Neural Network Based Face Recognition Using Gabor Transform

The position, spatial frequency and orientation selectivity properties are believed to have an important role in visual perception. This paper proposes a novel face representation and recognition approach by exploring information jointly in image space, scale and orientation domains. The face image is first decomposed into different scale and orientation responses by convolving multiscale and multiorientation Gabor filters. Second, local binary pattern analysis is used to describe the neighboring relationship not only in image space, but also in different scale and orientation responses. Thus information from different domains is explored to give a novel face image representation for recognition.Neural Networks provide significant benefits in face recognition. They are actively being used for such advantages as locating previously undetected patterns, controlling devices based on feedback, and detecting characteristics in face recognition. It improves the level of accuracy compared with existing face recognition methods. Keywords—Gabor Volume Based Local Binary Pattern (GV-LBP),Gabor Volume Representation, Local Binary Pattern (LBP).