PET瓶封盖缺陷视觉检测算法研究
|
摘要
针对PET饮料瓶在封盖过程中的缺陷问题,提出了一种基于机器视觉技术的检测算法。首先,搭建了检测系统硬件平台,对检测难点进行了分析;然后,使用模板匹配算法检测瓶盖的有无,并根据匹配结果对持胚环区域和瓶盖上边缘区域进行了定位;通过Harris角点检测算法确定了持胚环所在的基准直线方程,采用Canny边缘检测算法与最小二乘算法拟合出了瓶盖上边缘直线方程;最后,通过计算瓶盖上边缘线与基准直线的夹角和距离完成了对歪盖、高盖的检测。研究结果表明:该检测算法检测效果良好,处理效率高,准确率可达99%以上,单个PET瓶检测效率为100 ms左右,且算法通用性强。
Aiming at the problems of defects in PET bottle capping production line,a detection algorithm based on machine vision technology was proposed. Firstly,the hardware platform of the system was built,so that the detection difficulties were analyzed. The template matching algorithm was introduced to detect the presence or absence of the cap,and the regions of the embryo ring and upper edge of the cap were positioned from the matching results. Then,the Harris corner detection algorithm was used to fit the straight line of the embryo ring. Furthermore,the Canny algorithm and the least squares algorithm were used to fit the straight line of upper edge of the cap. Finally,by calculating the angle and distance between the line of upper edge of the cap and the reference line,the defects of inclined cap and high cap were categorized. The results indicate that the detection algorithm has great detection result and efficient real-time processing efficiency,with the detection accuracy up to 99%,the detection efficiency is less than 100 ms.
Aiming at the problems of defects in PET bottle capping production line,a detection algorithm based on machine vision technology was proposed. Firstly,the hardware platform of the system was built,so that the detection difficulties were analyzed. The template matching algorithm was introduced to detect the presence or absence of the cap,and the regions of the embryo ring and upper edge of the cap were positioned from the matching results. Then,the Harris corner detection algorithm was used to fit the straight line of the embryo ring. Furthermore,the Canny algorithm and the least squares algorithm were used to fit the straight line of upper edge of the cap. Finally,by calculating the angle and distance between the line of upper edge of the cap and the reference line,the defects of inclined cap and high cap were categorized. The results indicate that the detection algorithm has great detection result and efficient real-time processing efficiency,with the detection accuracy up to 99%,the detection efficiency is less than 100 ms.
引文
[1]童季刚,廖菲,罗良传.一种机器视觉的瓶罐缺陷检测系统设计[J].机电工程技术,2016,45(8):28-31.
[2]王海栋,赵巨峰,高秀敏,等.药品生产线瓶盖缝隙的视觉检测技术研究[J].光学仪器,2016,38(4):283-287.
[3]张哲,朱铮涛,李渊,等.瓶盖缺陷在线自动检测技术研究[J].计算机技术与发展,2016,26(6):151-154.
[4]王贵锦,刘博,何贝,等.应用对称匹配的PET瓶瓶盖缺陷实时检测[J].应用科学学报,2014,32(6):617-624.
[5]彭玉,王耀南,周显恩,等.基于轮廓曲率的PET瓶防盗环断裂检测[J].电子测量与仪器学报,2017,31(3):422-429.
[6]孙涛.基于图像匹配的PET饮料瓶封装缺陷检测研究[D].广州:广东工业大学自动化学院,2008.
[7]郑云峰,王贵锦,何贝,等.基于直线拟合算法的PET瓶瓶盖检测方法[J].计算机应用研究,2011,28(11):4398-4400.
[8]王保军.基于机器视觉的药瓶封装缺陷检测系统研究[D].沈阳:东北大学机械工程与自动化学院,2014.
[9]CAMPOS M,FERREIRA M,MARTINS T.Inspection of bottle crates in the beer industry through computer vision[C].Conference of the IEEE Industrial Electronics Society,Glendale:IEEE,2010.
