基于相似性分析和阈值自校正的烟箱缺条智能检测方法
|
摘要
为解决条烟装箱过程中出现的烟箱缺条等质量问题,基于烟箱内部前位、后位图片,建立了一种基于相似性分析和阈值自校正的烟箱缺条智能检测方法。首先,将前位和后位图片进行灰度变换和图像分割,基于处理后图片的横向和纵向分块,采用皮尔逊相似性分析计算图片的16个特征相似度指标,利用核密度估计确定所有建模图片16个指标的阈值;其次,采用横向和纵向分块的相似性分析方法,计算前位和后位图片的16个特征相似度指标,通过与阈值的比较识别前位和后位图片是否发生缺条;最后,将新的未缺条图片特征相似度指标添加到建模图片的特征相似度矩阵中,利用核密度估计进行阈值自校正。以杭州卷烟厂条烟装箱过程的实际运行数据进行验证,结果表明:该方法实现了烟箱内部图片特征信息的有效表征和量化,能够准确判断烟箱缺条缺陷,对测试数据中所有15种缺条缺陷的检测准确率为100%,标注后的图片为缺条问题追溯提供了依据。该方法可为提高烟箱缺条检测方法的适应性和可靠性提供技术支持。
In order to detect cigarette carton missing in cigarette case, an intelligent detection method based on similarity analysis and threshold self-correction was proposed on the basis of the front position and rear position images inside cigarette case. Firstly, the front position and rear position images were processed by gradation transformation and image segmentation; based on the horizontal and vertical segmentation of the processed images, 16 feature similarity indicators of the processed images were calculated by Pearson similarity analysis; and the thresholds of the 16 indicators for all modelling images were determined by kernel density estimation. Secondly, the 16 feature similarity indicators of the front position and rear position images were calculated by horizontal and vertical block similarity analysis method, and carton missing in the current front and rear images was judged via comparing with the thresholds. Finally, the feature similarity indicators of the new without carton missing images were added to the feature similarity matrix of the modelling images, and threshold self-correction was carried out with kernel density estimation. Off-line validation was carried out on the basis of actual running data of cigarette case filling process in Hangzhou Cigarette Factory, the results showed that the proposed method realized the effective characterization and quantification of feature information of the images inside cigarette cases and could accurately detect the carton missing in cigarette cases. The detection accuracy reached 100% for all 15 types of carton missing in the test data, and the labeled images provided the basis for carton missing tracing. The proposed method provides a technical support for improving the adaptability and reliability of detection method for carton missing in cigarette case.
In order to detect cigarette carton missing in cigarette case, an intelligent detection method based on similarity analysis and threshold self-correction was proposed on the basis of the front position and rear position images inside cigarette case. Firstly, the front position and rear position images were processed by gradation transformation and image segmentation; based on the horizontal and vertical segmentation of the processed images, 16 feature similarity indicators of the processed images were calculated by Pearson similarity analysis; and the thresholds of the 16 indicators for all modelling images were determined by kernel density estimation. Secondly, the 16 feature similarity indicators of the front position and rear position images were calculated by horizontal and vertical block similarity analysis method, and carton missing in the current front and rear images was judged via comparing with the thresholds. Finally, the feature similarity indicators of the new without carton missing images were added to the feature similarity matrix of the modelling images, and threshold self-correction was carried out with kernel density estimation. Off-line validation was carried out on the basis of actual running data of cigarette case filling process in Hangzhou Cigarette Factory, the results showed that the proposed method realized the effective characterization and quantification of feature information of the images inside cigarette cases and could accurately detect the carton missing in cigarette cases. The detection accuracy reached 100% for all 15 types of carton missing in the test data, and the labeled images provided the basis for carton missing tracing. The proposed method provides a technical support for improving the adaptability and reliability of detection method for carton missing in cigarette case.
引文
[1]侯勇刚,张寿明,李燕.称重式烟箱缺条检测与自动剔除控制系统[J].自动化仪表,2008,29(2):49-50.HOU Yonggang,ZHANG Shouming,LI Yan.Weighing control system for carton-missing detection and auto-removing in tobacco packing line[J].Process Automation Instrumentation,2008,29(2):49-50.
[2]张华军.基于SIWAREX FTA称重技术的烟箱缺条检测及剔除系统设计[J].包装与食品机械,2012,30(5):29-31.ZHANG Huajun.Design of carton box absent packets detecting and sorting out system based on the weighing technology of SIWAREX FTA[J].Packaging and Food Machinery,2012,30(5):29-31.
