An application of the onion peeling algorithm for fingerprint verification purposes

Abstract

In this paper, we apply digital image processing techniques using the onion algorithm of computational geometry to develop fingerprint verification. This paper describes the design and implementation of a fingerprint verification system, which operates in two stages: (i) pre-processing stage (ii) feature extraction using a Computational Geometry Algorithm (CCA). This method may be characterized as an alternative method to well-known minutiae extraction algorithms. In particular, the proposed method is based on specific features, which depend exclusively on the pixels brightness degree of the fingerprint image. These were extracted from a specific geometric area (convex layer) in which the dominant brightness value of the fingerprint ranges. The proposed algorithm is also compared to a well-known commercial verification system which is based on a minutiae extraction algorithm proposed by Jain et al. In the experimental part 2256 verification on tests for each of the two methods took place. The results of this comparison showed that the proposed method yields correct positive and correct negative verification scores greater than 99%. In particular, the proposed CGA method produced extremely reliable results even in cases where the tested fingerprints were complete specimens yet the position or pressure applied was not consistent. The computational complexity of the proposed algorithm may also he characterized as extreme competitive.