[10]MERY D,MEDINA O.Automated visual inspection of glass bottles using adapted median filtering[C].International Conference on Image Analysis&Recognition,Porto:Springer,2004.
[11]PENG Xiang-qian,LI Xiang-hua.An online glass medicine bottle defect inspection method based on machine vision[J].Glass Technology:European Journal of Glass Science&Technology Part A,2015,56(3):88-94.
[12]WANG Bao-jun,YANG Guang-yan.Medical bottle detecting system based on machine vision[J].Applied Mechanics and Materials,2013(373-375):521-524.
[13]郭倩茜.图像匹配的主要方法分析[J].科技创新与应用,2016(20):81.
[14]GONZALEZ R C.数字图像处理[M].3版.北京:电子工业出版社,2011.
[15]HOFHAUSER A,STEGER C,NAVAB N.Edge-based template matching and tracking for perspective distorted planar objects[J].Lecture Notes in Computer Science,2008,5358(1):35-44.
[16]HARRIS C.A combined corner and edge detector[J].Proc Alvey Vision Conf,1988(3):147-151.
[17]HOFHAUSER A,STEGER C,NAVAB N.Edge-based template matching with a harmonic deformation model[J].Communications in Computer and Information Science,2009,24(1):176-187.
[18]STEGER C.机器视觉算法与应用[M].北京:清华大学出版社,2008.
[2]王海栋,赵巨峰,高秀敏,等.药品生产线瓶盖缝隙的视觉检测技术研究[J].光学仪器,2016,38(4):283-287.
[3]张哲,朱铮涛,李渊,等.瓶盖缺陷在线自动检测技术研究[J].计算机技术与发展,2016,26(6):151-154.
[4]王贵锦,刘博,何贝,等.应用对称匹配的PET瓶瓶盖缺陷实时检测[J].应用科学学报,2014,32(6):617-624.
[5]彭玉,王耀南,周显恩,等.基于轮廓曲率的PET瓶防盗环断裂检测[J].电子测量与仪器学报,2017,31(3):422-429.
[6]孙涛.基于图像匹配的PET饮料瓶封装缺陷检测研究[D].广州:广东工业大学自动化学院,2008.
[7]郑云峰,王贵锦,何贝,等.基于直线拟合算法的PET瓶瓶盖检测方法[J].计算机应用研究,2011,28(11):4398-4400.
[8]王保军.基于机器视觉的药瓶封装缺陷检测系统研究[D].沈阳:东北大学机械工程与自动化学院,2014.
[9]CAMPOS M,FERREIRA M,MARTINS T.Inspection of bottle crates in the beer industry through computer vision[C].Conference of the IEEE Industrial Electronics Society,Glendale:IEEE,2010.
[10]MERY D,MEDINA O.Automated visual inspection of glass bottles using adapted median filtering[C].International Conference on Image Analysis&Recognition,Porto:Springer,2004.
[11]PENG Xiang-qian,LI Xiang-hua.An online glass medicine bottle defect inspection method based on machine vision[J].Glass Technology:European Journal of Glass Science&Technology Part A,2015,56(3):88-94.
[12]WANG Bao-jun,YANG Guang-yan.Medical bottle detecting system based on machine vision[J].Applied Mechanics and Materials,2013(373-375):521-524.
[13]郭倩茜.图像匹配的主要方法分析[J].科技创新与应用,2016(20):81.
[14]GONZALEZ R C.数字图像处理[M].3版.北京:电子工业出版社,2011.
[15]HOFHAUSER A,STEGER C,NAVAB N.Edge-based template matching and tracking for perspective distorted planar objects[J].Lecture Notes in Computer Science,2008,5358(1):35-44.
[16]HARRIS C.A combined corner and edge detector[J].Proc Alvey Vision Conf,1988(3):147-151.
[17]HOFHAUSER A,STEGER C,NAVAB N.Edge-based template matching with a harmonic deformation model[J].Communications in Computer and Information Science,2009,24(1):176-187.
[18]STEGER C.机器视觉算法与应用[M].北京:清华大学出版社,2008.