Iris recognition using fractional coefficients of transforms, Wavelet Transforms and Hybrid Wavelet Transforms

Iris recognition is the best breed authentication process among all the biometric traits. It is a biometric identification process that uses visual patterns of irides. Iris recognition has been acknowledged as one of the most accurate biometric modalities because of its high recognition rate. Here performance comparison among various proposed techniques of Iris Recognition using the fractional coefficients of transformed Iris images is done considering Genuine Acceptance Ratio(GAR).The proposed method presents Iris recognition using Fractional coefficients of Cosine, Walsh, Haar, Slant and Kekre Transforms their Wavelet Transforms and Hybrid Wavelet Transforms. The experiments are done on 384 samples of palacky university dataset. The experiments showed that the fractional coefficient of transformed iris images gives higher GAR than considering 100% coefficients. Results show that Cosine and Haar Transforms outperforms at 0.10% fractional coefficients. Walsh wavelet transforms gives better performance at 0.10% fractional coefficients among all the Wavelet transform techniques implemented. DCT-Walsh Hybrid Wavelet Transforms outperforms over other Hybrid wavelet transforms implemented at 0.10% fractional coefficients. From the above it is clear that Wavelet Transforms and Hybrid Wavelet Transforms gives better results than Transforms.