Efficient fingerprint singular points detection algorithm using orientation-deviation features

Abstract

Accurate singular point (SP) detection is an important factor in fingerprint (FP) recognition systems. We propose an algorithm to detect SPs in FP images. Our idea is based on the observation that the orientation field (OF) at the regions containing SPs has high variation, whereas in the other regions, it is smooth. Thus, a pixel-wise descriptor that comprises orientation-deviation (OD)-based features is proposed to measure the OF variation in the local neighborhood of a pixel which we call OF energy. Candidate SPs are characterized by locations where the OF energy function has local gradual maxima. Furthermore, the OD-based descriptor exhibits some advanced topological properties, in particular the descriptor profile tendency, which are highly correlated with the SP type. These properties are used to filter out some spurious SPs. A second refining step based on an extended Poincaré index is then applied to keep only genuine SPs with their information. The proposed algorithm has the ability to accurately detect the classical singularities as well as the arch-type SP. Experiments conducted over the public databases FVC2002 db1 and db2 confirm its accuracy and reliability with a reduced false alarm rate in comparison to other proposed methods.

Walking to singular points of fingerprints

“…Fingerprint singular points (upper core, lower core and delta), defined as where the orientation field is discontinuous or the ridge curvature is the high-est, are essential for registration and identification (specially for image-based approach instead of minutiae-based approach) [1,2]. Singular points detection methods have been well studied, including Poincaré index (PI) technique [3,4,5,6,7,8], model-based technique [9,10,11,12], complex filter technique [13,14,15,16,17,18] and others [19,20,21,22]. However, these methods are based on scanning process which consumes a lot of processing time as shown below.…”

“…However it's sensitive to the noise of fingerprint image and easy to detect many spurious singular points. To improve the robustness, different strategies are used, such as replacing closed line integral with surface integral [4], fusing global features [5,6,7] and combining with other local characteristics [8]. They surely need extra processing time compared with the original Poincaré index method.…”