二维Otsu的Z字折线阈值分割方法  

Two-Dimensional Otsu's Zigzag Thresholding Segmentation Method

作　　者：梁义涛 陈亚辉[1,2] 李永锋 LIANG Yitao;CHEN Yahui;LI Yongfeng(College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China;Henan Key Laboratory of Grain Photoelectric Detection and Control,Henan University of Technology,Zhengzhou 450001,China)

机构地区：[1]河南工业大学粮食信息处理与控制教育部重点实验室,河南郑州450001 [2]河南工业大学信息科学与工程学院,河南郑州450001

出　　处：《清远职业技术学院学报》2024年第1期56-66,共11页Journal of Qingyuan Polytechnic

基　　金：国家自然科学基金资助项目“小麦籽粒隐蔽性害虫生物光子学精准检测机理及模型”(3171775);河南省教育厅重点科研计划项目“雾霾降质图像清晰化关键算法研究”(17A510008)。

摘　　要：针对二维直方图阈值分割算法存在的因误分类而导致的分割精度下降的问题,结合二维直方图的先验知识的阈值分割方法,提出了二维Otsu的Z字折线阈值分割方法。基于二维Otsu区域斜分法的基础上进行改进。我们结合二维直方图中的边界区域和噪声区域的信息,采用Z字折线阈值作为分割标准,纠正了普遍存在的错误分类,并利用小概率事件原则自适应确定折线方程,实现高精度图像分割的同时还有效提高了算法的适应性。实验结果表明,改进方法能够有效提高图像分割的精度,增强自适应性,与同类分割算法比较,性能有了明显提升。In the two-dimensional histogram thresholding method,the segmentation accuracy could be degraded due to insufficient misclassification.An improved image segmentation method combining a priori knowledge of two-dimensional histogram and fully considering the influence of edges,the two-dimensional Otsu's zigzag thresholding segmentation method is proposed.Combining a priori information about the edge regions and noisy regions in a two-dimensional histogram,this paper uses a zigzag threshold as a segmentation criterion to correct the overall error classification and uses the small probability events to determine the line equations to achieve segmentation adaptively.Based on extensive experimentation,our method has been ob-served to significantly outperform comparable techniques.

关 键 词：图像分割 阈值分割 OTSU 二维直方图 曲线阈值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]