基于二维Otsu和模糊聚类的图像分割算法  

Image segmentation based on two-dimensional Otsu and fuzzy clustering

作　　者：胡敏[1] 宋银龙[1] 

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009

出　　处：《计算机应用研究》2012年第4期1563-1565,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(61075032);安徽省自然科学基金资助项目(090412059)

摘　　要：针对传统二维Otsu算法计算复杂度高的问题,提出一种改进的Otsu图像分割算法。该算法通过求两个一维Otsu法的阈值来代替传统二维Otsu法的阈值,使得计算复杂度得到了降低;同时为了改进分割效果,结合使用了模糊C-均值聚类算法。实验结果表明,改进的算法充分发挥了两者的优势,不仅在计算速度上优于原二维Otsu算法,且分割效果较好。Considering the disadvantage that the classical 2D Otsu thresholding method is time-consuming,this paper proposed an improved algorithm.By calculating two 1D Otsu threshold method instead of the traditional 2D Otsu threshold method,it reduced the complexity of the algorithm.Simultaneously in order to improve the segmentation performance,this algorithm adopted fuzzy C-means clustering method.The experimental results show that this improved algorithm can take the advantages of both.It is better than the traditional 2D Otsu not only in the computation time,but also in the quality.

关 键 词：图像分割 阈值化 二维直方图 OTSU算法 模糊C-均值聚类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]