Facial Expression Recognition Using Zernike Moment Invariants

Facial Expression Recognition is rapidly becoming area of interest in computer science and human computer interaction because the most expressive way of displaying the emotions by human is through the facial expressions. In this paper, recognition of facial expression is studied with the help of several properties associated with the face itself. As facial expression changes, the curvatures on the face and properties of the objects such as, eyebrows, nose, lips and mouth area changes. We have used Zernike Moment Invariants method to compute these changes and computed results (changes) are recorded as feature vectors. Zernike moment invariants are used to extract features from expressions and Artificial Neural Network as a classification tool and associated scheme is developed. The Generalized Feed-forward Neural Network recognizes six universal expressions i.e. anger, disgust, fear, happy, sad, and surprise as well as seventh one neutral. The Neural Network is trained and tested by using Scaled Conjugate Gradient Backpropogation Algorithm and we are able to attain 92.9 % classification or recognition rate.