying whether a first image of the one or more images of the certificate comprises the designated body part;

in response to that the first image comprises the designated body part, analyzing whether the first image comprises the one or more pieces of movement information to generate an analysis result, wherein the designated body part comprises a hand, and the analyzing comprises:

detecting an angle, a spatial location, and contours of each finger of the hand in the first image; and

determining whether the first image comprises the one or more pieces of movement information based on the angle, the spatial location, and the contours of each finger of the hand in the first image; and

determining, based on the analysis result, whether the certificate is a forged certificate.

16. The non-transitory computer-readable storage medium as claimed of claim 15 , wherein the operations further comprise:

before the verifying whether a first image of the one or more images of the certificate comprises the designated body part:

segmenting, from the first image, a first image region in which the certificate is located; and

determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate.

17. The non-transitory computer-readable storage medium as claimed in claim 16 , wherein the operations further comprise:

in response to determining that the certificate is not a forged certificate based on the image characteristic, verifying whether the first image comprises the designated body part.

18. The non-transitory computer-readable storage medium as claimed in claim 16 , wherein

the image characteristic includes at least one of a light spot characteristic, a screen moire characteristic, or a certificate rim characteristic; and

the determining, based on an image characteristic in the first image region, whether the certificate is a forged certificate comprises:

in response to that the image characteristic does not match a characteristic of a sample image, determining that the certificate is a forged certificate, wherein the characteristic of the sample image comprises an image characteristic in an image of the certificate obtained by imaging a sample certificate.

19. The non-transitory computer-readable storage medium as claimed in claim 15 , wherein the determining a target verification mode for verifying a certificate comprises:

determining at least one verification mode from a verification mode set according to a preset method; and

determining the at least one verification mode as the target verification mode for verifying the certificate of a user;

wherein the verification mode set comprises a plurality of verification modes, and each of the plurality of verification modes respectively comprises movement information of different movements performed by the designated body part with respect to the certificate.

20. The non-transitory computer-readable storage medium as claimed in claim 15 , wherein the operations further comprise:

in response to that the first image does not comprise the designated body part, or that the first image does not comprise the one or more pieces of movement information, determining that the certificate is a forged certificate.