算法评价是图像配准算法设计中不可缺少的一个环节.本文提出了一种基于配准函数曲线形状定量描述的客观评价方法.方法以曲线的半峰高与半峰宽之比度量配准算法的收敛速度和配准精度,以曲率变化率度量配准算法的鲁棒性,从而有效克服了传统评价方法的不可度量性和主观性;评价简单易行.通过与传统评价方法的比较,实验验证了本章所提出评价方法的有效性和优越性.

1. Pallotta S.Bucciolini B.Russo S Accuracy evaluation of image registration and segmentation tools used inconformal treatment planning of prostate cancer 2006(1)
2. Skerl D.Likar B.Pernus F A protocol for evaluation of similarity measures for rigid registration 2006(6)
3. Gong SJ.O'Keefe GJ.Scott AM Comparison and Evaluation of PET/CT Image Registration 2005
4. Slomka PJ.Mandel J.Downey D Evaluation of voxel-based registration of 3_d power doppler ultrasound and 2-d magnetic 2001(7)
5. Van de Kraats EB.Penney GP.Tomazevic D Standardized evaluation methodology for 2-D-3-D registration 2005(9)
6. Chou YY Transitive and Symmetric Nonrigid Image Registration
7. Fitzpatrick JM.Hill DLG.Shyr Y Visual assessment of the accuracy of retrospective registration of MR and CT images of the brain 1998
8. Maes F.Collignon A.Vandermeulen D Multimodality image registration by maximization of mutual information 1997(2)
9. He Y.Hamza AB.Krim H A generalized divergence measure for robust image registration 2003(5)
10. Cole-Rhodes AA.Johnson KL.LeMoigne J Multiresolution Registration of Remote Sensing Imagery by Optimization of Mutual Information Using a Stochastic Gradient 2003(12)
11. Anthony A.Lofffeld O Image registration using a combination of mutual information and spatial information 2006