Validating identification documents
The method, system, and non-transitory computer-readable medium embodiments described herein are directed to verifying documents. In various embodiments, a server may receive a first image of a front-side of a document. The server may extract a first feature of the front-side of the document from the first image and identify a first environmental feature from the first image. The server may receive a second image of a backside of the document and identify a second feature of the backside of the document from the second image. The server may also identify a second environmental feature from the second image. The server may verify the document by confirming that the first feature matches the second feature and the first environmental feature matches the second environmental feature.
1. A method to validate a document, the method comprising:
receiving, by a processor, a first image of a front-side of the document;
identifying, by the processor, a type of the document using a machine learning algorithm based on the first image;
extracting, by the processor, a first feature of the front-side of the document from the first image;
identifying, by the processor, a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera;
receiving, by the processor, a second image of a backside of the document;
confirming, by the processor, the type of the document using the machine learning algorithm based on the second image;
identifying, by the processor, a second feature of the backside of the document from the second image;
identifying, by the processor, a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and
verifying, by the processor, the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image,
wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance.
2. The method of claim 1 , wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image.
3. The method of claim 1 , wherein the first feature includes an imperceptible data.
4. The method of claim 3 , further comprising extracting, by the processor, the imperceptible data based on a bitmap of each pixel in the first image.
5. The method of claim 1 , wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises:
identifying, by the processor, a boundary of the document in the first and second image; and
identifying, by the processor, a surface outside the boundary of the document in the first and second image.
6. The method of claim 1 , wherein the first feature and the second feature each include at least one of: name, date of birth, height, organ donor status, hair color, eye color, or address.
7. The method of claim 1 , wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document.
8. The method of claim 1 , further comprising:
extracting, by the processor, a first facial image of a user associated with the document from the first image;
extracting, by the processor, a second facial image of the user associated with the document from the second image; and
matching, by the processor, the first facial image to the second facial image.
9. The method of claim 1 , further comprising:
extracting, by the processor, a first signature disposed on the front-side of the document from the first image;
extracting, by the processor, a second signature disposed on the backside of the document from the second image; and
matching, by the processor, the first signature with the second signature.
10. A system to validate a document, the system comprising: at least one memory; and
at least one processor coupled to the at least one memory, the at least one processor configured to:
receive a first image of a front-side of the document;
identify a type of the document using a machine learning algorithm based on the first image;
extract a first feature of the front-side of the document from the first image;
identify a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera;
receive a second image of a backside of the document;
confirm the type of the document using the machine learning algorithm based on the second image;
identify a second feature of the backside of the document from the second image;
identify a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and
verify the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image,
wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance.
11. The system of claim 10 , wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image.
12. The system of claim 10 , wherein the first feature includes an imperceptible data; and
the at least one processor is further configured to extract the imperceptible data based on a bitmap of each pixel in the first image.
13. The system of claim 10 , wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises:
identifying a boundary of the document in the first and second image; and
identifying a surface outside the boundary of the document in the first and second image.
14. The system of claim 10 , wherein the first feature and the second feature each include at least one of: name, date of birth, height, organ donor status, hair color, eye color, or address.
15. The system of claim 10 , wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document.
16. The system of claim 10 , wherein the at least one processor is further configured to:
extract a first facial image of a user associated with the document from the first image;
extract a second facial image of the user associated with the document from the second image; and
match the first facial image to the second facial image.
17. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations, the operations comprising:
receiving a first image of a front-side of a document;
identifying a type of the document using a machine learning algorithm based on the first image;
extracting a first feature of the front-side of the document from the first image using optical character recognition (OCR);
identifying a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera;
receiving a second image of a backside of the document;
confirming the type of the document using the machine learning algorithm based on the second image;
identifying a second feature of the backside of the document from the second image;
identifying a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and
verifying the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image,
wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance.
18. The non-transitory computer-readable medium of claim 17 , wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image.
19. The non-transitory computer-readable medium of claim 17 , wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises:
identifying a boundary of the document in the first and second image; and
identifying a surface outside the boundary of the document in the first and second image.
20. The non-transitory computer-readable medium of claim 17 , wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document.