作　　者： ; ; ;

机构地区： 中北大学信息与通信工程学院

出　　处： 《核电子学与探测技术》 2012年第1期112-115,共4页

摘　　要： 传统的二维Otsu方法考虑了图像的灰度信息和像素间的空间邻域信息,是一种有效的图像分割方法。针对传统二维阈值分割算法处理图像计算时间长、噪声干扰严重等缺点,提出了一种改进的二维快速Otsu阈值自动分割算法。该算法通过改变二维直方图判别域的划分,将阈值搜索空间由二维降为一维,并运用迭代运算提高运算速度。实验结果证明,所用的改进方法更为准确地划分了目标和背景区域,增强了图像的分割效果,运用迭代运算和传统方法相比减少了处理时间。 （2-D） Otsu＇s thresholding method which features a good performance based on grayscale and space information,is one of the main effective image threshold segmentation method.Applying traditional two-dimensional Otsu threshold algorithm in image is not ideal,it is long-paying computation and has too much noise.So this paper presents an improved two-dimensional 0tsu threshold automatic segmentation algorithm.The algorithm gets the optimization threshold value approximately by using new area partition method,which reduces the threshold domain from two dimension to one dimension and partitions the objective area and background area more precisely,improves arithmetic speed by using iterative method.The experiment result proves that the algorithm can partition the objective area and background area more precisely and make the segmentation effect better and pay less computational time than the traditional one.

关 键 词： 图像分割 二维 法 阈值选取

领　　域： [自动化与计算机技术] [自动化与计算机技术]