An Iris Recognition Technique based on Multi-Feature Extraction and Support Vector Machine

W.-S. Chen, P.-J. Tsai, S.-W. Shih, C.-M. Hsieh, and L. Hsieh (Taiwan)


Biometric Recognition, Iris Recognition, Wavelet Transform, SVM.


This paper presents a biometric recognition system based on the iris of a human eye using wavelet transform and eigen’s theory. The proposed system includes three modules: image preprocessing, feature extraction, and recognition modules. Image preprocessing module uses some image processing algorithms to localize the region of interest of iris from the input image. The feature extraction module defines the “wavelet-eigeniris” and employs the statistical moment concept to extract the features. In recognition module we adopt minimum distance classifier and support vector machine (SVM) as the matching processor. Experimental results show that the system has an encouraging performance on the CASIA database.

Important Links:

Go Back