LAP Lambert Academic Publishing Facial Expression Recognition System: Extracting Expressions from Facial Images

A human face is a complex object with varying features.The work presents a face recognition system that uses eyes, nose & mouth approximations for training a neural network to recognize faces in different expressions such as natural, smiley, sad and surprised. The developed system is implemented using our face database and browsing images from the computer. We have developed an automatic facial expression recognition system using neural network classifiers. First, we use the rough contour estimation routine, mathematical morphology, and point contour detection method to extract the precise contours of the eyebrows, eyes, and mouth of a face image. Then we define 30 facial points .We choose 6 main action units, being composed of facial characteristic point’s movements, as the input vectors for expression classifiers including radial basis function network. Preprocessing of image is done in Matlab6.0 using various filters, segmentation ,location or tracking Then classification is done using neural networks classifier. Selected facial feature points were automatically trackes and extracted feature vectors were used to classify expression using Fuzzy logic control system. About the Author Madhulika Bhatia is working as a Assistant Professor in Department of Computer Science and Engineering at Amity University,noida.She holds diploma in Computer Science Engineering, B.E in Computer Science Engineering ,MBA in Information Technology,M.Tech in Computer Science & Pursuing Ph.D in Video Object Tracking,Amity University,Noida.