一种改进的维吾尔文字图像分割算法研究  

Research on an improved image segmentation algorithm for Uyghur characters

作　　者：伊力哈木.亚尔买买提 YILIHAMU Yaermaimaiti(College of Electrical Engineering,Xinjiang University,Urumqi 830047,China)

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830047

出　　处：《现代电子技术》2017年第4期120-123,共4页Modern Electronics Technique

基　　金：国家自然科学基金(61462082)

摘　　要：针对复杂背景下维吾尔文字图像分割时产生缺陷和干扰问题,提出一种自适应二值势函数目标模糊C均值算法。首先,使用自适应势目标二值函数聚类方法来获取集群的维吾尔文字二值图像分割和聚类中心,然后利用其隶属度矩阵的最佳数量确定模糊计算维吾尔文字图像分割模糊聚类的维吾尔文字图像。实验结果表明,该算法可以实现维吾尔文字图像的自适应分割,准确地分割出维吾尔文字区域部分,同时极大地减少了计算复杂性,有利于实现维吾尔文字图像处理的准确度。Since the Uyghur characters segmented under the complicated background may cause the defect and interference,a binary potential function target segmentation algorithm of the adaptive fuzzy C?means is proposed. The adaptive potential target binary function clustering method is used to segment the Uyghur characters binary image of the clustering and obtain the cluster?ing center. The optimal quantity of the membership matrix is employed to determine the Uyghur characters image by means of the pixel segmentation theory,which obtained from the Uyghur characters′ image segmentation fuzzy clustering with fuzzy calcu?lation. The experimental results show this algorithm can segment the Uyghur characters image adaptively and Uyghur characters area accurately,reduce the computational complexity greatly,and is conducive to the improvement of the image processing accu?racy of the Uyghur characters.

关 键 词：维吾尔文字 势函数 隶属度矩阵 像素分割理论 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]