ABSTRACT

Biometrics deals with the uniqueness of an individual arising from their physiological or behavioral characteristics for the purpose of personal identification. Among many biometrics techniques, iris recognition is one of the most promising approache. This paper presents traditional subspace analysis method for iris recognition. Initially the eye images have been localized in circular form by using Daugman’s grid method and circular Hough transform method. The algorithms for subspace analysis methods namely PCA and LDA are implemented and experimental results are reported. The comparative performance for both the algorithms has been observed in term of recognition rate. The comprehensive experiments completed on UPOL and CASIA V1 iris databases.