基于二维最小Tsallis交叉熵和遗传算法的快速图像分割  

Fast Image Segmentation Based on Two-Dimensional Minimum Tsallis-Cross Entropy and GA

作　　者：魏伟一[1,2] 李战明[1] 张国权[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,甘肃兰州730050 [2]西北师范大学数学与信息科学学院,甘肃兰州730070

出　　处：《昆明理工大学学报（理工版）》2010年第5期61-65,共5页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：甘肃省自然科学研究基金项目(项目编号:0803RJZA025)

摘　　要：针对二维Otsu分割方法在求取最佳阈值时假设部分区域近似为0,降低了分割精度,以及采用的shannon熵因为具有广延性而忽略了两个分割子系统之间的相互作用的问题,提出一种基于二维最小Tsallis交叉熵和微粒群寻优的快速图像分割.利用灰度-梯度直方图并聚类得到有用区域,以具有非广延性的二维最小Tsallis交叉熵为优化函数,采用遗传算法得到最优的二维阈值.实验表明该算法对噪声图像具有良好的分割效果和较强的实时处理能力.The 2-D Otsu method degrades the efficiency of image segmentation because it supposes partial region close to zero and utilizes shannon entropy as the optimization function which has extensive property.To solve such problems,a fast image segmentation method based on 2-D minimum Tsallis-cross entropy and particle swarm optimization is proposed in this paper.The useful region is obtained by calculating and clustering gray level-gradient histogram.Minimum Tsallis-cross entropy is adopted as the optimization function.The optimal threshold is then realized by genetic algorithm.It is shown through the experiment results that the proposed algorithm achieves a good segmentation quality and real-time computation.

关 键 词：图像分割 Tsallis交叉熵 微粒群 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]