Iris localization based on the Hough transform, a radial-gradient operator, and the gray-level intensity

The iris biometric recognizes a human based on his/her iris texture, which is a stable and unique feature for every individual. A typical iris biometric system performs better for the ideal data, which is acquired under controlled conditions. However, its performance degrades when localizing iris in non-ideal data containing the noisy issues, e.g., the non-uniform illumination, defocus, and non-circular iris boundaries. This study proposes a reliable algorithm to localize iris in such images robustly. First, a small region containing the coarse location of iris is localized. Next, the pupillary boundary is extracted within this small region using an iterative-scheme comprising an adaptive binarization and a pupil location verification test. Following that, the limbic boundary is localized by reusing the Hough accumulator. The iris location is also verified through a gray-level test. After that, the pupillary and limbic boundaries are regularized by applying an enhanced method comprising a Radial-gradient operator (RGO), an error-transform (ET), and the Fourier series. Experimental results, obtained on the CASIA-IrisV3, CASIA-IrisV4, MMU V1.0, and MMU(new) V2.0 iris databases, show superiority of the proposed technique over some of the contemporary techniques.