Abstract

Faces represent complex, multidimensional, meaningful visual stimuli. A real-time face recognition system has been implemented which is based on Artificial Neural Network. The system integrates three phases. At the initial phase, an image or a frame is grabbed from a real-time video source or webcam. Then the face region is detected using Local SMQT features and Split up SNoW Classifier and after that the detected face is sent for recognition using Backpropagation Neural Network. Feature extraction has been performed on Gray-Scale images of detected faces using Gray-Scale Morphology that are nonlinear and translationinvariant. The feature extraction and classification networks are trained together, allowing the network to simultaneously perform feature extraction and classification. This system performs extremely well under constrained conditions such as gross variation in expression, position, orientation and illumination which are the complications of face recognition.