A novel approach to fingerprint identification using method of sectorization

Fingerprints are one of the most popular biometrics traits. Feature extraction and vector creation are crucial in fingerprint-matching algorithms. For increasing the confidence of fingerprint recognition, different feature vector forms are considered in literature. In this paper, we introduce a complete (fully-implemented) algorithm for fingerprint recognition. The work describes image preprocessing based on our previous works and feature vector creation that bases on sectoralization. The image preprocessing includes filtering, skeletonisation, minutiae extraction by CN (Crossing Number) algorithm and spurious minutiae removal. The feature vector creation is based on dividing the fingerprint into sectors. The division is done on the basis of image height.