摘要
针对医学图像配准对鲁棒性强、准确性高和速度快的要求,提出一种基于最小生成树的DoG(d ifference of Gaussian)关键点配准算法。该算法首先从图像上提取DoG关键点,然后将关键点对应的灰度信息融入联合Rényi熵中,最后使用最小生成树来估计联合Rényi熵。新算法结合了DoG关键点的鲁棒性和最小生成树估计Rényi熵的高效性。实验结果表明,在图像含有噪声、灰度不均匀和初始变换范围较大的情况下,该算法在达到良好配准精度的同时,具有较强的鲁棒性和较快的速度。
For medical image registration of good robustness, high-accuracy and speed requirements, this paper proposes a DoG（ difference of Gaussian） keypoints image registration algorithm based on Renyi entropy. This algorithm extracts DoG key points from images, then incorporates grey scale information of the key point into the joint Reuyi entropy, and estimates joint Renyi entropy directly using minimum spanning tree. The new algorithm combines the robustness of DoG key points and the high speed of Renyi entropy estimated by the minimum spanning tree. Experimental results show that in the images with noise, non-uniform intensity and large scope of the initial misalignment case, the algorithm achieves better robustness and higher speed while maintaining good registration accuracy.
出处
《中国图象图形学报》
CSCD
北大核心
2011年第4期647-653,共7页
Journal of Image and Graphics
基金
国家自然科学基金项目(60671050)
辽宁省重大科技计划项目(2008402001)
沈阳市重点技术创新计划项目(2008-9)
