Block ridgelet and SVM based fingerprint matching

Fingerprint matching has been deployed in a variety of security related applications. Traditional minutia detection based identification algorithms do not utilize the rich discriminatory texture structure of fingerprint images. Furthermore, minutia detection requires substantial improvement of image quality. And the efficiency of minutia detection depends on how well the ridges and valleys are extracted. This paper aims to open a new gateway by proposing a different approach for analyzing fingerprints. This approach offers a fine analysis from global characteristics via the block ridgelet transform. We explain how singularities are detected by block ridgelet transform associated to a SVM classifier. The design and implementation of ridgelet identification scheme are discussed. In order to evaluate the performance of the algorithm, FCV2002, FCV2004 fingerprint databases have been considered. The results show that this method has a serious potential in fingerprint matching.