Using segmented Fourier-Hankel preprocessing and the HAVNET neural network for Fingerprint identification

摘要

An optical modeless Automatic Fingerprint Identification Systems (AFIS) is presented. The system uses the HAusdorff-Voronoi NETwork (HAVNET), an artificial neural network designed for two-dimensional binary pattern recognition. It uses an adaptation of the Hausdorff distance to determine the similarity between an input pattern and a learned representation. A detailed review of the architecture, the learning equations, and the recognition equations for the HAVNET network are presented. Competitive learning has been implemented in training the network using a nearest-neighbor technique. The AFIS system presented in this paper is applied to the optical recognition of a set of grayscale fingerprints. Image preprocessing includes edge enhancement by histogram equalization, application of a Laplacian filter and thresholding. A segmented Hankel and Fourier transformation in polar coordinates is applied to the binary image. This rotationally and translationally invariant image structure employs the HAVNET neural network for image recognition. Results from the AFIS system without competitive training show typical shape identification problems. Implementation of competitive learning in the HAVNET neural network, improved recognition accuracy in this task to 95%.