Hybrid Feature Based Face Verification and Recognition System Using Principal Component Analysis and Artificial Neural Network

Abstract

In Human Computer Interaction (HCI), the issue of developing an automatic face verification and recognition system has been one of the most important concerns of the researchers due to its wide range of application especially in the areas where there has been a high demand for consistent identification electronic access system for an individual. This paper discusses an approach to verify the human face and recognize the person's face through a still image. The proposed method is a hybrid approach that considers the local components of the face as well as the entire face of a human being. The local facial components comprises of the lips, nose, left eye and right eye. The proposed system has been implemented using Principal Component Analysis (PCA) and the Artificial Neural Network (ANN). The system has been designed to handle the noises, illumination variations and the facial emotions to some extent. Hence, the proposed system proves to be efficient as it gives the correct recognition rate of 93.5% for ideal facial image and approximately 85% for noise affected facial image.