Face Recognition based on Gabor Wavelet and Backpropagation Neural Network

Face recognition is an efficient biometric technique which automatically identifies the face of an individual from adatabase of images. This paper proposes a face recognition technique using Gabor wavelet and Backpropagation Neural Network. Although there are so many existing methods, the illumination changes, out of plane rotations and occlusions still remain as challenging problems. In the proposed method, Gabor wavelet coefficients are used for creating feature vector due to its representative capability of the primary visual cortex of Human Visual System. The method also uses Principal Component Analysis for dimensionality reduction. The reduced feature vector is used as the input of the classifier, the Backpropagation neural network. Face recognition has many applications in a variety of fields such as access control, authentication and public surveillance.