Fingerprint Orientation Refinement through Iterative Smoothing
This work addresses the specific problem of improving fingerprint recognition accuracy for biometric systems, but it appears incremental as it builds on existing gradient-based methods with new regularization techniques.
The authors tackled the problem of extracting and refining fingerprint orientation fields from noisy images, proposing a gradient-based method with a regularization procedure using three new integral operators and a pre-processing technique, and reported results from a numerical experiment to demonstrate the algorithm's efficiency.
We propose a new gradient-based method for the extraction of the orientation field associated to a fingerprint, and a regularisation procedure to improve the orientation field computed from noisy fingerprint images. The regularisation algorithm is based on three new integral operators, introduced and discussed in this paper. A pre-processing technique is also proposed to achieve better performances of the algorithm. The results of a numerical experiment are reported to give an evidence of the efficiency of the proposed algorithm.