Open AccessResearch on iris location based on improved particle swarm algorithm and sub-regional noise reduction
Author(s) -
Wanchao Zhu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1654/1/012042
Subject(s) - iris recognition , iris (biosensor) , normalization (sociology) , artificial intelligence , particle swarm optimization , computer vision , segmentation , computer science , noise reduction , biometrics , pattern recognition (psychology) , noise (video) , image (mathematics) , algorithm , sociology , anthropology
Iris localization is the basis of iris recognition, iris medical diagnosis and other technical fields. In view of image of Asian iris, according to the characteristics of the human eye pupil, the combination method of image back-complement enhancement and improved particle swarm optimization is firstly adopted to fit and locate the inner circle of iris. Then, combined with the characteristics of the outer iris boundary, the outer iris circle is located by using the method of sub-regional noise reduction and improved particle swarm optimization. Meanwhile, coordinate transformation approach is introduced for normalization of image. Finally, the feasibility of the method is verified by using iris library of Chinese Academy of Sciences and the self-built iris library sample. This study successfully overcomes the interference of the spot in library and can efficiently complete the segmentation of the iris region.