Identity Scanner

Identity Scanner is a Zia AI-driven component that enables you to perform secure identity checks on individuals and documents by scanning and processing various ID proofs or official documents. It is a comprehensive suite that incorporates multiple functionalities divided into two major categories- E-KYC and Document Processing.

Note: Catalyst does not store any of the files you upload in its systems. The documents you upload are only used for one-time processing. They are not used for ML model training purposes. Catalyst components are fully compliant with all applicable data protection and privacy laws.

Facial Comparison

Facial Comparison, also known as E-KYC, is a part of Identity Scanner that Compares two faces in two different images to determine if they are the same individual. This will enable you to verify an individual’s identity from their ID proof by comparing it with an existing photo of theirs. For example, you can verify the authenticity of a photo ID, such as an individual’s Aadhaar card, by comparing it with their current photograph.

Note: While the Document Processing feature of Identity Scanner is only relevant to Indian users, the Facial Comparison API and SDK tools are available to a global audience. However, accessing and testing Facial Comparison or E-KYC from the Catalyst console is restricted to the users from IN DC alone.

You can perform a face comparison between a source image and a query image, by specifying the path to both the image files, as shown in the sample code. The compare_face() method processes both these images. The zia reference used below is already defined in the component instance page.

Note: You can mark either the ID proof image or the individual's photograph as the source or the query image. This will not affect the results.

Allowed file formats: .jpg, .jpeg, .png

File size limit: 10 MB

The result of the comparison is set to true if the faces match, or false if they don’t match. The result also contains a confidence score between the range of 0 to 1, which determines the accuracy of the processing. Only if the comparison yields a confidence score of above 50% i.e., 0.5, the result will be set to true.

#Facial Comparison feature implementation img = open('sample1.jpg', 'rb') img2 = open('sample2.jpg', 'rb') result = zia.compare_face(img, img2)

The sample response is shown below :

{ confidence: 0.9464, matched: "true" }

Last Updated 2023-12-18 16:20:08 +0530 +0530