扬声器纸盆缺陷的机器视觉检测方法研究
|
摘要
针对目前扬声器纸盆外观缺陷检测主要依靠人工,其工作效率低、易出现误检的现象,提出一种基于机器视觉的检测技术。通过对检测系统的组成和软件算法的设计进行研究,从两个不同的角度对目标缺陷区域进行特征提取,并由此提出两种不同的缺陷识别方法。实验结果表明,机器视觉检测技术能够较好地适用于扬声器纸盆外观缺陷检测,同时,采用基于BP神经网络的识别方式,其正确识别率可达94.8%,符合工业检测要求,具有较高的推广应用价值。
Aiming atthe low working efficiency,error prone of the appearance defect detection of the loudspeaker cone resulting from relying on manual work,proposing a detection recognition technology based on machine vision. Through the research of the composition of the detection system and the design of the software algorithm,the feature extraction of the target defect area is made from two different angles,and two different defect identification methods are proposed. The experimental results show that the machine vision detection technology can be well applied to the defects identificationof loudspeaker cone,meanwhile,after adopting the identification method based on BP neural network,it's correct recognition rate can up to94.8%,which meets the requirements of industrial inspection and has high value of popularization and application.
Aiming atthe low working efficiency,error prone of the appearance defect detection of the loudspeaker cone resulting from relying on manual work,proposing a detection recognition technology based on machine vision. Through the research of the composition of the detection system and the design of the software algorithm,the feature extraction of the target defect area is made from two different angles,and two different defect identification methods are proposed. The experimental results show that the machine vision detection technology can be well applied to the defects identificationof loudspeaker cone,meanwhile,after adopting the identification method based on BP neural network,it's correct recognition rate can up to94.8%,which meets the requirements of industrial inspection and has high value of popularization and application.
引文
[1]姚红兵,马桂殿,沈宝国.基于机器视觉的树脂镜片疵病检测系统研究[J].激光与光电子学进展,2013(11):112-119.(Yao Hong-bing,Ma Gui-dian,Shen Bao-guo.Flaws detection systemfor resin lenses based on machine vision[J].Laser&Optoelectronics Progress,2013(11):112-119.)
[2]沈宝国,梁佩佩,宦小玉.基于机器视觉的工件角度检测方法研究[J].机械设计与制造,2016(11):230-232+236.(Shen Bao-guo,Liang Pei-pei,Huan Xiao-yu.Study on workpiece angle detection methods based on machine vision[J].Machinery Design&Manufacture,2016(11):230-232+236.)
[3]张平生,张桂梅.基于机器视觉的管孔类零件尺寸测量方法[J].机械设计与制造,2012(12):139-141.(Zhang Ping-sheng,Zhang Gui-mei.Automatic dimensions measuring method of pore part’s based on machine vision[J].Machinery Design&Manufacture,2012(12):139-141.)
[4]石炜,邵珠庆,李巍巍.机器视觉在圆锥滚子轴承内圈外表面缺陷检测中的应用[J].机械设计与制造,2015(5):137-139.(Shi Wei,Shao Zhu-qing,Li Wei-wei.Using machine vision to complete tapered roller bearing out of the loop detection of Surface defects[J].Machinery Design&Manufacture,2015(5):137-139.)
[5]C Baby Sherin,L.Mredhula.A Novel Methodfor Edge Detection inImages Based on Particle Swarm Optimization[J].Journal of Physics:Conference Series,2017,787(1).
[6]王诗宇,林浒,孙一兰.一种改进的Canny算子在机器人视觉系统中的应用[J].计算机系统应用,2017(3):144-149.(Wang Shi-Yu,Lin Hu,Sun Yi-lan.Improved canny operator in the application of robot vision system[J].Computer System Applications,2017(3):144-149.)
[7]刘亮,温宗周,薛冬旺.基于ROI区域子图像奇异值分解的夜视图像检测技术[J].西安工程大学学报,2017(1):71-76.(Liu Liang,Wen Zong-zhou,Xue Dong-wang.Night visiondetecti-on technology based on ROI regionalsub-image singularvaluedecomposition[J].Journal of Xi’an Polytechnic University,2017(1):71-76.)
