【摘要】 提出基于小波变换的图像配准算法是一种多分辨率匹配算法。该算法可以利用数字减影图像在不同层次上的相似性,配准精度从低至高逐步提高,同时有效地减少运动矢量的搜索复杂度,较好地解决了运算量和检测精度之间的矛盾。该方法被证明是以指数衰减收敛的。整个配准过程在不牺牲配准效果的前提下,提高了匹配速度以及一致性。更多还原

【Abstract】 The proposed registration algorithm based on wavelet transform is a multi-resolution block matching one, which exploits the hierarchical self-similarity of Digital Subtraction Angiography images.This method befit-tingly trades off between the estimation precision and computational complexity, because the registration precision is from coarse to fine, which reduces the searching complexity of motion vector.This technique has been proved that the convergence speed is exponential.The proposed method takes full advantage of the precise location both temporally and frequently which characterizes the wavelet transform. Both the matching speed and consistency are boosted without the loss of matching performance.更多还原