An improved sequential edge linking model for contour detection in medical images

A novel approach is presented to extract the contour of an ROI (region of interest) in medical images and medical bar-code. It combines threshold segmentation method and SEL (sequential edge linking) algorithm. Threshold is obtained and used to binarilize the whole image. The binary image is processed by the SEL algorithm to extract the contour of an ROI. Experiments show that the proposed method offers excellent ability to suppress noise and false edges. It can extract the precise and continuous contour of an ROI in medical images and medical bar-code.