Face recognition based on DWT and DBC

The face recognition is used to authenticate a person in several real time applications. We propose Face Recognition based on DWT and DBC (FRDD) for PolyU Near Infra Red Face database. The face image is preprocessed to obtain only face part in an image. The DWT is applied on face part to derive four subbands. The LL subband is segmented into one hundred cells of each 5∗5 matrix. The features are extracted from each cell using DBC. The test face image is compared with database images using Euclidian distance. It is observed that the proposed algorithm gives better results compared to the existing algorithm.