特征空间、几何变换、相似性测度以及优化算法是设计医学图象配准方法时要考虑的四个主要因素。
Many investigator explore in the domain. Medical images registration methods have four main factors: features space, geometry transformation, similarity, and optimizing algorithm.
原始图像数据经过小波变换后,根据子带系数之间在空间上和方向上所呈现出的带间相似性,将像素集合重新定义为集合树。
After the DWT of the original image data, and according the similarity between the band shown by subband coefficients in the space and the direction, the collection of pixels is redefined as set tree.
在实际问题求解中,可以根据问题需要取不同相似性函数,以便将问题变换到所需的粒度空间进行处理。
In practice, problems can be transformed into required granular space, by selecting different comparability functions according to the problem.
应用推荐