Facial Expression Recognition and Head Tracking in Video Using Gabor Filter

Facial Expression Recognition (FER) from video is an essential research area in the field of Human Computer Interfaces (HCI). In this work, we present a new method to recognize several facial expressions from time sequential facial expression images. Firstly the video sequence is converted to image frames. Sequentially each image frame is subjected to image pre processing. Then the features are extracted using Gabor filter and neural network is used as a classifier. Finally the images are categorized into 5 different forms of basic emotions including happiness, sadness, anger, surprise and neutral. The facial expressions are recognized by eliminating head movement. The Yale database is used to train and evaluate the algorithm. The results of the test on this database of facial expression video show that our proposed system yields a high average performance of about 89% in person independent facial expression recognition.