Some transform parameters need to be solved after the matching.
在匹配之后，往往需要解求变换参数。
When searching the optimal geometric transform parameters, peak signal-noise ratio (PSNR) was selected as the similarity measure between the reference and floating images.
在寻找最优几何变换参数时，采用峰值信噪比(PSNR)作为参考图像和浮动图像的相似性测度。
The Probabilistic Reaxation Labeling (PRL) technique is applied tO optimize and determine the matching relations so that the registration transform parameters could be obtained.
用概率松弛标签算法优化和确认匹配，进而得出对位所需的变换参数。
应用推荐