In recent years

the animal iris recognition tend to become a new animal identification technology

which has potential applications to control the safety of the meat products. This paper presents an approach to cattle iris segmentation. The inner and outer boundaries of cattle iris are fitted respectively as two ellipses which are detected by following the least square principle

according to the feature of cattle iris structure. The inner ellipse is fitted by the edge points on the boundary of pupil. The outer ellipse is fitted by the edge points which are selected randomly on the boundary of iris in order to reduce the influence of the noise on the outer edge. The distance between the outer edge points and the fitted ellipses is calculated to decide the best outer ellipse in the cattle iris image. Normalization is carried out using a geometric method. Experimental results indicate the efficiency of the proposed approach.