An algorithm of Iris feature-extracting based on 2D Log-Gabor

摘要

This paper proposes a new algorithm for iris feature extraction. The algorithm uses the odd symmetric 2D Log-Gabor filter to analyze the phase and amplitude of iris texture with respect to different frequencies and orientations, and uses feature fusion to eliminate redundant feature. It successfully solves such problems as the crescent-shaped spectrum and grid-like patterns which will appear when 2D Log-Gabor wavelet is used to extract iris features. The experimental results also show that the algorithm proposed has strong robustness against noise and interference, and has important theoretical value and practical significance.