[1]刘建宝,李平.织物纬斜检测图像光照不均匀的校正方法[J].华侨大学学报(自然科学版),2020,41(3):388-393.[doi:10.11830/ISSN.1000-5013.201906022]
　LIU Jianbao,LI Ping.Method for Correcting Uneven Illumination of Fabric Weft Detection Image[J].Journal of Huaqiao University(Natural Science),2020,41(3):388-393.[doi:10.11830/ISSN.1000-5013.201906022]
点击复制

织物纬斜检测图像光照不均匀的校正方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第41卷
期数:
2020年第3期
页码:
388-393
栏目:
出版日期:
2020-05-20

文章信息/Info

Title:
Method for Correcting Uneven Illumination of Fabric Weft Detection Image
文章编号:
1000-5013(2020)03-0388-06
作者:
刘建宝;  李平
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
LIU Jianbao;  LI Ping
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
图像二值化;  光照不均匀;  织物纹理;  纬斜检测
Keywords:
image binarization;  uneven illumination;  fabric texture;  fabric skew detection
分类号:
TP391.4;TS195.3
DOI:
10.11830/ISSN.1000-5013.201906022
文献标志码:
A
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.
Abstract:
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.

参考文献/References:

[1] 刘洲峰,王龙,赵亚茹,等.摄像整纬控制系统的设计[J].自动化应用,2016(7):69-71.DOI:10.3969/j.issn.1674-778X.2016.07.038.
[2] 赵奇志,朱亦军.论整纬器在染整行业的作用和前景[J].轻纺工业与技术,2011,40(4):112-113.DOI:10.3969/j.issn.2095-0101.2011.04.039.
[3] 吉庆高.精细织物纬斜检测方法研究及检测装置设计[D].南京:南京理工大学,2015.
[4] 金守峰.面向机器视觉的织物纬斜检测方法[J].天津工业大学学报,2011,30(2):40-42.DOI:10.3969/j.issn.1671-024X.2011.02.010.
[5] 董燕,刘洲峰,吕云鹏.一种纬斜检测的改进投影映射算法及其硬件实现[J].计算机测量与控制,2013,21(5):1294-1296.DOI:10.16526/j.cnki.11-4762/tp.2013.05.052.
[6] 李敏,罗红艳,郑小林,等.一种改进的最大类间方差图像分割法[J].南京理工大学学报,2012,36(2):332-337.DOI:10.14177/j.cnki.32-1397n.2012.02.021.
[7] 史进伟,郭朝勇,刘红宁,等.基于Hough变换和双峰法的枪弹外观缺陷提取[J].火力与指挥控制,2013,38(5): 129-132.DOI:10.3969/j.issn.1002-0640.2013.05.035.
[8] 成亚维,李茜,汤伟.改进的阈值选取方法在纸病图像分割中的应用[J].造纸科学与技术,2014,33(1):65-68.
[9] 何晶,范九伦,李利.基于多层次分块的指纹图像二值化方法[J].计算机工程与设计,2008,29(14):740-742.
[10] WHITE J M,ROHRER G D.Image thresholding for optical character recognition and other applications requiring character image extraction[J].IBM Journal of Research and Development,1983,27(4):400-411.DOI:10.1147/rd.274.0400.
[11] BERNSEN J.Dynamic thresholding of grey-level images[C]//Proceedings of the 8th International Conference on Pattern Recognition.Paris:IEEE Computer Society Press,1986:1251-1255.
[12] NIBLACK W.An introduction to digital image processing[M].Denmark:Strandberg Publishing Company Birkeroed,1986:115-116.
[13] SAUVOLA J,PIETIKÄINEN M.Adaptive document image binarization[J].Pattern Recognition,2000,33(2):225-236.DOI:10.1016/S0031-3203(99)00055-2.
[14] YAO Zhijun,LAI Zhongyuan,WANG Chun.Brightness preserving and non-parametric modified bi-histogram equalization for image enhancement[C] //12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery.Changsha:IEEE Press,2016:16408916.DOI:10.1109/FSKD.2016.7603464.
[15] PUGAZHENTHI A,KUMAR L S.Image contrast enhancement by automatic multi-histogram equalization for satellite images[C]//Fourth International Conference on Signal Processing, Communication and Networking.Chennai:IEEE Press,2017:1-4.DOI:10.1109/ICSCN.2017.8085722.
[16] 陈文飞,廖斌,许雪峰,等.基于Piecewise直方图均衡化的图像增强方法[J].通信学报,2011,32(9):153-160.DOI:10.3969/j.issn.1000-436X.2011.09.022.
[17] LIU Zhanwen,GAO Tao,KONG Fanjie,et al.Restoration algorithm for noisy complex illumination[J].IET Computer Vision,2019,13(2):224-232.DOI:10.1049/iet-cvi.2018.5163.
[18] 刘晓波.基于Retinex理论人脸识别光照预处理方法的对比分析[J].科技视界,2015(3):124-125.DOI:10.19694/j.cnki.issn2095-2457.2015.03.093.
[19] ZHANG Libo,YANG Lin,LUO Tiejian,et al.A novel illumination compensation method with enhanced retinex[C]//3rd International Conference on Information Science and Control Engineering.Beijing:IEEE Press,2016:16430479.DOI:10.1109/ICISCE.2016.28.
[20] YASNOFF W A,MUI J K,BACUS J W.Error measures for scene segmentation[J].Pattern Recogn,1977,9(4):217-231.DOI:10.1016/0031-3203(77)90006-1.

备注/Memo

备注/Memo:
收稿日期: 2019-06-20
通信作者: 李平(1981-),女,副教授,博士,主要从事非线性系统与智能控制、复杂控制系统的研究.E-mail:pingping_1213@126.com.
基金项目: 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)
更新日期/Last Update: 2020-05-20