从特征识别到局部拼接的零件轴承孔在线检测
|
摘要
针对在无夹具定位的饮料灌装设备轨迹控制零件轴承孔在线检测过程中,单张图片无法满足高精度检测需求的问题,提出一种从零件整体特征识别到局部图像拼接的零件轴承孔在线检测的方法。首先采用全局图像轴承孔的中心位置关系构建特征描述矩阵,利用支持向量机(SVM)方法进行整体特征孔识别。针对已识别轴承孔,采用KAZE方法对局部特征孔图像进行拼接,实现轴承孔的高精度测量。研究实例表明,该方法可快速实现轴承孔的高精度测量,测量效率和成功率较高。
In the online detection process of the bearing hole of the trajectory control part of a beverage filling equipment without fixture positioning,an single picture isn't enough for the high-precision detection measuring.This paper proposes a 2 steps method:feature recognition from the overall visual and high resolution local image obtaining by image stitching.Firstly,the feature description matrix is constructed by the central position relationship of the global image bearing hole,and the overall feature hole recognition is performed by the support vector machine(SVM)method.Secondly,for the identified bearing holes,the KAZE method is used to splicing the local feature hole images to achieve high-precision measurement of the bearing holes.Research examples show that the method can quickly achieve high-precision measurement of bearing bores with high measurement efficiency and success rate.
In the online detection process of the bearing hole of the trajectory control part of a beverage filling equipment without fixture positioning,an single picture isn't enough for the high-precision detection measuring.This paper proposes a 2 steps method:feature recognition from the overall visual and high resolution local image obtaining by image stitching.Firstly,the feature description matrix is constructed by the central position relationship of the global image bearing hole,and the overall feature hole recognition is performed by the support vector machine(SVM)method.Secondly,for the identified bearing holes,the KAZE method is used to splicing the local feature hole images to achieve high-precision measurement of the bearing holes.Research examples show that the method can quickly achieve high-precision measurement of bearing bores with high measurement efficiency and success rate.
引文
[1]王耀南,陈铁健,贺振东,等.智能制造装备视觉检测控制方法综述[J].控制理论与应用,2015(3):273-286.
[2]LOWE D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[3]刘立,詹茵茵,罗扬,等.尺度不变特征变换算子综述[J].中国图象图形学报,2013(8):885-892.
[4]WANG Fu-bin,TU Paul,CHEN Wu,et al.Multi-image mosaic with SIFT and vision measurement for microscale structures processed by femtosecond laser[J].Optics and Lasers in Engineering,2018,100:124-130.
[5]YANG Kun,PAN An-ning,YANG Yang,et al.Remote sensing image registration using multiple image features[J].Remote Sensing,2017,9(6):581-601.
[6]ALCANTARILLA P F,BARTOLI A,DAVISON A J.KA-ZE features[C]//FITZGIBBON A,LAZEBNIK S,PERO-NA P,et al.Computer.Vision-ECCV 2012.Berlin,Heidelberg:Springer Berlin Heidelberg,2012:214-227.
[7]杨婷婷,顾梅花,章为川,等.彩色图像边缘检测研究综述[J].计算机应用研究,2015(9):2 566-2 571.
[8]MUKHOPADHYAY P,CHAUDHURI B B.A survey of Hough Transform[J].Pattern Recognition,2015,48(3):993-1 010.
[9]张雨浓,陈锦浩,劳稳超,等.多类单输入多项式神经网络预测能力比较[J].系统仿真学报,2014(1):90-96.
[10]LUI Han,COCEA M.Induction of classification rules by Gini-index based rule generation[J].Information Sciences,2018,436-437:227-246.
[11]郭明玮,赵宇宙,项俊平,等.基于支持向量机的目标检测算法综述[J].控制与决策,2014(2):193-200.
[12]邱光应,彭桂兰,陶丹,等.基于决策树支持向量机的苹果表面缺陷识别[J].食品与机械,2017,33(9):131-135.
[13]刘洋,王涛,左月明.基于支持向量机的野生蘑菇近红外识别模型[J].食品与机械,2016,32(4):92-94.
[14]WU Yi-chao,LIU Yu-feng.Robust Truncated Hinge Loss Support Vector Machines[J].Journal of the American Statistical Association,2007,102(479):974-983.
[15]HAMID N,YAHYA A,AHMAD R B,et al.A Comparison between Using SIFT and SURF for Characteristic Region Based Image Steganography[J].International Journal of Computer Science Issues,2012,9(3):110.
[16]汪方斌,储朱涛,朱达荣,等.一种改进的KAZE特征检测描述算法[J].激光与光电子学进展,2018,55(9):165-172.
[2]LOWE D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[3]刘立,詹茵茵,罗扬,等.尺度不变特征变换算子综述[J].中国图象图形学报,2013(8):885-892.
[4]WANG Fu-bin,TU Paul,CHEN Wu,et al.Multi-image mosaic with SIFT and vision measurement for microscale structures processed by femtosecond laser[J].Optics and Lasers in Engineering,2018,100:124-130.
[5]YANG Kun,PAN An-ning,YANG Yang,et al.Remote sensing image registration using multiple image features[J].Remote Sensing,2017,9(6):581-601.
[6]ALCANTARILLA P F,BARTOLI A,DAVISON A J.KA-ZE features[C]//FITZGIBBON A,LAZEBNIK S,PERO-NA P,et al.Computer.Vision-ECCV 2012.Berlin,Heidelberg:Springer Berlin Heidelberg,2012:214-227.
[7]杨婷婷,顾梅花,章为川,等.彩色图像边缘检测研究综述[J].计算机应用研究,2015(9):2 566-2 571.
[8]MUKHOPADHYAY P,CHAUDHURI B B.A survey of Hough Transform[J].Pattern Recognition,2015,48(3):993-1 010.
[9]张雨浓,陈锦浩,劳稳超,等.多类单输入多项式神经网络预测能力比较[J].系统仿真学报,2014(1):90-96.
[10]LUI Han,COCEA M.Induction of classification rules by Gini-index based rule generation[J].Information Sciences,2018,436-437:227-246.
[11]郭明玮,赵宇宙,项俊平,等.基于支持向量机的目标检测算法综述[J].控制与决策,2014(2):193-200.
[12]邱光应,彭桂兰,陶丹,等.基于决策树支持向量机的苹果表面缺陷识别[J].食品与机械,2017,33(9):131-135.
[13]刘洋,王涛,左月明.基于支持向量机的野生蘑菇近红外识别模型[J].食品与机械,2016,32(4):92-94.
[14]WU Yi-chao,LIU Yu-feng.Robust Truncated Hinge Loss Support Vector Machines[J].Journal of the American Statistical Association,2007,102(479):974-983.
[15]HAMID N,YAHYA A,AHMAD R B,et al.A Comparison between Using SIFT and SURF for Characteristic Region Based Image Steganography[J].International Journal of Computer Science Issues,2012,9(3):110.
[16]汪方斌,储朱涛,朱达荣,等.一种改进的KAZE特征检测描述算法[J].激光与光电子学进展,2018,55(9):165-172.