[3]王前进,程相龙,刘长庆.称重式烟箱缺条检测装置设计应用[J].自动化技术与应用,2016,35(6):116-118.WANG Qianjin,CHENG Xianglong,LIU Changqing.Design and application of weighting type cartonmissing detection device[J].Techniques of Automation&Applications,2016,35(6):116-118.
[4]高雷,刘向东,崔霄,等.基于红外成像的条烟自动检测系统[J].沈阳航空航天大学学报,2011,28(2):55-58.GAO Lei,LIU Xiangdong,CUI Xiao,et al.On the infrared-image-based autodetect system for case packing of cigarette carton[J].Journal of Shenyang Aerospace University,2011,28(2):55-58.
[5]倪松鹏,王晓年,朱劲.用于烟箱缺条检测的禁忌匹配算法[J].计算机应用,2012,32(1):269-271,283.NI Songpeng,WANG Xiaonian,ZHU Jin.Tobacco matching method for carton missing detection[J].Journal of Computer Applications,2012,32(1):269-271,283.
[6]杜劲松,高雪锋,毕欣,等.基于智能相机的箱缺条在线检测系统研究[J].机械设计与制造,2012(11):109-111.DU Jingsong,GAO Xuefeng,BI Xin,et al.Cigarette packet on-line inspection system research based on smart camera[J].Machinery Design&Manufacture,2012(11):109-111.
[7]蔡培良,何邦贵,易凡竣,等.YP13型装封箱机缺条视觉检测系统设计[J].包装工程,2017,38(11):92-96.CAI Peiliang,HE Banggui,YI Fanjun,et al.Design of carton-missing vision inspection system on YP13 case filling and sealing machine[J].Packaging Engineering,2017,38(11):92-96.
[8]毕欣,李晓锋,杜劲松,等.封箱机香烟缺条视觉在线检测系统[J].控制工程,2011,18(增刊1):138-141.BI Xin,LI Xiaofeng,DU Jingsong,et al.Vision inspection system of article lack of sealing machine[J].Control Engineering of China,2011,18(S1):138-141.
[9]吴忠云,邓春宁.机器视觉检测技术在烟箱缺条检测方面的运用[J].机械制造与自动化,2014(6):188-190.WU Zhongyun,DENG Chunning.Application of machine vision technology in box lack detection[J].Machine Building&Automation,2014(6):188-190.
[10]邓春宁.一种箱装缺条检测装置故障自诊断系统的设计[J].机械设计与制造工程,2017,46(9):66-68.DENG Chunning.The design of a fault self-diagnosis system for the box missing strip detection device[J].Machine Design and Manufacturing Engineering,2017,46(9):66-68.
[11]Tong C D,Yan X F.A novel decentralized process monitoring scheme using a modified multiblock PCAalgorithm[J].IEEE Transactions on Automation Science and Engineering,2017,14(2):1129-1138.
[12]Jiang Q C,Huang B.Distributed monitoring for large-scale processes on multivariate statistical analysis and Bayesian method[J].Journal of Process Control,2016,46:75-83.
[13]王伟,张利宏,黎明星,等.卷烟制叶丝段批次过程的多阶段分布式监测与异常诊断[J].烟草科技,2018,51(2):69-76.WANG Wei,ZHANG Lihong,LI Mingxing,et al.Multi-stage distributed working status monitoring and trouble diagnosis for batch process in cut strip processing section[J].Tobacco Science&Technology,2018,51(2):69-76.
[14]Li W Q,Zhao C H,Gao F R.Linearity evaluation and variable subset partition based hierarchical process modeling and monitoring[J].IEEE Transactions on Industrial Electronics,2018,65(3):2683-2692.
[15]杨帆,冯翔,阮羚,等.基于皮尔逊相关系数法的水树枝与超低频介损的相关性研究[J].高压电器,2014,50(6):21-25.YANG Fan,FENG Xiang,RUAN Ling,et al.Correlation study of water tree and VLF tanδbased on Pearson correlation coefficient[J].High Voltage Apparatus,2014,50(6):21-25.
[16]颜伟,任洲洋,赵霞,等.光伏电源输出功率的非参数核密度估计模型[J].电力系统自动化,2013,37(10):35-40.YAN Wei,REN Zhouyang,ZHAO Xia,et al.Probabilistic photovoltaic power modeling based on nonparametric kernel density estimation[J].Automation of Electric Power Systems,2013,37(10):35-40.
[2]张华军.基于SIWAREX FTA称重技术的烟箱缺条检测及剔除系统设计[J].包装与食品机械,2012,30(5):29-31.ZHANG Huajun.Design of carton box absent packets detecting and sorting out system based on the weighing technology of SIWAREX FTA[J].Packaging and Food Machinery,2012,30(5):29-31.
