Efficient IRIS Recognition through Improvement of Feature Extraction and subset Selection - Computer Science > Computer Vision and Pattern RecognitionReport as inadecuate




Efficient IRIS Recognition through Improvement of Feature Extraction and subset Selection - Computer Science > Computer Vision and Pattern Recognition - Download this document for free, or read online. Document in PDF available to download.

Abstract: The selection of the optimal feature subset and the classification has becomean important issue in the field of iris recognition. In this paper we proposeseveral methods for iris feature subset selection and vector creation. Thedeterministic feature sequence is extracted from the iris image by using thecontourlet transform technique. Contourlet transform captures the intrinsicgeometrical structures of iris image. It decomposes the iris image into a setof directional sub-bands with texture details captured in differentorientations at various scales so for reducing the feature vector dimensions weuse the method for extract only significant bit and information from normalizediris images. In this method we ignore fragile bits. And finally we use SVMSupport Vector Machine classifier for approximating the amount of peopleidentification in our proposed system. Experimental result show that mostproposed method reduces processing time and increase the classificationaccuracy and also the iris feature vector length is much smaller versus theother methods.



Author: Amir Azizi, Hamid Reza Pourreza

Source: https://arxiv.org/







Related documents