摘要
研究图像配准精度问题。图像配准技术一直被广泛应用在医学图像和遥感图像等众多领域,由于不同的模式设备对人体内的组织会存在不同的灵敏度和分辨率,造成了图像的分辨率不同,而传统的配准算法对于具有不同的分辨率的图像配准的精度度难以提高。为此提出了一种将改进的自适应遗传算法并应用到图像配准的优化过程中,该算法首先采用进化前后期分别调整交叉概率和变异概率来克服传统遗传算法容易陷入局部最优的缺点,同时采用了刚体旋转方法对图像进行旋转匹配,使得图像可以进行局部的匹配。仿真结果表明了该算法有效的提高了图像配准的精确度,验证了该算法是一种可行性有效的图像配准算法。
Image registration techniques have been widely used in medical imaging,remote sensing images,and other fields.For the traditional image registration algorithms have low efficiency and lack of precision,an improved self-adaptive genetic algorithm was proposed and applied in the optimization process of image registration.The algorithm first adjusted the crossover probability and mutation probability in the early and late evolutionary process to overcome the shortcoming that traditional genetic algorithm is easy to fall into local optimum.Simulation results show that the algorithm effectively improves the accuracy of image registration,and is an efficient image registration algorithm.
出处
《计算机仿真》
CSCD
北大核心
2012年第4期293-296,332,共5页
Computer Simulation
基金
2011年河南省科技厅科技计划项目
残疾人人机交互面部检测及跟踪技术研究(112300410128)
关键词
遗传算法
图像配准
自适应
交叉
变异
Genetic algorithms
Image registration
Adaptive
Cross
Variation