Difference Squared Hausdorff Distance Based Medical Image Registration
In medical image registration, Hausdorff distance has only represented the similarity of the feature points of the images, not considered the overall information of the images, and it is sensitive to disturbances and noise. This paper proposes an improved Hausdorff Distance(HD) metric-the Difference Squared Hausdorff Distance(DSHD) metric, taking the whole information of the images as a part of the metric. It adds an overall factor-the difference square between the images, to the traditional Hausdorff distance, and forms DSHD. The experiment results show that the method solves the problem the traditional Hausdorff distance exits, and improves the registration precision.
Hausdorff Distance Difference Square DSHD Image Registration
Anna Wang Xiyan Sun Xiaoxing Zhou Wenjuan Hu
College of Information Science and Engineering Northeastern University Liaoning, Shenyang, 110004, China
国际会议
海口
英文
150-153
2011-02-22(万方平台首次上网日期,不代表论文的发表时间)