NEURAL NETWORKS FOR FINGERPRINT RECOGNITION

After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the p robability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thous and pairs of images originated from a subset of the data base correspo nding to 20 individuals. The error rate currently achieved is less tha n 0.5%. Additional results, extensions, and possible applications are also briefly discussed.