改进Otsu图像分割方法  

An improved Otsu image segmentation method

作　　者：李想 谢慕君[1] LI Xiang;XIE Mujun(School of Electrical & Electronic Engineering, Changchun University of Technology, Changchun 130012, China)

机构地区：[1]长春工业大学电气与电子工程学院,吉林长春130012

出　　处：《长春工业大学学报》2019年第2期117-120,共4页Journal of Changchun University of Technology

基　　金：国家自然科学基金资助项目(61374051)

摘　　要：在计算分割阈值时,利用类内灰度差方进行多次迭代,获得阈值初值。图像总体灰度均值分别与目标及背景进行方差计算,得到最终分割阈值。In the process of calculating segmentation threshold, intra-class gray-scale difference is used for multiple iterations to obtain the threshold initial value. The variance between the overall gray mean of the images and object, as well the one between the overall gray mean of the images and background, is calculated to get the final segmentation threshold.

关 键 词：图像分割 阈值分割 灰度 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]