基于分水线算法的二维直方图阈值化分割在箱包DR-CT检测系统中的应用  

Thresholding using two-dimensional histogram and watershed algorithm in the luggage inspection system

作　　者：陈景运[1] 丛鹏[1] 宋麒[1] 

机构地区：[1]清华大学核能与新能源研究院,北京100084

出　　处：《核电子学与探测技术》2006年第6期901-904,954,共5页Nuclear Electronics & Detection Technology

摘　　要：DR图像的区域分割是箱包DR-CT检测系统中的一个重要环节。采用二维直方图阈值化方法,在一维直方图灰度信息的基础上,引入局部空间的信息,利用分水线算法在二维直方图垂直投影上求取分割阈值,取得了较好图像分割效果。In this paper we present a new DR image segmentation method based on two-dimensional histogram and watershed algorithm. We use watershed algorithm to locate threshold on the vertical projection plane of two-dimensional histogram. This method is applied to the segmentation of DR images produced by luggage inspection system with DR-CT. The advantage of this method is also analyzed.

关 键 词：二维直方图 分水线算法 箱包DR-CT检测系统 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]