Face recognition has received much attention in recent years due to its many applications such as human computer interface, video surveillance and face image database management. It is a challenging technique due to under different lighting conditions, facial expressions and changes in head pose. Single class of feature is not enough to capture all the available information in face. Multi algorithm approach of face recognition improves the accuracy using feature level fusion. This paper proposes an efficient technique for identification of an individual by using Average Half Face (AHF). We propose feature fusion technique using Principal component Analysis (PCA) and Discrete Wavelet Transform (DWT). For classification, distance classifier is used. The proposed method was tested using the cropped extended Yale B database, where the images vary in illumination and expression. High recognition performance has been obtained by fusion of PCA and Wavelet features at feature level for average half face compared to full face.
Keywords
Face Recognition, PCA, Wavelet, Multi Algorithm, Average Half Face.
User
Information