Automatic Expression Recognition Technique Using 2-D DCT and Eigen Vectors Based Neural Network

Facial expression recognition has attracted much attention in recent years because of its importance in realizing highly intelligent human-machine interfaces. In this paper, we propose a new facial expression recognition technique that utilizes the 2-D DCT of full size facial images and eigenvectors based feed forward neural network. The neural network is designated to separate group of facial expressions with members “happy”, “surprise”, “anger”, “shock”, “disgust” and “sadness”. This work is the first trial to use feed forward neural network, eigenvectors and 2-D DCT simultaneously within a single recognition task. To demonstrate the capability of the proposed recognition technique, we use two databases, including a recently constructed one, which contain 2-D front face images of 120 men and 80 women, respectively. Experimental results reveal that the new technique outperforms, on the whole, the simple vector matching and K-means based vector matching techniques and two recently developed methods using fixed size and constructive neural networks. The mean recognition rates of the new technique have been found as high as 98.5% and 95.8% for these two databases, respectively, which are the best results among those obtained for the same databases. Keywords— Feed forward neural network, 2-DCT, Eigenvectors, Facial expression, Recognition, Facial image, Pattern Recognition, Neural network, Expression classification.