图像分割中采用自适应3次B样条修饰轮廓线.pdfVIP

Received 2001-02-19, revised 2001-09-10 稿件收到日期 2001-02-19, 修改稿收到日期 2001-09-10 CONTOURS EMBELLISHMENT USING ADAPTIVE CUBIC B - SPLINE IN IMAGE SEGMENTATION LI Bin ~U ~ai - Bo Z~UANG Tian - Ge Department of Biomedical Engineering , Shanghai ]iaotong University , Shanghai 200030, China ) Abstract A novel method to get smooth contour in image segmentation process Was presented . First , dynamic programming algorithm Was adopted to process the least cumulative cost matrix of object image , and the optimum contour Was extracted along the direction that the cumulative costs descend fastest . Then the contour Was smoothened and f itted by using adaptive cubic B - spline , Which adjusts the distr ibution of control points adaptively according to the contour curvature . Experiment results of many images shoWed that this method could ef fectively suppress tiny zigzags on contours and could produce smoother contour curve than other previous methods Without losing the f ine structures of the contours at the same time . Key words contour extraction , image segmentation , B - spline , adaptive . 图像分割中采用自适应 3 次 B 样条修饰轮廓线 李 斌 胡海波 庄天戈 上海交通大学生物医学工程系 , 上海 , 200030) 摘要 提出了一种在图像分割中获取连续光滑轮廓线的方法 . 该方法先以动态规划方法处理图像的全局最小累积 代价阵 , 并从累积代价梯度降低最快的方向提取全局最优的轮廓线 . 然后用一种自适应 3 次 B 样条对获得的轮廓 线进行修饰和平滑处理 . 该样条可根据轮廓线不同处的曲率变化情况 , 自适应地调整控制点的分布 . 在各类图像上 的试验表明 , 该方法能有效地消除轮廓线上的小锯齿 , 获得较其它方法更平滑的曲线 , 同时又保留了轮廓线的特征 细节 . 关键词 轮廓提取 , 图像分割 , B 样条 , 自适应 . Introduction The contour is a fundamental f eature of an im- age . It is termed as a set of the pixels , Which con- trast With the near pixels apparently in gray val- ues . The contours consist of the regions that exist betWeen dif f erent objects , dif f erent areas , or dif - f erent basic units . They are the most important f eatures Which image segmentation depends on , and they are also the important information source of texture feature and the basis of shape feature analysis . Most previous algorithms of contour detection obtain objects according to the pixel