Iris Recognition using Fractional Coefficients of Cosine , Walsh , Haar , Slant , Kekre Transforms and Wavelet Transforms

The goal of Iris recognition is to recognize human identity through the textural characteristics of one’s Iris muscular patterns. 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, Hartley, Slant and Kekre Transforms and their 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 giving faster and better iris recognition. Results show that Cosine Transform and Cosine Wavelet Transform at 0.10% energy Compaction, Walsh wavelet at 0.10% energy compaction, Haar Transform and Haar Wavelet Transform at 0.10%energy compaction gives the best results as far as other Transforms and wavelet transforms are considered. It also proves that Wavelet Transforms outperforms Transforms by giving higher GAR at various energy compaction levels.