摘要
在棉网图像中,棉结和杂质(简称结杂)大多都混杂在聚集的纤维网中难以检出和识别.针对这一问题,提出了一种将最大类间方差法(Otsu法)与线性回归相结合的棉网图像结杂分割方法.首先对棉网图像进行预处理,然后根据Otsu法获取棉网图像与背景分开的阈值,再根据线性回归找出该阈值与结杂灰度的关系,获得结杂分割的最佳阈值,从而实现结杂的识别.
Nep and trash in carded web image are usually difficult to be detected as they often superimpose on dense fiber layer.In order to solve this problem,one adaptive threshold segmentation method was proposed for obtaining the information about nep and trash from card web image,based on Otsu threshold method and linear regression model.Firstly,the image of card web was preprocessed.Secondly,the basic threshold was obtained by Otsu threshold method.Then,the linear regression model between this threshold and the optimal one was built,and more precise threshold was got,which was taken to segment the webs.Finally,nep and trash were segmented away from the web image much accurately.
出处
《东华大学学报（自然科学版）》
CAS
CSCD
北大核心
2010年第2期144-147,共4页
Journal of Donghua University(Natural Science)
关键词
棉网图像
结杂识别
自适应阈值
图像分割
最大类间方差法
carded web image
nep and trash recognition
adaptive threshold
image segmentation
Otsu threshold method