[8]Taewan Kim,Eungtae Kim.A Vehicle License Plate RecognitionSystem Using Morphological ROI(Region of Interest)Map Gene-rated from Morphology Operation[J].Journal of Physics:Confere-nceSeries,2017,806(1).
[9]王帆,吕继东,申根荣.基于CLAHE和开闭运算的绿色苹果图像分割[J].计算机测量与控制,2017(2):141-145.(Wang Fan,Lv Ji-dong,Shen Gen-rong.Segmentation method of green apple image based on CLARE and open and close operation[J].Computer Measurement and Control,2017(2):141-145..)
[10]王杉,苑津莎,张卫华.基于BP神经网络的变压器故障诊断[J].黑龙江科技信息,2011(29):40-41.(Wang Shan,Yuan Jin-sha,Zhang Wei-hua.Transformer fault diagnosis based on BP neural network[J].Heilongjiang Science and Technology Information,2011(29):40-41.)
[2]沈宝国,梁佩佩,宦小玉.基于机器视觉的工件角度检测方法研究[J].机械设计与制造,2016(11):230-232+236.(Shen Bao-guo,Liang Pei-pei,Huan Xiao-yu.Study on workpiece angle detection methods based on machine vision[J].Machinery Design&Manufacture,2016(11):230-232+236.)
[3]张平生,张桂梅.基于机器视觉的管孔类零件尺寸测量方法[J].机械设计与制造,2012(12):139-141.(Zhang Ping-sheng,Zhang Gui-mei.Automatic dimensions measuring method of pore part’s based on machine vision[J].Machinery Design&Manufacture,2012(12):139-141.)
[4]石炜,邵珠庆,李巍巍.机器视觉在圆锥滚子轴承内圈外表面缺陷检测中的应用[J].机械设计与制造,2015(5):137-139.(Shi Wei,Shao Zhu-qing,Li Wei-wei.Using machine vision to complete tapered roller bearing out of the loop detection of Surface defects[J].Machinery Design&Manufacture,2015(5):137-139.)
[5]C Baby Sherin,L.Mredhula.A Novel Methodfor Edge Detection inImages Based on Particle Swarm Optimization[J].Journal of Physics:Conference Series,2017,787(1).
[6]王诗宇,林浒,孙一兰.一种改进的Canny算子在机器人视觉系统中的应用[J].计算机系统应用,2017(3):144-149.(Wang Shi-Yu,Lin Hu,Sun Yi-lan.Improved canny operator in the application of robot vision system[J].Computer System Applications,2017(3):144-149.)
[7]刘亮,温宗周,薛冬旺.基于ROI区域子图像奇异值分解的夜视图像检测技术[J].西安工程大学学报,2017(1):71-76.(Liu Liang,Wen Zong-zhou,Xue Dong-wang.Night visiondetecti-on technology based on ROI regionalsub-image singularvaluedecomposition[J].Journal of Xi’an Polytechnic University,2017(1):71-76.)
[8]Taewan Kim,Eungtae Kim.A Vehicle License Plate RecognitionSystem Using Morphological ROI(Region of Interest)Map Gene-rated from Morphology Operation[J].Journal of Physics:Confere-nceSeries,2017,806(1).
[9]王帆,吕继东,申根荣.基于CLAHE和开闭运算的绿色苹果图像分割[J].计算机测量与控制,2017(2):141-145.(Wang Fan,Lv Ji-dong,Shen Gen-rong.Segmentation method of green apple image based on CLARE and open and close operation[J].Computer Measurement and Control,2017(2):141-145..)
[10]王杉,苑津莎,张卫华.基于BP神经网络的变压器故障诊断[J].黑龙江科技信息,2011(29):40-41.(Wang Shan,Yuan Jin-sha,Zhang Wei-hua.Transformer fault diagnosis based on BP neural network[J].Heilongjiang Science and Technology Information,2011(29):40-41.)