Model based algorithm for singular point detection from fingerprint images (MP-P3)

Author(s) : Nannan Wu (Department of Automation,Tsinghua University, China) Jie Zhou (Department of Automation,Tsinghua University, China)

Abstract : The detection of singular points (SP) is an important step for automatic fingerprint identification system (AFIS). Conventional algorithms of singular points detection are mainly based on Poincare index. In this paper, a model-based algorithm for singular points (including cores and deltas) detection is proposed. Based on a model, which can describe the directional fields around the singular points in fingerprints, a Hough transform is taken to compute the coefficients of the model, i.e., the exact position of the singular point. Since more information can be used than Poincare index based algorithms, the proposed algorithm has a better performance, especially in eliminating the spurious SPs. At the same time, the voting value of the Hough transform can be used to indicate the likelihood of the detected singular point, which is also important for AFIS. The experiments are taken to illustrate the algorithm¡¯s effectiveness.

Menu