Iris Recognition Based on Empirical Mode Decomposition

摘要：

Empirical Mode Decomposition(EMD),a multi-resolution decomposition technique,is adaptive andsuitable for nonlinear,non-stationary data analysis.We adopt the EMD approach to decompose the Irisimages into many ingredients with different frequencyrange,and exploit the mutual information criterion toextract proper parts of them as features for recognition.The proposed method can solve the problem ofillumination variation and eyelidleyelash occlusion.Experimental results show that the performance of theproposed method is encouraging and comparable tothe state-of-the-art iris recognition algorithm.

关键词： Biometrics iris recognition feature extraction mutual information

作者: Han Min Peng Yuhua Sun Weifeng

作者单位: School of Information Science and Engineering,Shandong University,Jinan 250100,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 1054-1058

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）