快速模拟退火算法用于噪声图像配准

Fast Algorithm for Simulated Annealing Applied to Registering of Noisy Images

提出一种基于快速模拟退火的噪声图像配准算法.将模拟退火算法纳入鲍威尔(Powell)直接搜索法可以使优化解不陷入局部极值解而获得全局优化解,而且可大大地提高运算效率.实验表明,该算法能对平移、旋转后的噪声图像进行有效地配准.

A registration algorithm for noisy image is proposed in this paper. Using the Powell algorithm in simulated annealing can prevent the optimizing process from being trapped into local minima. Moreover, the computation efficency can be improved substantially. Experimental results show that the proposed registration algorithm can efficiently register noisy images that have undergone translation and rotation.