[3]王前进,程相龙,刘长庆.称重式烟箱缺条检测装置设计应用[J].自动化技术与应用,2016,35(6):116-118.WANG Qianjin,CHENG Xianglong,LIU Changqing.Design and application of weighting type cartonmissing detection device[J].Techniques of Automation&Applications,2016,35(6):116-118.
[4]高雷,刘向东,崔霄,等.基于红外成像的条烟自动检测系统[J].沈阳航空航天大学学报,2011,28(2):55-58.GAO Lei,LIU Xiangdong,CUI Xiao,et al.On the infrared-image-based autodetect system for case packing of cigarette carton[J].Journal of Shenyang Aerospace University,2011,28(2):55-58.
[5]倪松鹏,王晓年,朱劲.用于烟箱缺条检测的禁忌匹配算法[J].计算机应用,2012,32(1):269-271,283.NI Songpeng,WANG Xiaonian,ZHU Jin.Tobacco matching method for carton missing detection[J].Journal of Computer Applications,2012,32(1):269-271,283.
[6]杜劲松,高雪锋,毕欣,等.基于智能相机的箱缺条在线检测系统研究[J].机械设计与制造,2012(11):109-111.DU Jingsong,GAO Xuefeng,BI Xin,et al.Cigarette packet on-line inspection system research based on smart camera[J].Machinery Design&Manufacture,2012(11):109-111.
[7]蔡培良,何邦贵,易凡竣,等.YP13型装封箱机缺条视觉检测系统设计[J].包装工程,2017,38(11):92-96.CAI Peiliang,HE Banggui,YI Fanjun,et al.Design of carton-missing vision inspection system on YP13 case filling and sealing machine[J].Packaging Engineering,2017,38(11):92-96.
[8]毕欣,李晓锋,杜劲松,等.封箱机香烟缺条视觉在线检测系统[J].控制工程,2011,18(增刊1):138-141.BI Xin,LI Xiaofeng,DU Jingsong,et al.Vision inspection system of article lack of sealing machine[J].Control Engineering of China,2011,18(S1):138-141.
[9]吴忠云,邓春宁.机器视觉检测技术在烟箱缺条检测方面的运用[J].机械制造与自动化,2014(6):188-190.WU Zhongyun,DENG Chunning.Application of machine vision technology in box lack detection[J].Machine Building&Automation,2014(6):188-190.
[10]邓春宁.一种箱装缺条检测装置故障自诊断系统的设计[J].机械设计与制造工程,2017,46(9):66-68.DENG Chunning.The design of a fault self-diagnosis system for the box missing strip detection device[J].Machine Design and Manufacturing Engineering,2017,46(9):66-68.
[11]Tong C D,Yan X F.A novel decentralized process monitoring scheme using a modified multiblock PCAalgorithm[J].IEEE Transactions on Automation Science and Engineering,2017,14(2):1129-1138.
[12]Jiang Q C,Huang B.Distributed monitoring for large-scale processes on multivariate statistical analysis and Bayesian method[J].Journal of Process Control,2016,46:75-83.
[13]王伟,张利宏,黎明星,等.卷烟制叶丝段批次过程的多阶段分布式监测与异常诊断[J].烟草科技,2018,51(2):69-76.WANG Wei,ZHANG Lihong,LI Mingxing,et al.Multi-stage distributed working status monitoring and trouble diagnosis for batch process in cut strip processing section[J].Tobacco Science&Technology,2018,51(2):69-76.
[14]Li W Q,Zhao C H,Gao F R.Linearity evaluation and variable subset partition based hierarchical process modeling and monitoring[J].IEEE Transactions on Industrial Electronics,2018,65(3):2683-2692.
[15]杨帆,冯翔,阮羚,等.基于皮尔逊相关系数法的水树枝与超低频介损的相关性研究[J].高压电器,2014,50(6):21-25.YANG Fan,FENG Xiang,RUAN Ling,et al.Correlation study of water tree and VLF tanδbased on Pearson correlation coefficient[J].High Voltage Apparatus,2014,50(6):21-25.
[16]颜伟,任洲洋,赵霞,等.光伏电源输出功率的非参数核密度估计模型[J].电力系统自动化,2013,37(10):35-40.YAN Wei,REN Zhouyang,ZHAO Xia,et al.Probabilistic photovoltaic power modeling based on nonparametric kernel density estimation[J].Automation of Electric Power Systems,2013,37(10):35-40.