Fingerprint recognition: state-of-the-art and new directions
After a brief introduction on the overall architecture of a fingerprint recognition system, this lecture presents the classical fingerprint feature extraction and matching steps: segmentation of the ridge-line pattern from the background, estimation of local ridge-line orientation and frequency, enhancement of the ridge-line pattern, minutiae detection and minutiae matching. Some examples of basic Python implementations are provided. New (deep learning based) approaches for latent fingerprint processing are then introduced to highlight the capabilities of the new generation of AFIS.