
浏览全部资源
扫码关注微信
南京工业大学 机械与动力工程学院, 江苏 南京 211800
[ "陈 昕(1998—),男,江苏兴化人,硕士研究生,2020年于南京工业大学浦江学院获得学士学位,主要从事机器视觉方面的研究。E-mail:1216298849@qq.com" ]
[ "方成刚(1974—),男,江苏大丰人,博士,副教授,2004年于南京工业大学获得博士学位,主要从事智能制造方面的研究。E-mail: 279119134@qq.com" ]
收稿日期:2022-03-31,
修回日期:2022-04-11,
纸质出版日期:2022-10-05
移动端阅览
陈昕, 方成刚. 多特征矩融合的液晶屏字符缺陷检测算法[J]. 液晶与显示, 2022,37(10):1326-1333.
Xin CHEN, Cheng-gang FANG. LCD character defect detection algorithm based on multi-feature moment fusion[J]. Chinese journal of liquid crystals and displays, 2022, 37(10): 1326-1333.
陈昕, 方成刚. 多特征矩融合的液晶屏字符缺陷检测算法[J]. 液晶与显示, 2022,37(10):1326-1333. DOI: 10.37188/CJLCD.2022-0103.
Xin CHEN, Cheng-gang FANG. LCD character defect detection algorithm based on multi-feature moment fusion[J]. Chinese journal of liquid crystals and displays, 2022, 37(10): 1326-1333. DOI: 10.37188/CJLCD.2022-0103.
为了实现液晶屏字符高效、精准的自动化检测,针对液晶屏字符显示的断线、亮度缺陷,提出一种基于多特征矩融合的液晶屏字符缺陷检测算法。首先提取原始液晶屏图像中ROI区域,使用Hu不变矩来描述字符的结构特征,采用Zernike矩来弥补Hu矩所不能描述的高阶矩信息;然后使用颜色矩来描述字符的颜色特征,采用灰度矩弥补颜色矩所不能描述的灰度信息,并运用2DPCA技术融合上述矩阵,通过欧氏距离来衡量标准图像融合特征矩阵与待检测图像融合特征矩阵之间的相似度,通过设定相似度阈值来达到缺陷检测的目的。实验的客观和主观评价结果表明:主观上,该算法具有一定的稳定性、实用性;客观上,该算法相比于同类算法具有较低的误判率1%、漏判率0%以及较高的效率0.6 s,基本满足实际检测需求。
In order to realize the automatic detection of LCD characters efficiently and accurately, a character defect detection algorithm based on multi-feature moment fusion was proposed for the disconnection and brightness defects of LCD character display. Firstly, the ROI region of the original LCD image was extracted, Hu invariant moments were used to describe the structural characteristics of characters, and Zernike moments were used to compensate for the information of higher moments that Hu moments could not describe. The color moment was used to describe color features of the characters,and the gray moment was used to make up the gray information that the color moment can not describe. The matrices were fused using 2DPCA technology. The similarity between the standard image fusion characteristic matrix and the image fusion characteristic matrix to be detected were measured by Euclidean distance. By setting the similarity threshold, the goal of defect detection was achieved. Experiment results show that the algorithm is stable and practical subjectively. Objectively, compared with the similar algorithms, the algorithm has a lower false judgment rate of 1%, a lower misjudgment rate of 0% and a higher efficiency of 0.6 s, basically meeting the actual detection needs.
