基于信息能量的圆形直方图断点选择及阈值化和彩色图像分割方法  被引量:8

Circular Histogram Breakpoint Selection and Threshold and Color Image Segmentation Method Based on Information Energy

在线阅读下载全文

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)

机构地区:[1]西安邮电大学通信与信息工程学院,陕西西安710121

出  处:《激光与光电子学进展》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)。

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.

关 键 词:视觉 颜色与视觉光学 彩色图像分割 色调、饱和度、强度颜色模型 圆形直方图 断点 信息能量 

分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象