二维直线型最小误差阈值分割法  

Two-Dimensional Linear-Type Mnimum Error Threshold Segmentation Method

作　　者：范九伦[1] 雷博[1] 

机构地区：[1]西安邮电学院信息与控制系,西安710061

出　　处：《电子与信息学报》2009年第8期1801-1806,共6页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60572133)资助课题

摘　　要：一维最小误差阈值法假设了目标和背景的灰度分布服从混合正态分布。考虑到噪声等因素对图像质量的影响,该文在二维灰度直方图上,基于二维混合正态分布假设,给出二维直线型最小误差阈值法的表达式。为了提高算法的运行速度,也给出了快速递推算法。实验表明,二维直线型最小误差阈值法是一个有效的图像分割算法,能够更好地适应目标和背景方差相差较大的含噪图像分割问题。One-dimensional minimum error thresholding method assumes that the histogram distributions of object and background are governed by a mixture Gaussian distribution. Considering the affects of noise and other factors on image quality, based on the assumption of two-dimensional mixture Gaussian distribution, a two-dimensional linear-type minimum error threshold segmentation method is proposed on two-dimensional gray-level histogram. In order to improve the running speed, a fast recursive formula is also given. Experimental results show that the new method is a valuable image segmentation method which can be well adapted to the cases where the variances of the object and the background are distinctly different and contains noises.

关 键 词：图像处理 阈值分割 最小误差阈值法 二维灰度直方图 

分 类 号：TN911.73[电子电信—通信与信息系统]