A Wavelet Transform Based Technique For The Recognition Of The Human Iris
Wageeh Boles · Information Sciences, Signal Processing and their Applications · 1996
A new approach for the recognition of the iris of human eyes based on the wavelet transform is presented. It specifically uses the zero-crossings of the wavelet transform of the unique features obtained from the grey level profiles of the ins. The recognition process is performed in two stages. The fxst stage consists of building a one-dimensional representation of the grey level profiles of the iris, followed by obtaining the wavelet transform zerocrossings of the resulting representation. The second stage is the matching procedure for iris recognition. The proposed approach uses only a few selected intermediate resolution levels for matching, thus making it computationally efficient while being less sensitive to noise and quantisation errors. A normalisation process is implemented to compensate for size variations due to the possible variations in the camera-to-face distance. The technique has been tested on real images obtained under both noise-free and noisy conditions.