一种新的灰度直方图分割阈值的自动检测方法  

A Novel Histogram Threshold Auto-detection Method

作　　者：王文宁[1] 王汇源[1] 牟文英[1] 

机构地区：[1]山东大学信息科学与工程学院,济南250100

出　　处：《计算机工程与应用》2005年第26期89-90,173,共3页Computer Engineering and Applications

摘　　要：本文提出了一种新的灰度直方图的阈值点自动提取方法。利用灰度直方图的直观特征,把直方图的峰点作为分水岭,每两个相邻的峰值点和两者之间的谷点组成一个水域。从最低的谷点向上升高水位,直到各个水域水满为止。找到水量最大的几个水域,其谷底就是作为分割阈值的谷点。In this paper,we propose a novel auto-detection algorithm of thresholds and peaks in image histogram.In accordance with the intuitionistic features of the histogram,the peaks of the histogram are considered as watersheds, each valley including two neighboring peaks and a bottom point.We raise the water level up from the bottom point until every valley is full of water.At last,we obtain several valleys with the largest amount of water,and the bottom of these valleys becomes a segmentation threshold.

关 键 词：灰度直方图 分水线 图像分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]