基于交换-单亲遗传算法的砂岩三维显微图像重建  

Reconstruction of 3D Microstructure of Sandstone Based on Swap-Partheno-Genetic Algorithm

作　　者：滕奇志[1] 唐棠[1] 何小海[1] 周怡佳[1] 

机构地区：[1]四川大学电子信息学院,成都610065

出　　处：《数据采集与处理》2010年第3期364-368,共5页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(60972130)资助项目

摘　　要：根据二维显微图像中孔隙的统计特征,重建具有相同特征的三维孔隙结构具有重要意义。本文提出用交换算子产生子代个体,替代传统单亲遗传算法中倒位算子、移位算子和突变算子,构建交换-单亲遗传算法。和传统单亲遗传算法相比,该算法能快速更新子代个体的适应值,算法复杂度大大降低。实验结果表明,与常用的模拟退火重建算法相比,交换-单亲遗传算法能有效加快个体能量下降速度,重建结果的统计特征与二维图像更相符,更适合应用于三维重建问题。It is importatnt to reconstruct 3D microstructure of sandstone with the same statistical characteristics of 2D section image.A swap-partheno-genetic algorithm is presented by using a swap operator to replace the reverse,the move and the mutation operators of the normal partheno-genetic algorithm.The computational complexity of the algorithm is reduced compared with the normal partheno-genetic algorithm.Thus,it is easier to calculate the fitness value of the chromosomes of the next generation.The speed of the algorthm is about 105 times of the normal partheno-genetic algorithm.Experiment results show that compared with the popular simulated anealing reconstruction algorithm,the algorthm converges faster.The energy of the reconstruction result is 14.54% of the simulated annealing algorithm,and the statistical characteristics of the algorithm matches with those of the 2D image.

关 键 词：图像处理 单亲遗传算法 三维重建 砂岩微观结构 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术]