摘要
运用彩色图像色调、饱和度、强度(HSI)模型的H分量进行彩色图像阈值分割是一个新的彩色图像阈值化方式。考虑到H分量是一个圆形直方图,将圆形直方图断开为线性直方图,然后采用线性直方图阈值分割法进行阈值选取是一种有效途径。在信息论中,信息能量是Shannon熵的对偶,首先引入线性概率分布的累积分布信息能量概念,基于此来确定圆形直方图的断点;然后给出线性直方图上的信息能量阈值法,并基于此实现H分量圆形直方图的阈值选取。相比于基于对数运算的Shannon熵阈值选取准则,基于平方运算的信息能量阈值选取准则具有表述简单、运算速度快的优点。
A new method of color image threshold involves dividing the color image threshold using the H component of the color image hue-saturation-intensity(HSI) model.Considering that the H component is a circular histogram,it is an effective method to break the circular histogram into a linear histogram and subsequently use the linear histogram threshold segmentation method to select the threshold.In information theory,the information energy is the dual of Shannon entropy,and this study first introduces the concept of cumulative distribution information energy of the linear probability distribution,which is used to determine the breakpoint of the circular histogram.Thereafter,it provides the information energy threshold method on the linear histogram,which is used to determine the threshold of the H-component circular histogram.Compared with the Shannon entropy threshold selection criterion based on logarithmic operation,the information energy threshold selection criterion based on square operation has the advantages of simple expression and fast calculation speed.
作者
杨继鹏
范九伦
Yang Jipeng;Fan Jiulun(School of Communication and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,Shaanxi,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2023年第2期447-455,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金(62071378,62071379,62171380,61901365)
西安邮电大学西邮新星团队资助项目(xyt2016-01)。
