Skip to Main Content
As an important step for iris recognition, iris segmentation provides available texture region for subsequent processing. When using portable image capture device, non-ideal iris images are often obtained. Hence, this paper presents a novel algorithm for accurate and fast iris segmentation. By combining level set theory with variational method, probabilistic active contour model (PAC) is established. In addition, region information and probability distribution are used as stop terms. Under this model, initial curve is iteratively driven towards iris boundaries. In the evolving process, eyelids, eyelashes, reflections and shadows are simultaneously detected. Experimental results on iris image database demonstrate that the proposed algorithm outperforms state-of-the-art methods in both accuracy and speed.