Certificate verification
A computer-implemented certificate verification method includes: obtaining, by a certificate verification module, at least two images of a certificate, in which the at least two images are acquired under different acquisition conditions; obtaining, from the at least two images, at least two target images that correspond to respective images of the at least two images and that each include an image of a light-reflective coating of the certificate; and determining, based on the at least two target images, a probability that the certificate is an original.
1. A computer-implemented certificate verification method, comprising:
obtaining, by a certificate verification module, at least two images of a certificate, wherein the at least two images are acquired under different acquisition conditions;
obtaining, from the at least two images, at least two target images that correspond to respective images of the at least two images and that each comprise an image of a light-reflective coating of the certificate;
extracting values corresponding to the light-reflective coating from the at least two target images;
dividing each of the at least two target images into areas;
comparing the extracted values from corresponding areas of the target images to obtain respective comparison scores for the areas;
aggregating the comparison scores to obtain an overall score; and
determining, based on the extracted values from the at least two target images, a probability that the certificate is an original including applying a decision policy to the overall score, wherein the decision policy maps aggregated overall scores computed from target images for a certificate to corresponding probabilities that the certificate is an original.
2. The computer-implemented method of claim 1 , wherein the different acquisition conditions comprise at least one of: different acquisition angles and different lighting environments.
3. The computer-implemented method of claim 1 , wherein obtaining the at least two images of the certificate comprises:
obtaining the at least two images from a video of the certificate.
4. The computer-implemented method of claim 1 , wherein obtaining the at least two target images comprises:
performing image binarization processing on the at least two images to obtain binarized images corresponding to the at least two images; and
obtaining the at least two target images from the binarized images.
5. The computer-implemented method of claim 1 , wherein obtaining the at least two target images comprises:
performing image alignment processing on the at least two images to obtained aligned images corresponding to the at least two images; and
obtaining the at least two target images from the aligned images.
6. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
obtaining, by a certificate verification module, at least two images of a certificate, wherein the at least two images are acquired under different acquisition conditions;
obtaining, from the at least two images, at least two target images that correspond to respective images of the at least two images and that each comprise an image of a light-reflective coating of the certificate;
extracting values corresponding to the light-reflective coating from the at least two target images;
dividing each of the at least two target images into areas;
comparing the extracted values from corresponding areas of the target images to obtain respective comparison scores for the areas;
aggregating the comparison scores to obtain an overall score; and
determining, based on the extracted values from the at least two target images, a probability that the certificate is an original including applying a decision policy to the overall score, wherein the decision policy maps aggregated overall scores computed from target images for a certificate to corresponding probabilities that the certificate is an original.
7. The computer-readable medium of claim 6 , wherein the different acquisition conditions comprise at least one of: different acquisition angles and different lighting environments.
8. The computer-readable medium of claim 6 , wherein obtaining the at least two images of the certificate comprises:
obtaining the at least two images from a video of the certificate.
9. The computer-readable medium of claim 6 , wherein obtaining the at least two target images comprises:
performing image binarization processing on the at least two images to obtain binarized images corresponding to the at least two images; and
obtaining the at least two target images from the binarized images.
10. The computer-readable medium of claim 6 , wherein obtaining the at least two target images comprises:
performing image alignment processing on the at least two images to obtained aligned images corresponding to the at least two images; and
obtaining the at least two target images from the aligned images.
11. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
obtaining, by a certificate verification module, at least two images of a certificate, wherein the at least two images are acquired under different acquisition conditions;
obtaining, from the at least two images, at least two target images that correspond to respective images of the at least two images and that each comprise an image of a light-reflective coating of the certificate;
extracting values corresponding to the light-reflective coating from the at least two target images;
dividing each of the at least two target images into areas;
comparing the extracted values from corresponding areas of the target images to obtain respective comparison scores for the areas;
aggregating the comparison scores to obtain an overall score; and
determining, based on the extracted values from the at least two target images, a probability that the certificate is an original including applying a decision policy to the overall score, wherein the decision policy maps aggregated overall scores computed from target images for a certificate to corresponding probabilities that the certificate is an original.
12. The computer-implemented system of claim 11 , wherein the different acquisition conditions comprise at least one of: different acquisition angles and different lighting environments.
13. The computer-implemented system of claim 11 , wherein obtaining the at least two images of the certificate comprises:
obtaining the at least two images from a video of the certificate.
14. The computer-implemented system of claim 11 , wherein obtaining the at least two target images comprises:
performing image binarization processing on the at least two images to obtain binarized images corresponding to the at least two images; and
obtaining the at least two target images from the binarized images.
15. The computer-implemented system of claim 11 , wherein obtaining the at least two target images comprises:
performing image alignment processing on the at least two images to obtained aligned images corresponding to the at least two images; and
obtaining the at least two target images from the aligned images.