Iris recognition based on 2D Log-Gabor filtering

An iris recognition approach based on 2D Log-Gabor filtering was proposed. Instead of Gabor filters which are not strictly bandpass filters, multichannel Log-Gabor filters were employed to extract the iris phase information. The similarity of two iris codes was measured by their weighted hamming distance. The noise mask codes were adopted to reduce the interference of eyelids occlusion. The experimental results in the CASIA database and UBIRIS database demonstrate that the proposed approach can achieve lower Equal Error Rate and lower False Rejection Rate at the same False Acceptance Rate comparing with traditional approaches.