空瓶检测机器人瓶底缺陷检测方法研究
作者:
作者单位:

1.湖南大学 电气与信息工程学院 机器人视觉感知与控制技术国家工程实验室长沙410082;2.佛山市湘德智能科技有限公司佛山528000

中图分类号:

TP391.4;TN081

基金项目:

国家自然科学基金(61573134)资助项目


Research on detection method of bottle bottom defects based on empty bottle detection robot system
Author:
Affiliation:

1. National Engineering Laboratory for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha 410082, China; 2. Foshan Xiangde Intelligent Technology Co. Ltd., Foshan 52800, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对当前瓶底圆心定位方法精度不高、瓶底防滑纹区域缺陷易误检等问题,利用瓶底防滑纹的几何特征,提出一种改进的基于变权重随机圆拟合的瓶底定位算法,首先采用重心法对瓶底圆心进行快速预定位,再采用变权重随机圆拟合法实现瓶底精定位。然后检测瓶底图像疑似缺陷区域,并提取区域面积、轮廓长度、圆形度、灰度方差和灰度均值等特征,采用支持向量机算法进行分类决策,检测出缺陷。实验表明,瓶底定位误差小于6个像素,缺陷检测准确率为92.7%,基本满足实际生产精度的要求。

    Abstract:

    Aiming at the problem that the method of positioning the bottle bottom center is not accurate and the results for detecting the antiskid grain areas of bottom are unreliable, by taking advantage of the geometric features of antiskid grain areas on the bottom of the bottle, a localization algorithm based on variable weight random circle fitting the bottom is proposed in the paper. First, the bottom center is quickly prepositioned by gravity method, then the random variable weight circle fitting method is used to realize the precise positioning. Finally, the suspected defect region of the bottle bottom image is detected, and area, contour length, average gray, gray variance and circularity are extracted, then the support vector machine is used for classification and the defect is detected. The experiment results show that the positioning error of this method is less than 6 pixels, and the detect accuracy is 92.7%. It basically meets the actual production requirements.

    参考文献
    [1]苏国营.以LED点阵为特征的差动式视觉检测技术[J]. 电子测量技术,2016,39(2):6468. SU G Y. Differential vision detecting technology based on LED array[J]. Electronic Measurement Technology, 2016,39(2):6468.
    [2]周显恩,王耀南,朱青,等.基于机器视觉的瓶口缺陷检测方法研究[J]. 电子测量与仪器学报,2016,30(5):702 713. ZHOU X EN,WANG Y N,ZHU Q.Research on defect detection method for bottle mouth based on machine vision [J]. Electronic Measurement and Instrumentation, 2016, 30(5): 702  713.
    [3]吴成中,王耀南,冯明涛,等. 基于神经网络的医药微弱异物视觉检测机器人[J]. 电子测量与仪器学报, 2015, 29(12):17461756. WU CH ZH,WANG Y N,FENG M T,et al.Neural network based pharmaceutical weak foreign body visual inspection robot [J].Electronic Measurement and Instrumentation, 2015,29(12): 17461756.
    [4]SHAFAIT F,IMRAN S M,KLETTEMATZAT S. Fault detection and localization in empty water bottles through machine vision[C].IEEE ETech,2004: 3034.
    [5]AIGER D, TALBOT H. The phase only transform for unsupervised surface defect detection[J]. IEEE Con ference on Computer Vision & Pattern Recognition, 2010, 238(6): 295303.
    [6]段峰.啤酒瓶视觉检测机器人研究[D].长沙:湖南大学,2007: 8292. DUAN F.Study on visual empty bottle inspector for beer bottle[D].Changsha: Hunan University,2007: 8292.
    [7]DUAN F.A machine vision inspector for beer bottle[J]. Engineering Applications of Artificial Intelligence, 2007,20(7): 10131021.
    [8]马思乐,黄彬,何印洲,等.智能空瓶检测系统瓶底快速定位实现[J].自动化仪表,2012,33(10):3941,45. MA S L,HUANG B,HE Y ZH,et al, Implementation of fast positioning for the bottom of bottle intelligent empty bottie inspection system[J].Process Automation Instrumentation, 2012, 33(10):3941,45.
    [9]张田田.基于机器视觉的啤酒瓶瓶口检测系统的研究[D].青岛: 山东科技大学,2009: 3645. ZHANG T T.The research on visionbased beer finish inspector [D].Qingdao: Shangdong University of Science and Technology, 2009: 3645.
    [10]俞龙江,杨英,孙圣和.基于最小二乘拟合法的焊点形状检测[J].仪器仪表学报,2007,28( 7) : 12551258. YU L J,YANG Y,SUN SH H.Solder joint shape ins pection using least square fitting[J].Chinese Journal of Scientific Instrument,2007,28( 7) : 1255 1258.
    [11]黄志鸿,毛建旭,王耀南,等.基于机器视觉的啤酒瓶口缺陷检测分类方法研究[J]. 电子测量与仪器学报,2016,30(6): 873879. HUANG ZH H,MAO J X,WANG Y N,et al. Research on beer bottle defect classification detection method based on machine vision [J]. Electronic Measurement and Instrumentation, 2016, 30(6): 873879.
    [12]于晓东.基于机器视觉的玻璃瓶在线检测算法研究与系统实现[D]. 武汉: 华中科技大学,2013: 3337. YU X D. Research on algorithms of glass bottles online inspection based on machine vision and system implementation[D].Wuhan:Huazhong University of Science and Technology, 2013: 3337.
    [13]周显恩,王耀南,李康军,等.一种多次随机圆检测及拟合度评估的瓶口定位法[J].仪器仪表学报,2015,36(9):2021 2029. ZHOU X E,WANG Y N,LI K J,et al.One kind of multiple round random testing and assessment of the bottle fitting location method [J]. Chinese Journal of Scientific Instru ment, 2015,36(9): 20212029.
    [14]STEGER C,ULRICH M,WIEDEMANN C.Machine Vision Algorithms and Applications[M]. Newyork:WileyVCH, 2007.
    [15]张文博,姬红兵,王磊.一种自适应权值的多特征融合分类方法[J].系统工程与电子计术,2013,35(6):11331137. ZHANG W B,JI H B,WANG L. Adaptive weighted feature fusion classification method[J].Systems Engineering and Electronic, 2013,35(6):11331137.
    [16]WANG F Q, ZUO W M, ZHANG L,et al.A Kernel classification framework for metric learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 26 (9):19501962.
    [17]CHANG C C,LIN C J.LIBSVM: A library for support vector machines[J].ACM Transactions on Intelligent Systems & Technology, 2011, 2 (3):127.
    [18]WU J X.Efficient HIK SVM learning for image classify cation[J].IEEE Transactions on Image Processing,2012,21(10) : 4253.
    [19]刘松松,张辉,毛征,等.基于HRM特征提取和SVM的目标检测方法[J].国外电子测量技术,2014,33(10): 3841. LIU S S,ZHANG H,MAO ZH,et al.Detection method of HRM feature extraction and moving object based on SVM[J]. Foreign Electronic Measurement Technology,2014, 33(10) : 3841.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

范涛,朱青,王耀南,周显恩,刘远强.空瓶检测机器人瓶底缺陷检测方法研究[J].电子测量与仪器学报,2017,31(9):1394-1401

复制
分享
文章指标
  • 点击次数:3091
  • 下载次数: 8573
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2017-11-06
文章二维码