An incremental method for accurate iris segmentation

The paper presents an incremental method for accurate iris segmentation. Firstly, observing the characteristics of iris images, we search for a square region that contains pupil within or nearby which a specular highlight lies. Means and standard deviations of both pupil and specular highlight are employed for detection of such a square, and Integral Images are used to accelerate the detection procedure. Next Canny edge detection followed by Hough transform are used for accurate localization of pupillary boundary. Secondly, by seeking points with maximum gradient along two line segments radiating from pupil center, the radius of outer, limbic boundary can be coarsely determined. According to the rough radius, two annulus sectors are found out within which limbic boundary is finely localized by Canny edge detection plus Hough transform as well. The incremental technique reduces region for edge detection and parameter space for Hough transform, facilitating accurate and fast iris segmentation. Experiments on publicly available UBIRIS database show that the proposed method has encouraging performance.