Open AccessCore point pixel-level localization by fingerprint features in spatial domain
Author(s) -
Xueyi Ye,
Yuzhong Shen,
Min Zeng,
Yirui Liu,
Huahua Chen,
Zihao Zhao
Publication year - 2022
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2022032
Subject(s) - robustness (evolution) , artificial intelligence , computer science , fingerprint (computing) , ridge , point (geometry) , computer vision , singular point of a curve , pattern recognition (psychology) , pixel , mathematics , geometry , geography , cartography , biochemistry , chemistry , gene
Singular point detection is a primary step in fingerprint recognition, especially for fingerprint alignment and classification. But in present there are still some problems and challenges such as more false-positive singular points or inaccurate reference point localization. This paper proposes an accurate core point localization method based on spatial domain features of fingerprint images from a completely different viewpoint to improve the fingerprint core point displacement problem of singular point detection. The method first defines new fingerprint features, called furcation and confluence, to represent specific ridge/valley distribution in a core point area, and uses them to extract the innermost Curve of ridges. The summit of this Curve is regarded as the localization result. Furthermore, an approach for removing false Furcation and Confluence based on their correlations is developed to enhance the method robustness. Experimental results show that the proposed method achieves satisfactory core localization accuracy in a large number of samples.