A Study on Automated Retinal Vessel Segmentation Using Active Contour Model without Edges

Biometric system is a pattern-recognition system that recognizes a person based on the personal physiological or behavioural characteristics that the person possesses. Human retina, one source of biometric provides the most reliable and with the emerging potentials of automated image processing a highly secure means of authentication is possible. The proposed system describes the development of segmentation methodology in the processing of retinal blood vessel image obtained using fundus colour photography. It is a personal identification system based on the vascular pattern of human retina consisting of three stages; i.e. preprocessing, feature extraction and finally the classification process. The colour fundus retinal image is acquired from the medical fundus camera from which the blood vessel pattern is segmented using morphological operations with the disc shaped structuring element. The features extracted from the vessel pattern by using active contour without region method. General Terms Biometric systems, retinal vascular pattern, fundus.