Face recognition based verification with reinforced decision support

A facial recognition based verification system is a computer application for automatically identifying or verifying a person from a digital image or a video feature. Our work deals with the recognition of human faces. One stage of recognizing a face is to figure out how the eyes, nose and mouth are placed in the facial structure which are used as decision support entities of the system configured using a Generalized Feed Forward Artificial Neural Network (GFFANN). A specially designed feature set extracted from the eyes, nose and mouth are fed to a GFFANN which provides a decision. The other flow of the system takes the entire face and extracts its features which are applied to another GFFANN. The decision from these two GFFANNs is combined to provide a reinforced decision for verification of a person´s identity. The work includes images with illumination variations. The test results obtained show a success rate of around the higher 90s.