An Improved Algorithm for Iris Feature Extraction

摘要：

2D Log-Gabor will produce a crescent-shaped wave form in frequency domain if its angular bandwidth approximates 2π. The grid-like shape will then appear in iris feature images, which reduces the validity of the features. To solve the problem, this paper proposes a new algorithm for iris feature extraction. The algorithm uses the odd-symmetric 2D LogGabor filter to analyze the phase and amplitude of iris texture of different frequencies and orientations, and uses feature fusion to eliminate redundant feature. It successfully prevents the crescentshaped spectrum and grid-like patterns. The experimental results show that the equal error rate (EER) of the proposed algorithm can be 11％ and 38％ lower than the 2D Gabor filter and LogGabor composite filter respectively on average. It clearly justifies the strong robustness of the proposed algorithm against noise and interferences.

作者: Hui Lü Jin Shang Lintao Lü Tao Yang

作者单位: Department of Civil Engineering, Chong Qing University Chong Qing 400045, PR China School of Computer Science and Engineering Xian University of Technology, Xian,Shaanxi 710048, PR School of Computer Science and Engineering Xian University of Technology, Xian, Shaanxi 710048, PR

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 167-171

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）