Multiscale wavelet based edge detection and Independent Component Analysis (ICA) for Face Recognition

In this paper we have proposed wavelet based edge detection algorithm that combines the coefficients of wavelet transforms on a series of scales. The outcome of this algorithm is edginess like information further used to obtain Independent Components using ICA algorithms. The combination of Multiscale wavelet based edge detection and Independent Component Analysis (ICA) is used for Face Recognition becomes a novel approach. The independent components obtained by ICA algorithms are used as feature vectors for classification. The Euclidean distance (L2) classifier is used for testing of images. The algorithm is tested on two different databases i.e Asian face database and Indian face database of face images for variation in illumination, facial expressions and facial poses up to 1800rotation angle. Encouraging results of this unique approach of face recognition has given future direction for research work in this area.