Two-Dimensional projection and crossing for iris optimal localization

Authors:
Xueyi Ye;Peng Yao;Liang Wu;Zhenquan Zhuang
Affiliations:
Department of Electronic Science & Technology, University of Science and Technology of China, HeFei, Anhui, P.R China;Department of Electronic Science & Technology, University of Science and Technology of China, HeFei, Anhui, P.R China;Department of Electronic Science & Technology, University of Science and Technology of China, HeFei, Anhui, P.R China;Department of Electronic Science & Technology, University of Science and Technology of China, HeFei, Anhui, P.R China
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 2
Cited 1

High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Personal Identification Based on Iris Texture Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence

Noise detection of iris image based on texture analysis

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates some factors possibly disturbing iris localization in an iris image operated by the localizing pre-processing, and gives an optimal localization method from a new viewpoint different with the past After establishing two-dimensional projection histograms and corresponding matrices of an image edge-rude-field, the method researches the relation between every dimensional projecting character and the tangled distributing traits in the edge-rude-field Then it obtains an as good as possible rude-field of the iris edge using the way of scout and crossing which detect and get rid of the bad points in the edge-rude-field, finally calculates the exact iris boundary After the comparing test and the analysis to an iris image database, the experiment result shows that the robust method can quickly and accurately completes iris localization and is not sensitive to different filters worked on the pre-processing of the localization.