刘伟 , 韩震宇 . 基于机器视觉的SMD字符缺陷检测 [J]. 科技与创新 , 2018 ( 9 ): 114 - 115 . doi: 10.15913/j.cnki.kjycx.2018.09.114 http://dx.doi.org/10.15913/j.cnki.kjycx.2018.09.114
LIU W , HAN Z Y . SMD character defect detection based on machine vision [J]. Science and Technology & Innovation , 2018 ( 9 ): 114 - 115 . (in Chinese) . doi: 10.15913/j.cnki.kjycx.2018.09.114 http://dx.doi.org/10.15913/j.cnki.kjycx.2018.09.114
李定珍 , 王萍 . VFD显示图像缺陷检测技术研究 [J]. 液晶与显示 , 2013 , 28 ( 1 ): 138 - 145 . doi: 10.3788/yjyxs20132801.0138 http://dx.doi.org/10.3788/yjyxs20132801.0138
LI D Z , WANG P . Defects detection technology of VFD display image [J]. Chinese Journal of Liquid Crystals and Displays , 2013 , 28 ( 1 ): 138 - 145 . (in Chinese) . doi: 10.3788/yjyxs20132801.0138 http://dx.doi.org/10.3788/yjyxs20132801.0138
徐珩 , 刘学平 . 基于多对象匹配与融合字符特征的印刷质量检验方法 [J]. 包装工程 , 2019 , 40 ( 11 ): 188 - 193 . doi: 10.1109/cac51589.2020.9326829 http://dx.doi.org/10.1109/cac51589.2020.9326829
XU H , LIU X P . Printing quality inspection method based on multi-object matching and fusion character features [J]. Packaging Engineering , 2019 , 40 ( 11 ): 188 - 193 . (in Chinese) . doi: 10.1109/cac51589.2020.9326829 http://dx.doi.org/10.1109/cac51589.2020.9326829
徐炜东 , 郭斌 , 张永超 , 等 . 液晶屏字符显示缺陷检测算法研究 [J]. 中国计量学院学报 , 2014 , 25 ( 2 ): 139 - 143 . doi: 10.3969/j.issn.1004-1540.2014.02.005 http://dx.doi.org/10.3969/j.issn.1004-1540.2014.02.005
XU W D , GUO B , ZHANG Y C , et al . Research on defect detection algorithm of LCD character display [J]. Journal of China Jiliang University , 2014 , 25 ( 2 ): 139 - 143 . (in Chinese) . doi: 10.3969/j.issn.1004-1540.2014.02.005 http://dx.doi.org/10.3969/j.issn.1004-1540.2014.02.005
郑菁菁 . 指针式仪表表盘的缺陷检测 [J]. 科技经济市场 , 2010 ( 4 ): 34 - 36 . doi: 10.3969/j.issn.1009-3788.2010.04.019 http://dx.doi.org/10.3969/j.issn.1009-3788.2010.04.019
ZHENG J J . Defect detection of dial of pointer instrument [J]. Science & Technology Economy Market , 2010 ( 4 ): 34 - 36 . (in Chinese) . doi: 10.3969/j.issn.1009-3788.2010.04.019 http://dx.doi.org/10.3969/j.issn.1009-3788.2010.04.019
郑魁敬 , 刘学超 , 王萌萌 . 基于机器视觉的手机电池表面缺陷检测 [J]. 制造技术与机床 , 2020 ( 4 ): 105 - 112 . doi: 10.4028/www.scientific.net/amr.403-408.1356 http://dx.doi.org/10.4028/www.scientific.net/amr.403-408.1356
ZHENG K J , LIU X C , WANG M M . Surface defect detection of mobile phone battery based on machine vision [J]. Manufacturing Technology & Machine Tool , 2020 ( 4 ): 105 - 112 . (in Chinese) . doi: 10.4028/www.scientific.net/amr.403-408.1356 http://dx.doi.org/10.4028/www.scientific.net/amr.403-408.1356
李海山 , 唐海艳 , 梁栋 , 等 . 基于卷积神经网络的印刷品颜色缺陷检测 [J]. 包装工程 , 2021 , 42 ( 23 ): 170 - 177 .
LI H S , TANG H Y , LIANG D , et al . Detection of printing color defect based on convolutional neural network [J]. Packaging Engineering , 2021 , 42 ( 23 ): 170 - 177 . (in Chinese)
范蟠果 , 薛小斌 , 王恩俊 . 基于Hu矩、Zernike矩和小波矩的局部放电识别分析 [J]. 电气应用 , 2016 , 35 ( 19 ): 58 - 61,70 .
