An iris recognition system by laws texture energy measure based k-NN classifier

Biometric recognition technology is correlated generally with very expensive top secure applications. Iris recognition system is one of the effective biometric recognition systems. The main purpose of this study is to recognize the human from different eye images according to their iris texture characteristics. The digital crop images are derived from CASIA iris image database. The texture feature vectors are extracted from the local iris regions by using Laws Texture Energy Measure (TEM) which is a new method for image texture feature extraction. The obtained feature vectors are separated by k-Nearest Neighbor (k-NN) classifier as taking the neighbor number (k) parameter in different values and the performance results of each system are compared according to disparate k values. Finally, the best average performance is observed as 80.74 % in k=1 and 2 neighbors structure of k-NN classifier.