改进的张量投票算法  

An Improved Tensor Voting Algorithm

作　　者：邵晓芳[1] 孙即祥[1] 

机构地区：[1]国防科技大学电子科学与工程学院,长沙410073

出　　处：《计算机辅助设计与图形学学报》2006年第7期1028-1031,共4页Journal of Computer-Aided Design & Computer Graphics

摘　　要：在引入迭代过程的基础上,修正底层的取向估计结果、修正原始算法的显著性测度函数,并对每次投票结果进行细化和修剪.实验结果表明:文中改进措施有效地解决了张量投票算法在提取主观轮廓中存在的问题.An iterative optimization procedure is developed based on eigenvalue perturbation analysis to complete the contour gaps and reduce the blurring effect of the original method. The iterative optimization procedure also involves reducing the orientation estimation error, revising the salient measure and thinning the tensor voting results. Experimental results show that the proposed algorithm is more efficient than the original method in subjective contour extraction.

关 键 词：计算机视觉 张量投票 主观轮廓 取向估计 边界修复 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]