Contourlet Based Finger Print Matching

This paper describes a novel approach to finger print matching using a new mathematical transform: the contourlet transform. Contourlet improves traditional wavelet based approaches by incorporating a directional component. It finds a direct discrete-space construction and is therefore computationally efficient. In this paper, 2-D spectrum is divided into fine slices using iterated directional filter bank (DFB), directional energy distributions for each block from the decomposed subband outputs is then computed. Only dominant directional energy components are employed as elements of the input feature vector, which serves to reduce noise and improve computational efficiency. The proposed algorithm captures both local and global details in a fingerprint as a compact fixed length FingerCode. The fingerprint matching is based on the Euclidean distance between the two corresponding FingerCodes and hence is extremely fast. The method significantly reduces the memory cost and processing time associated with verification, primarily because of the efficient DFB structure and the exploitation of directional specific information. Index Terms – Biometrics, directional energy, directional filter bank (DFB), Contourlet, feature extraction, fingerprints, matching, verification