Automatic biometric identification based on fingerprintsis still one of the most reliable identification method in criminaland forensic applications. A critical step in fingerprintanalysis without human intervention is to automatically andreliably extract singular points from the input fingerprintimages. These singular points (cores and deltas) not onlyrepresent the characteristics of local ridge patterns but alsodetermine the topological structure (i.e., fingerprint type)and largely influence the orientation field. Poincaré Indexbasedmethods are one of the most common for singularpoints detection. However, these methods usually result inmany spurious detections. Therefore, we propose an enhancedversion of the method presented by Zhou et al. [13]that introduced a feature called DORIC to improve the detection.Our principal contribution lies in the adoption of asmoothed orientation field and in the formulation of a newalgorithm to analyze the DORIC feature. Experimental resultsshow that the proposed algorithm is accurate and robust,giving better results than the best reported results sofar, with improvements in the range of 5% to 7%.
展开▼
