FINGERPRINT RECOGNITION IN LOW-QUALITY IMAGES

Algorithms are identified which are best suited for an automatic finge rprint recognition system operating on low quality images. New preproc essing algorithms for noise removal and binarization are described. Th ree approaches to classification are investigated: a correlation class ifier, and two feature-based classification schemes. The best results on a database of 80 fingerprints are obtained with spatial-frequency f eatures. Three classifiers (neural net, linear classifier and nearest neighbour) using these features are successful in identifying an indep endent test set. Details of the results are shown. In conclusion sugge stions are made concerning the most suitable algorithms in each of the processing steps.