Abstract:
The paper presents a fingerprint classification system and its performance in an
identification system. The classification scheme is based on fingerprint feature extraction, which
involves encoding the singular points (Core and Delta) together with their relative positions and
directions obtained from a binaries fingerprint image. Image analysis is carried in four stages, namely,
segmentation, directional image estimation, singular-point extraction and feature encoding. A fuzzyneural
network classifier is used to implement the classification of input feature codes according to the well-known Henry system. Fingerprint images from NIST-4database were tested
and, 98.5% classification accuracy was obtained for the five classes- problem.
