Bovine Iris Segmentation Using Region-based Active Contour Model

Iris recognition is one of the most reliable and accurate biometric technologies, as the richness and apparent stability of the iris texture make it robust. Iris segmentation is a critical part in iris recognition, because it defines the inner and outer boundaries of iris region which is used for feature analysis. Active contour model, also known as snake, is a powerful image segmentation technique. This paper proposes a novel global and local region-based active contour model to extract the bovine iris from the surrounding structures. The proposed active contour model elicits the iris texture in an iterative fashion and is guided by both global and local intensity information of the image. Then, iris region is normalized into rectangle shape, which is convenient for later feature extraction. Experimental result indicates the efficacy of the proposed technique.