People-credentials comparison authentication method, system and camera

1. An authentication method for person-identity document comparison, which is applicable to a camera, comprising:

acquiring multiple face images of a face;

obtaining at least one target face image that meets a preset condition from the multiple face images,

receiving an ID image obtained by an ID reading support device;

comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively; and

if the number of target face images with person-ID document similarities higher than a preset similarity threshold reaches a first preset number, determining that the authentication is successful;

wherein, obtaining at least one target face image that meets a preset condition from the multiple face images comprises:

based on a preset face scoring strategy, obtaining at least one target face image with a score higher than a preset score threshold from the multiple face images, wherein the preset face scoring strategy comprises factors containing at least one of front face, non-obscuration and clarity;

or,

based on the preset face scoring strategy, obtaining target face images that meet a second preset number from the multiple face images according to a descending order of the score.

2. The method of claim 1 , wherein, acquiring multiple face images comprises:

determining a region of interest for acquiring a face based on a preset installation position of the camera and a preset capture range; wherein, the preset installation position is an installation position that meets a preset height range and a preset depression angle range; and

continuously acquiring images in the region of interest, and determining face images in all images by a face recognition technology.

3. The method of claim 1 , wherein, after determining that the authentication is successful if the number of target face images with person-ID document similarities higher than the preset similarity threshold reaches the first preset number, the method further comprises:

sending at least one of a target face image with a maximum person-ID document similarity, respective target face images, the ID image and a result of successful authentication to a client, so that the client displays at least one of:

the target face image with the maximum person-ID document similarity, respective target face images, the ID image and the result of successful authentication.

4. The method of claim 1 , wherein, comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively comprises:

extracting face features from the ID image and each target face image to obtain face features of the ID image and face features of each target face image; and

matching the face features of the ID image with the face features of each target face image one by one, to obtain a person-ID document similarity for each target face image.

5. The method of claim 1 , wherein, if the number of target face images with person-ID document similarities higher than the preset similarity threshold reaches the first preset number, determining that the authentication is successful, comprises:

comparing a person-ID document similarity for each target face image with the preset similarity threshold in sequence, to obtain the number of target face images with person-ID document similarities greater than the preset similarity threshold by statistics; and

if the number of target face images with person-ID document similarities greater than the preset similarity threshold reaches the first preset number, determining that the authentication is successful.

6. The method of claim 1 , wherein, after comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively, the method further comprises:

if the number of target face images with person-ID document similarities not lower than the preset similarity threshold is lower than a third preset number, determining that the authentication fails, and outputting authentication failure information.

7. The method of claim 6 , wherein, outputting authentication failure information comprises:

sending at least one of a target face image with a maximum person-ID document similarity, respective target face images, the ID image and a result of authentication failure to a client, so that the client displays at least one of:

the target face image with the maximum person-ID document similarity, each target face image, the ID image and the result of authentication failure.

8. A camera, comprising:

a lens, configured for acquiring multiple face images of a face; and

a processor, configured for obtaining at least one target face image that meets a preset condition from the multiple face images; receiving an ID image obtained by an ID reading support device; comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively; and, if the number of target face images with person-ID document similarities higher than a preset similarity threshold reaches a first preset number, determining that the authentication is successful;

wherein, the processor is specifically configured for:

based on a preset face scoring strategy, obtaining at least one target face image with a score higher than a preset score threshold from the multiple face images, wherein the preset face scoring strategy comprises factors containing at least one of front face, non-obscuration and clarity;

or,

based on the preset face scoring strategy, obtaining target face images that meet a second preset number from the multiple face images according to a descending order of the score.

9. The camera of claim 8 , wherein, the lens is specifically configured for:

determining a region of interest for acquiring a face based on a preset installation position of the camera and a preset capture range; wherein, the preset installation position is an installation position that meets a preset height range and a preset depression angle range; and

continuously acquiring images in the region of interest, and determining face images in all images by a face recognition technology.

10. The camera of claim 8 , wherein, the processor is further specifically configured for:

sending at least one of a target face image with a maximum person-ID document similarity, respective target face images, the ID image and a result of successful authentication to a client, so that the client displays at least one of:

the target face image with the maximum person-ID document similarity, respective target face images, the ID image and the result of successful authentication.

11. The camera of claim 8 , wherein, the processor is further specifically configured for:

extracting face features from the ID image and each target face image to obtain face features of the ID image and face features of each target face image; and

matching the face features of the ID image with the face features of each target face image one by one, to obtain a person-ID document similarity for each target face image.

12. The camera of claim 8 , wherein, the processor is further specifically configured for:

comparing a person-ID document similarity for each target face image with the preset similarity threshold in sequence, to obtain the number of target face images with person-ID document similarities greater than the preset similarity threshold by statistics; and

if the number of target face images with person-ID document similarities greater than the preset similarity threshold reaches the first preset number, determining that the authentication is successful.

13. The camera of claim 8 , wherein, the processor is further specifically configured for:

if the number of target face images with person-ID document similarities not lower than the preset similarity threshold is lower than a third preset number, determining that the authentication fails, and outputting authentication failure information;

wherein, the processor is further specifically configured for:

sending at least one of a target face image with a maximum person-ID document similarity, respective target face images, the ID image and a result of authentication failure to a client, so that the client displays at least one of:

the target face image with the maximum person-ID document similarity, each target face image, the ID image and the result of authentication failure.

14. An authentication system for person-identity document comparison, comprising:

a camera, configured for acquiring multiple face images of a face; obtaining at least one target face image that meets a preset condition from the multiple face images; receiving an ID image obtained by an ID reading support device; comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively; and, if the number of target face images with person-ID document similarities higher than a preset similarity threshold reaches a first preset number, determining that the authentication is successful, wherein, obtaining at least one target face image that meets a preset condition from the multiple face images comprises: based on a preset face scoring strategy, obtaining at least one target face image with a score higher than a preset score threshold from the multiple face images, wherein the preset face scoring strategy comprises factors containing at least one of front face, non-obscuration and clarity; or, based on the preset face scoring strategy, obtaining target face images that meet a second preset number from the multiple face images according to a descending order of the score; and

an ID reading support device, configured for acquiring the ID image and sending the ID image to the camera.

15. The system of claim 14 , wherein, the camera is connected to the ID reading support device via a connection port.

16. The system of claim 14 , wherein, the system further comprises:

a client, configured for receiving and displaying at least one of: the target face image and a result of the authentication sent by the camera, and the ID image sent by the ID reading support device.

17. The system of claim 16 , wherein, the camera sends the target face images and the result of the authentication to the client via a USB network adapter card; and

the ID reading support device sends the ID image to the client via the USB network adapter card.

18. The system of claim 14 , wherein, the ID reading support device is specifically configured for:

acquiring ID information, and reading a face image corresponding to the ID information from an information base as the ID image;

or,

capturing and extracting a face image from the ID document as the ID image.