Methods and apparatuses for processing image and identity verification, electronic devices, and storage media
View Patent ↗Embodiments of the present disclosure provide method for processing images and apparatuses, method for identity verifications and apparatuses, electronic devices, and storage media. The method for processing images includes: obtaining first feature data of a first user image; comparing the first feature data with at least one piece of second feature data included in a database to obtain a comparison result; and determining, according to the comparison result, whether to update the database. According to the embodiments of the present disclosure, it is beneficial to the database to adapt to identity verification in different scenarios and changes in user's appearance generated over time, thereby improving the user experience.
1. A method for processing an image, comprising:
obtaining first feature data of a first user image;
comparing the first feature data with at least one piece of second feature data comprised in a database to obtain a comparison result; and
determining, according to the comparison result, whether to update the database,
wherein when the at least one piece of second feature data refers to multiple pieces of second feature data, the method further comprises:
determining target feature data from the multiple pieces of second feature data based on multiple similarities between the first feature data and the multiple pieces of second feature data; and
updating the target feature data stored in the database based on the first feature data,
wherein the updating the target feature data stored in the database based on the first feature data comprises:
performing fusing processing on the first feature data and the target feature data based on a weight attenuation coefficient to obtain fused feature data.
2. The method according to claim 1 , wherein the comparing the first feature data with at least one piece of second feature data comprised in a database to obtain a comparison result comprises:
determining at least one similarity between the first feature data and the at least one piece of second feature data; and
obtaining the comparison result based on the at least one similarity.
3. The method according to claim 2 , wherein the obtaining the comparison result based on the at least one similarity comprises:
determining a maximum value in the at least one similarity as the comparison result.
4. The method according to claim 1 , wherein the determining, according to the comparison result, whether to update the database comprises:
in response to the comparison result being greater than or equal to a first predetermined threshold, determining to update the database.
5. The method according to claim 4 , wherein the first predetermined threshold is greater than a second predetermined threshold for determining whether a user passes image verification.
6. The method according to claim 1 , wherein the determining, according to the comparison result, whether to update the database comprises:
in response to the comparison result being less than a second predetermined threshold for determining whether a user passes image verification and being greater than or equal to a third predetermined threshold, prompting the user to perform identity verification by using another verification approach different from an image verification approach; and
in response to the verification in the another verification approach being passed by the user, determining to update the database.
7. The method according to claim 6 , wherein the another verification approach comprises at least one of a password verification approach, a fingerprint verification approach, an iris verification approach, or a gesture verification approach.
8. The method according to claim 1 , wherein the method further comprises:
in response to determining to update the database, performing fusing processing on the first feature data and the at least one piece of second feature data to obtain at least one piece of updated feature data.
9. The method according to claim 1 , wherein when the at least one piece of second feature data refers to one piece of second feature data, before the obtaining first feature data of a first user image, the method further comprises:
obtaining feature data of multiple second user images, and
performing fusing processing on the feature data of the multiple second user images to obtain the one piece of second feature data.
10. An electronic device, comprising: a processor and a memory, wherein the memory is configured to store at least one executable instruction, and the at least one executable instruction enables the processor to perform:
obtaining first feature data of a first user image;
comparing the first feature data with at least one piece of second feature data comprised in a database to obtain a comparison result; and
determining, according to the comparison result, whether to update the database,
wherein when the at least one piece of second feature data refers to multiple pieces of second feature data, the at least one executable instruction enables the processor to further perform:
determining target feature data from the multiple pieces of second feature data based on multiple similarities between the first feature data and the multiple pieces of second feature data; and
updating the target feature data stored in the database based on the first feature data,
wherein the updating the target feature data stored in the database based on the first feature data comprises:
performing fusing processing on the first feature data and the target feature data based on a weight attenuation coefficient to obtain fused feature data.
11. A non-transitory computer readable storage medium having computer programs stored thereon, wherein when executed by a processor, the processor is configured to perform:
obtaining first feature data of a first user image;
comparing the first feature data with at least one piece of second feature data comprised in a database to obtain a comparison result; and
determining, according to the comparison result, whether to update the database,
wherein when the at least one piece of second feature data refers to multiple pieces of second feature data, the processor is further configured to perform:
determining target feature data from the multiple pieces of second feature data based on multiple similarities between the first feature data and the multiple pieces of second feature data; and
updating the target feature data stored in the database based on the first feature data,
wherein the updating the target feature data stored in the database based on the first feature data comprises:
performing fusing processing on the first feature data and the target feature data based on a weight attenuation coefficient to obtain fused feature data.
12. The electronic device according to claim 10 , wherein the comparing the first feature data with at least one piece of second feature data comprised in a database to obtain a comparison result comprises:
determining at least one similarity between the first feature data and the at least one piece of second feature data; and
obtaining the comparison result based on the at least one similarity.
13. The electronic device according to claim 12 , wherein the obtaining the comparison result based on the at least one similarity comprises:
determining a maximum value in the at least one similarity as the comparison result.
14. The electronic device according to claim 10 , wherein the determining, according to the comparison result, whether to update the database comprises:
in response to the comparison result being greater than or equal to a first predetermined threshold, determining to update the database.
15. The electronic device according to claim 14 , wherein the first predetermined threshold is greater than a second predetermined threshold for determining whether a user passes image verification.
16. The electronic device according to claim 10 , wherein the determining, according to the comparison result, whether to update the database comprises:
in response to the comparison result being less than a second predetermined threshold for determining whether a user passes image verification and being greater than or equal to a third predetermined threshold, prompting the user to perform identity verification by using another verification approach different from an image verification approach; and
in response to the verification in the another verification approach being passed by the user, determining to update the database.
17. The electronic device according to claim 16 , wherein the another verification approach comprises at least one of a password verification approach, a fingerprint verification approach, an iris verification approach, or a gesture verification approach.
18. The electronic device according to claim 10 , wherein the at least one executable instruction enables the processor to further perform:
in response to determining to update the database, performing fusing processing on the first feature data and the at least one piece of second feature data to obtain at least one piece of updated feature data.
19. The electronic device according to claim 10 , wherein the at least one piece of second feature data refers to one piece of second feature data; and
before the obtaining first feature data of a first user image, the at least one executable instruction enables the processor to further perform:
obtaining feature data of multiple second user images, and
performing fusing processing on the feature data of the multiple second user images to obtain the one piece of second feature data.