FAN P G , XUE X B , WANG E J . Identification of PARTIAL discharge based on Hu moment, Zernike moment and wavelet moment [J]. Electrotechnical Application , 2016 , 35 ( 19 ): 58 - 61, 70 . (in Chinese)
张丽红 , 张慧 , 王晓凯 . 边缘检测和区域生长相结合的图像ROI提取方法 [J]. 计算机技术与发展 , 2011 , 21 ( 4 ): 234 - 237 . doi: 10.3969/j.issn.1673-629X.2011.04.061 http://dx.doi.org/10.3969/j.issn.1673-629X.2011.04.061
ZHANG L H , ZHANG H , WANG X K . An ROI search method for color images based on edge detection and region growing [J]. Computer Technology and Development , 2011 , 21 ( 4 ): 234 - 237 . (in Chinese) . doi: 10.3969/j.issn.1673-629X.2011.04.061 http://dx.doi.org/10.3969/j.issn.1673-629X.2011.04.061
赵婷婷 , 唐晶磊 , 黄志远 , 等 . 基于孤立像素点去除的车牌ROI区域快速定位方法研究 [J]. 现代计算机 , 2014 ( 9 ): 46 - 50 .
ZHAO T T , TANG J L , HUANG Z Y , et al . Research on the method of license ROI plate fast location based on isolated pixel removal [J] Modern Computer , 2014 ( 9 ): 46 - 50 . (in Chinese)
文生平 , 冯泽锋 , 洪培烽 , 等 . 基于改进Hu矩算法的AGV字符识别研究 [J]. 计算机测量与控制 , 2020 , 28 ( 5 ): 229 - 232,251 .
WEN S P , FENG Z F , HONG P F , et al . Research on AGV character recognition based on improved Hu moment algorithm [J]. Computer Measurement & Control , 2020 , 28 ( 5 ): 229 - 232, 251 . (in Chinese)
兰蓉 , 贾世英 . 基于纹理与颜色特征融合的刑侦图像检索算法 [J]. 西安邮电大学学报 , 2016 , 21 ( 2 ): 57 - 62 .
LAN R , JIA S Y . A retrieval algorithm of forensic image fusion based on fusioning texture and color feature [J]. Journal of Xi’an University of Posts and Telecommunications , 2016 , 21 ( 2 ): 57 - 62 . (in Chinese)
王峰 , 孟立凡 , 李艳 . 基于伪Zernike矩的车牌字符识别 [J]. 电子测试 , 2012 ( 8 ): 19 - 23 . doi: 10.3969/j.issn.1000-8519.2012.08.005 http://dx.doi.org/10.3969/j.issn.1000-8519.2012.08.005
WANG F , MENG L F , LI Y . License plate character recognition based on pseudo-Zernike moment [J]. Electronic Testing , 2012 ( 8 ): 19 - 23 . (in Chinese) . doi: 10.3969/j.issn.1000-8519.2012.08.005 http://dx.doi.org/10.3969/j.issn.1000-8519.2012.08.005
施怡澄 , 刘洞波 , 陈玉婷 . 基于Surf和改进颜色矩的服装图像检索算法研究 [J]. 湖南工程学院学报(自然科学版) , 2021 , 31 ( 3 ): 53 - 58 .
