A Hybrid Face Recognition Method Based on Structural and Holistic Features

Abstract

In this paper we have proposed a novel face recognition method. This method is a hybrid of holistic and structural approaches. First, we locate the position of the nose tip and then we divide the image into eight octants with nose tip as the center. The petal projection method is employed on each octant to obtain a radial intensity profile. Then these radial intensity profiles are transformed by DCT for more compact and scale free representation. The transformed coefficient vectors are used to compute the similarity between the images. The proposed method is simple to implement and is efficient. The performance of the proposed method is evaluated on ORL database, and this offers a good trade-off between the recognition rate and the complexity of the method.