改进的最大熵算法在图像分割中的应用  

Maximum Entropy Method of Image Segmentation Based on Genetic Algorithm

作　　者：王文渊[1] 王芳梅[2] 

机构地区：[1]楚雄师范学院计算机科学系,云南楚雄675000 [2]云南经济管理职业学院,云南昆明650106

出　　处：《计算机仿真》2011年第8期291-294,319,共5页Computer Simulation

摘　　要：研究图像分割优化问题,要求图像分割速度快,清晰度高。针对传统的熵值法在理论上存在的不足,同时抗噪能力差,速度慢,图像模糊等缺陷,造成图像分割过程耗时长,分割效率低等问题。为了提高图像分割效率和精确度,提出一种改进的遗传算法和最大熵算法相结合的图像分割新方法。首先依据图像二维直方图信息来对图像进行特征提取,最后通过遗传算法的选择、交叉和变异操作搜索最优阈值,从而获得最优阈值来对图像进行分割。仿真结果表明,改进的算法与传统最大熵值的图像分割算法相比,分割效率明显提高,同时图像分割的精度也大大提高,加快了图像分割的速度,为设计提供了依据。The traditional entropy threshold has shortcomings of theory and computational complexity,resulting in time-consuming in image segmentation and low efficiency.In order to improve the efficiency and accuracy of image segmentation,an image segmentation method is proposed,which combines the improved genetic algorithm with maximum entropy algorithm.First,the two-dimensional histogram based on the image gray value information is used to extract features,then three genetic operations of selecting,crossover and mutation are used to search for the optimal threshold for image segmentation.Simulation results show that the improved algorithm,compared with the traditional maximum entropy image segmentation algorithm,increases segmentation efficiency,and the accuracy of image segmentation has greatly improved,which speeds up the segmentation speed.

关 键 词：图像分割 遗传算法 最大熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]