SHI Y C , LIU D B , CHEN Y T . Research on garment image retrieval algorithm based on surf and improved color moment [J]. Journal of Hunan Institute of Engineering (Natural Science Edition) , 2021 , 31 ( 3 ): 53 - 58 . (in Chinese)
柯洁 . 基于数学形态学和灰度矩的高温亚像素边缘检测 [J]. 工具技术 , 2019 , 53 ( 3 ): 132 - 136 . doi: 10.3969/j.issn.1000-7008.2019.03.033 http://dx.doi.org/10.3969/j.issn.1000-7008.2019.03.033
KE J . Subpixel edge detection method under high temperature based on mathematical morphology and gray moment [J]. Tool Engineering , 2019 , 53 ( 3 ): 132 - 136 . (in Chinese) . doi: 10.3969/j.issn.1000-7008.2019.03.033 http://dx.doi.org/10.3969/j.issn.1000-7008.2019.03.033
胡娜 , 马慧 , 湛涛 . 融合LBP纹理特征与B2DPCA技术的手指静脉识别方法 [J]. 智能系统学报 , 2019 , 14 ( 3 ): 533 - 540 . doi: 10.11992/tis.201801014 http://dx.doi.org/10.11992/tis.201801014
HU N , MA H , ZHAN T . Finger vein recognition method combining LBP texture feature and B2DPCA technology [J]. CAAI Transactions on Intelligent Systems , 2019 , 14 ( 3 ): 533 - 540 . (in Chinese) . doi: 10.11992/tis.201801014 http://dx.doi.org/10.11992/tis.201801014
李漫丽 , 赵鹏 . 基于图像融合的木板表面缺陷检测研究 [J]. 液晶与显示 , 2016 , 31 ( 9 ): 882 - 888 . doi: 10.3788/yjyxs20163109.0882 http://dx.doi.org/10.3788/yjyxs20163109.0882
LI M L , ZHAO P . Wood surface defect detection based on image fusion [J]. Chinese Journal of Liquid Crystals and Displays , 2016 , 31 ( 9 ): 882 - 888 . (in Chinese) . doi: 10.3788/yjyxs20163109.0882 http://dx.doi.org/10.3788/yjyxs20163109.0882
王静 , 姚远 . 基于特征距离的CNN人脸识别方法的实现 [J]. 新疆师范大学学报(自然科学版) , 2021 , 40 ( 2 ): 67 - 70 .
WANG J , YAO Y . Realization of face recognition method based on CNN and feature distance [J]. Journal of Xinjiang Normal University (Natural Sciences Edition) , 2021 , 40 ( 2 ): 67 - 70 . (in Chinese)
姜涛 , 张桂林 , 高俊鹏 . 面向机器视觉检测的缸体横孔照明 [J]. 中国光学 , 2020 , 13 ( 6 ): 1285 - 1292 . doi: 10.37188/co.2020-0054 http://dx.doi.org/10.37188/co.2020-0054
JIANG T , ZHANG G L , GAO J P . Illumination of a cylinder block transverse hole for machine vision inspection [J]. Chinese Optics , 2020 , 13 ( 6 ): 1285 - 1292 . (in Chinese) . doi: 10.37188/co.2020-0054 http://dx.doi.org/10.37188/co.2020-0054
赵鹏鹏 , 李庶中 . 融合视觉显著性和局部熵的红外弱小目标检测 [J]. 中国光学 , 2022 , 15 ( 2 ): 267 - 275 . doi: 10.37188/co.2021-0170 http://dx.doi.org/10.37188/co.2021-0170
ZHAO P P , LI S Z . Infrared dim small target detection based on fusion of visual saliency and local entropy [J]. Chinese Optics , 2022 , 15 ( 2 ): 267 - 275 . (in Chinese) . doi: 10.37188/co.2021-0170 http://dx.doi.org/10.37188/co.2021-0170
秦钟伟 , 陈捷 , 洪荣晶 , 等 . 摩擦片表面缺陷的视觉显著性检测算法 [J]. 浙江大学学报(工学版) , 2019 , 53 ( 10 ): 1883 - 1891 .
QIN Z W , CHEN J , HONG R J , et al . Visual salience detection algorithm for surface defects of friction sheets [J]. Journal of Zhejiang University (Engineering Science) , 2019 , 53 ( 10 ): 1883 - 1891 . (in Chinese)
0
浏览量
204
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621