Noise detection of iris image based on texture analysis

Authors:
Xiangde Zhang;Qi Wang;Hegui Zhu;Cuili Yao;Longcheng Gao;Xianyan Liu
Affiliations:
College of Sciences, Northeastern University, Shenyang, China;College of Sciences, Northeastern University, Shenyang, China;College of Sciences, Northeastern University, Shenyang, China;College of Sciences, Northeastern University, Shenyang, China;College of Sciences, Northeastern University, Shenyang, China;College of Sciences, Northeastern University, Shenyang, China
Venue:
CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Year:
2009

Citing 7
Cited 1

Digital Image Processing

Digital Image Processing
High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Iris Segmentation Method for Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Toward Accurate and Fast Iris Segmentation for Iris Biometrics

IEEE Transactions on Pattern Analysis and Machine Intelligence
Two-Dimensional projection and crossing for iris optimal localization

SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
New Methods in Iris Recognition

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Efficient iris recognition by characterizing key local variations

IEEE Transactions on Image Processing

Adaboost and multi-orientation 2D Gabor-based noisy iris recognition

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Noise detection is very important in an iris recognition system. A novel noise detection method for iris images is presented in this paper. According to the texture feature of different noises, a 2-D circular Gabor Filter is designed to detect specular reflection and estimate pupil's location, then, a I-D peak Gabor Filter is proposed to detect eyelid boundary and eyelashes. Furthermore, eyelid is localized on eyelid boundary image by parabolic Integrodifferential operator. In terms of the experiment on the CASIA-Iris V3-Lamp iris database, which contains 16214 iris images, the correct rate of pupil estimation is 100% and eyelid localization is 99.4% respectively. The results show that the proposed method is quite effective.