Fingerprint Matching Using Rotational Invariant Image Based Descriptor and Machine Learning Techniques

The reliability of fingerprint matching system is highly depends on the perfect alignment algorithm and a suitable matching techniques, which assign a label to the input fingerprint image. In this paper, we propose a rotation invariant fingerprint descriptor and a improved generalization performance classifier. The proposed new descriptor is represented by a histogram of local directional pattern (LDP) computed from extracted region of interest (ROI) of fingerprint images. For fingerprint matching, we propose a single hidden layer neural network (SLFN), which combines a powerful extreme learning machine (ELM) and a well generalized resilient propagation (RPROP) algorithm. The proposed fingerprint matching system comprises the following steps: fingerprint pre-processing/enhancement, ROI extraction, invariant LDP feature extraction, and matching using proposed hybrid classifier. The experimental result shows that the matching accuracy of the proposed system is improved as compare to ELM for lower values of hidden nodes, and other distance based matching approaches proposed in the literature.