灰度图像的二维交叉熵直线型阈值分割法-电子学报.PDF

第3 期 电 子 学 报 Vol. 37 No. 3 2009 年3月 ACTA ELECTRONICA SINICA Mar. 2009 灰度图像的二维交叉熵直线型阈值分割法 , (西安邮电学院信息与控制系, 陕西西安710061) : 维Otsu 法是 个经典的阈值分割方法, 遵循该方法的构造思想,Li 与 Lee 基于交叉熵提出了 个阈 值分割方法.在解释和说明Li 与 Lee 的方法的基础上,与二维Otsu 直线型阈值分割方法相对应, 提出二维灰度直方图 上的二维交叉熵直线型阈值分割方法并给出快速递推公式. 与二维Otsu 直线型阈值分割法相比, 新方法能够更好的 适应目标和背景方差相差较大的情形,是 个有效的阈值分割方法. : 阈值分割; Otsu 法; 交叉熵 : TN911173 : A : 037222112 (2009) 032 0476205 Two2dime nsional Cro ss2e ntropy Linear2type Threshold Segmentation Method for Gray2level Images FAN Jiu2lun,LEI o ( Department of Inf ormation and Control, Xi. an Institute of Post and Telecommunications, Xi. an, Shaanxi 710061, China ) Ab stract : One2 dimensional Otsu. s method is a classical threshold segmentation method.Following this thought,Li and Lee proposed a threshold segmentation method based on cross2 entropy. A two2 dimensional cross2 entropy linear2type threshold segmenta2 tion method and its fast recursive formula were proposed based on the explanation and demonstration of Li and Lee. s method and corresponding with the two2 dimensional Otsu. s linear2type threshold segmentation method.Compared with thetwo2 dimensional Ot2 su. s linear2typethreshold segmentation method,thenewmethod can bebetter adapted to the cases that the variancebetween the ob2 ject and background is large. It is shown that thenew method is an available threshold selection method. Ke y word s : threshold segmentation; Otsu. s method;cross2 entropy