Other

Rahul Parthe

Vishesh Mistry

Debayan Deb

Neil Rudeforth

Allan Malcolm

A system for an automated real-time digital identity verification based on predictive analytics of user identity data, including a processor of a digital identity verification (DIV) node configured to host a machine learning (ML) module and connected to at least one verifier entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire an identity verification request associated with a user from the at least one verifier entity node, wherein the identity verification request comprising user biographic data and a truncated facial biometric hash extracted from a digital identity feature embedded into an identification document of the user and user biographic data acquired from the identification document and a facial biometric hash generated from the user identification document; parse the identity verification request to derive a plurality of key features; generate at least one feature vector based on the plurality of the key features; and provide the at least one feature vector to the ML module configured to execute a predictive model based on underlying neural network configured to produce at least one user identity verification parameter for generation of a user identity verification verdict.

System and method for AI-based digital identity verification field of disclosure

A fingerprinting solution that uses neural network (NN) based trained Machine Learning (ML) modules in combination with traditional image processing for contactless fingerprint capture, liveness detection to rule out fake fingers, and fingerprint matching using a portable handheld device with integrated camera, thereby eliminating the need for a special device dedicated for fingerprinting. The trained NN modules detect the size and direction of fingers in the captured image, check if fingers are reversed in the image (thereby making nails visible), check if the thumb of the correct hand is captured, and generate fixed-length fingerprint templates for subsequent matching of fingerprints. Three dimensional (3D) depth map of a finger is used to bring the fingerprint resolution to 500 dpi and eliminate distortion caused by the curvature of the finger shape to improve accuracy while scaling and flattening a fingerprint image. The solution facilitates contactless-to-contactless as well as contactless-to-contact based fingerprint matching.

Growing community of inventors

Bloomfield Hills, MI, United States of America

Rahul Parthe