Canny-based Active Contour Accurate Locating
Active contour algorithms is not high precision for the extracted boundary, analysis of the Canny edge detection algorithm, the fusion algorithm is proposed with Canny edge detection and active contour extraction, with which the active contour locating accuracy is improved. In order to meet the initial contour sensitivity of Snake model, the initial snake is extracted with the region growing algorithm, in order to improve falling into local minima because of the high noise and reducing the number of algorithms iterative, it is proposed in the external energy calculation, that the gradient vector is calculated with Canny edge detector, and the external border of Canny detection is as feature control points, the contour deform and evolution with it. Experiments show that the method can resolve the exact contours extraction.
active contours Canny edge detection regional growth contour snake model
Junchai Gao Zhiyong Lei Zemin Wang Keding Yan
School of Electronic Information Engineering Xian Technological University Xian, Shaanxi, 710032, China
国际会议
2011 International Conference on Information and Industrial Electronics(2011年信息与工业电子国际会议 ICIIE 2011)
成都
英文
215-218
2011-01-14(万方平台首次上网日期,不代表论文的发表时间)