Advanced techniques for iris recongnition system - An investigation into a range of problems involved in iris recognition based on a multiscale approache

The complex structure of an iris image result in the difficulty of iris representation especially for iris images of insufficient quality.it has been found that several accurate iris recognition algorithms employ multiscale techniques, which provide a well suited representation for iris data. existing methods either assume that iris images are of sufficient quality or devote much effort to accurately segment them. To address this problem especially when images are noisy or distorted this book proposes a new multiscale approach as a pre-processing step to efficiently localise the iris followed by a new normalisation scheme based on both an optimum unwrapping reference to capture the data and dynamic size to avoid inherent interpolation inefficiencies which cause loss of information. A feature extraction technique, which is based on a combination of some multiscale feature extraction techniques, is also proposed and evaluated.In addition, optimisation techniques are proposed to reduce the effect of eyelids and eyelashes.The experimental results have shown that the proposed system could be used for personal verification in an efficient and effective manner