SP-NET: One Shot Fingerprint Singular-Point Detector
This work addresses the need for accurate and efficient singular point detection in fingerprint analysis, which is important for biometric security applications, and it represents a significant improvement over existing techniques.
The paper tackles the problem of detecting singular points in fingerprint images, which are crucial for fingerprint recognition and indexing, by proposing a novel deep learning architecture that achieves true detection rates of 98.75%, 97.5%, and 92.72% on three databases, outperforming state-of-the-art methods.
Singular points of a fingerprint image are special locations having high curvature properties. They can play a pivotal role in fingerprint normalization and reliable feature extraction. Accurate and efficient extraction of a singular point plays a major role in successful fingerprint recognition and indexing. In this paper, a novel deep learning based architecture is proposed for one shot (end-to-end) singular point detection from an input fingerprint image. The model consists of a Macro-Localization Network and a Micro-Regression Network along with three stacked hourglass as a bottleneck. The proposed model has been tested on three databases viz. FVC2002 DB1_A, FVC2002 DB2_A and FPL30K and has been found to achieve true detection rate of 98.75%, 97.5% and 92.72% respectively, which is better than any other state-of-the-art technique.