Face & Facial Expression Recognition Using Combinational Techniques

Abstract: A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. One of the ways to do this is by comparing selected facial features from the image and a facial database. In this project intend to develop a new robust system for Facial expression recognition using three sub-space techniques, namely Principal Component Analysis (PCA), Independent Component Analysis (ICA), Local Binary Pattern (LBP), and along with the combination of the score value of all the above techniques for better results . The system developed would perform Facial expression recognitions. The six major expressions considered are anger, disgust, fear, happiness, sadness and surprise. Given an input facial image using various techniques the facial features are extracted and its score level is noted and finally Score level of each technique are integrated to develop a new robust facial expression recognition system. Keywords: PCA, LBP, ICA, Feature extraction, Score level fusion.