图像配准中的非均匀多分辨率分析技术研究

在基于灰度的图像配准中，针对传统的空间均匀采样的多分辨率分析技术在低分辨率时会丢失重要边缘信息，从而产生较多局部极值点，导致误配准问题，通过使用基于灰度概率分布和其梯度信息的抽样方法，提出了非均匀空间采样的多分辨率分析技术．在人体脑部图像的刚体配准实验中应用非均匀多分辨率分析技术，实验结果表明，该非均匀多分辨率分析技术可以有效地减少局部极值点，并提高配准速度．

Non-uniform Multi-resolution Analysis Method in Image Registration

When using traditional multi-resolution analysis of uniform space sub sampling, the important edge information will be lost in image registration based on intensity, which will results in many local maxima and wrong registration. In order to solve the problem, the non-uniform multi-resolution analysis method is proposed, which is based on sub sampling method of intensity probability distribution and gradient information. The non-uniform multiresolution analysis is applied in the rigid registration of brain images. The results of test show that the new method can decrease the number of maxima and improve registration speed.