Information distance-based selective feature clarity measure for iris recognition
Craig Belcher, Yingzi Du · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
Iris recognition systems have been tested to be the most accurate biometrics systems. However, poor quality images greatly affect accuracy of iris recognition systems. Many factors can affect the quality of an iris image, such as blurriness, resolution, image contrast, iris occlusion, and iris deformation, but blurriness is one of the most significant problems for iris image acquisition. In this paper, we propose a new method to measure the blurriness of an iris image called information distance based selective feature clarity measure. Different from any other approach, the proposed method automatically selects portions of the iris with most changing patterns to measure the level of blurriness based on their frequency characteristics. Log-Gabor wavelet is used to capture the features of the selected portions. By comparing the information loss from the original features to blurred versions of the same features, the algorithm decides the clarity of the original iris image. The preliminary experiment results show that this method is effective.