织物纬斜检测图像光照不均匀的校正方法  

Method for Correcting Uneven Illumination of Fabric Weft Detection Image

作　　者：刘建宝 李平[1] LIU Jianbao;LI Ping(College of Information Science and Engineering,Huaqiao University,Xiamen 361021,China)

机构地区：[1]华侨大学信息科学与工程学院,福建厦门361021

出　　处：《华侨大学学报（自然科学版）》2020年第3期388-393,共6页Journal of Huaqiao University(Natural Science)

基　　金：国家自然科学基金资助项目(61603144);福建省自然科学基金资助项目(2018J01095);福建省高校产学合作科技重大项目(2013H6016);华侨大学中青年教师科技创新资助计划项目(ZQN-PY509)。

摘　　要：为了解决在织物纬斜的检测过程中织物图像光照不均匀的问题,提出一种织物图像校正方法.首先,在每个像素点所处的列中,统计一个纬线宽度范围内像素值小于该点的个数,将统计结果作为该点的像素值;然后,按比例还原每个点的像素值,使每条纬线对应位置的像素值恢复到同一灰度水平;最后,把校正后的图像用Otsu法进行二值化,并与其他解决光照不均匀问题的经典方法进行对比.结果表明:文中方法能够很好地消除光照不均匀的影响,得到接近均匀光照下的二值图像.In order to solve the problem of uneven illumination in fabric image during weft skew detection,a method of fabric image correction is proposed.Firstly,in the column of each pixel point,count the number of pixels less than that point in the width range of a weft line,and take the statistical result as the pixel value of the point.Then restore the pixel value of each point in proportion,so that the pixel value of the corresponding position of each weft line can be restored to the same gray range.Finally,the Otsu method is used to binarize the corrected image,and the results are compared with those of other classical methods.The results show that the proposed method can eliminate the influence of uneven illumination and get binary images near uniform illumination.

关 键 词：图像二值化 光照不均匀 织物纹理 纬斜检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TS195.3[自动化与计算机技术—计算机科学与技术]