Gabor and Neural based Face Recognition

Face recognition is a form of computer vision that uses faces to identify a person or verify a person's claimed identity. Main attractive feature of this paper is the Gabor wavelet representation of face images which are invariant to illumination and facial expression changes. Here a neural based algorithm is presented, to classify and detect frontal views of faces. The dimensionality is reduced by the Principal component analysis and this method is robust and accurate. Here a dataset of 300 face images are taken and have better performance in terms of 80-90%recognition rate.