期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：11
页码：9077-9081
出版社：IJECS
摘要：Biometric methods have been played important roles in personal recognition during last twenty years. These methodsinclude the face recognition, finger print and iris recognition. Recent ly iris imaging has many applications in security systems.The aim of this paper is to design and implement a new iris recognition algorithm. In this paper, the new feature extractionmethods according to log-gabor filters and curvelet transform for identifying the iris images are provided. Iris recognition isannular region between the sclera and the pupil of the human eye. In this region, there exists an extraordinary texture includingmany prominent features, on which the recognition is mainly relied. In the existing approach adopted the Scale invariant FeatureTransform (SIFT) to extract the local feature points in both Cartesian and polar coordinate systems. Since it is very likely thatmany local patterns of the iris are similar, the recognition accuracy of the system based on SIFT is not as good as those of thetraditional methods. A novel fuzzy matching strategy with invariant properties, which can provide a robust and effective matc hingscheme for two sets of iris feature points and the nonlinear normalization model, is adopted to provide more accurate positionbefore matching. An effective iris segmentation method is proposed to refine the detected inner and outer boundaries to smoot hcurves. For feature extraction, instead of Log-Gabor filters we propose curvelet transform to detect the local feature points fromthe segmented iris image in the Cartesian coordinate system and to generate a rotation -invariant descriptor for each detectedpoint. The proposed matching algorithm, which is based on the PFM method, is used to compare two sets of feature points byusing the information comprising the local features and the position of each point .
