Research and improvement of Live-Wire Interactive Algorithm for Medical Image Segmentation
Traditional Live Wire algorithm distinguished the strength edge of objectives uneasily and executive speed of algorithm is slow.For these problems,an improved Live-Wire algorithm is proposed.First it implements anisotropic diffusion filtering to images and constructs a new expense function,then combined with region growing segmentation algorithm,it implements interactive segmentation to medical images.Improved algorithm avoids the shortcomings of the traditional Live-wire algorithm which is sensitive to noise and can not effectively distinguish the edge of the strength,also reduces the time and blindness of dynamic programming to find the optimal path and improves the accuracy and implementation efficiency of the image segmentation.
interactive medical image Live-wire image segmentation
Li Ji-ying Dang Jian-wu
School of Electronic & Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China Key Laboratory of Opto-electronic Technology and Intelligent ControI,Lanzhou Jiaotong University,Min
国际会议
沈阳
英文
1065-1068
2012-09-07（万方平台首次上网日期，不代表论文的发表时间）