Simple and Fast Face Detection System Based on Edges

Face detection is an important first step to many advanced computer vision, biometrics recognition and multimedia applications, such as face tracking, face recognition, and video surveillance. In this paper, a faster face detection system is proposed with minimal features based on edges. Our proposed framework consists of three steps: initially the images are enhanced by applying median filter for noise removal and histogram equalization for contrast adjustment. In the second step the edge image is constructed from the enhanced image by applying sobel operator. Then a novel edge tracking algorithm is applied to extract the sub windows from the enhanced image based on edges. The rectangle features are calculated for the sub windows, and these feature values are fed into a trained Backpropagation Neural Network (BPN) to classify the sub-window as either face or non-face. The performance of the proposed method is compared with adaboost classifier. The result shows that our proposed method outperforms than the existing in terms of processing time in training and testing.