收藏本站
收藏 | 手机打开
二维码
手机客户端打开本文

The Surface Defects Detection Algorithm Based on Computer Vision for Connectors

Alimbekov Abay  
【摘要】:Today's markets demand the highest quality levels with regard to homogenous,patterned,printed,coated,or colored complex surfaces.As an important part of automatic systems,the surface defect detection based on computer vision can ensure the quality of the production.Even the smallest deviations or defects lead to production interruption and decline.Traditional,artificial visual and sampling methods were used to detect the surface detection.However,these methods have a high error rate and affect the efficiency of production greatly.Therefore,the surface defect detection for a special component"connector" is studied in this paper.The research content consists of four main parts:1.First of all,common defect types of connectors are analyzed.According to the structure and image characteristics of the connector,combined with the machine vision defects detection technology,comparison between template and testing image were proposed.The system can be roughly divided into four parts,such as image acquisition,image pre-processing,image registration and connector defect's recognition.2.Some image pre-processing methods were investigated and applied to the connector images.After pre-processing,images are compared and the proper one is selected for the subsequent defect recognition.3.The image registration methods are investigated align the testing image and anchor one in the same coordinate for the comparison and detection in the net step.It is also the main contribution of this thesis.Firstly,the common registration methods based on edge feature detection,SURF and FAST are implemented respectively and compared.Then we propose an improved approach to increase the speed and accuracy utilizing the special characteristics of the connector in edge feature detection.4.After registration,the current test image is compared with the template.It is classified as the correct product ones or with different types of defects.


知网文化
【相似文献】
中国期刊全文数据库 前20条
1 叶发茂;徐少平;熊宇虹;;Two-step image registration by artificial immune system and chamfer matching[J];Chinese Optics Letters;2008年09期
2 张见威;黄达承;桂姜琴;叶文忠;;2D registration based on contour matching for partial matching images[J];Journal of Central South University;2014年12期
3 Xijia Liu;Xiaoming Tao;Ning Ge;;Fast Remote-Sensing Image Registration Using Priori Information and Robust Feature Extraction[J];Tsinghua Science and Technology;2016年05期
4 Shao-Ya Guan;Tian-Miao Wang;Cai Meng;Jun-Chen Wang;;A Review of Point Feature Based Medical Image Registration[J];Chinese Journal of Mechanical Engineering;2018年04期
5 ;Akamai Connector实现新整合[J];网络安全和信息化;2018年06期
6 ;Binding Post & Banana Connector[J];家电检修技术;2014年03期
7 ;Finite element model analysis of thermal failure in connector[J];Journal of Zhejiang University(Science A:An International Applied Physics & Engineering Journal);2007年03期
8 马金锋;潘瑜春;郭占军;王纪华;;应用ArcIMS Java connector制作动态专题图[J];计算机应用研究;2008年05期
9 沈洪兴,张春才,许硕贵,王家林;Nickel-Titanium swan-like memory connector: a new tool to treat humeral shaft nonunion[J];Journal of Medical Colleges of PLA;2004年01期
10 杨?,裴继红;Image registration by maximization of mutual information based on edge width matching using particle swarm optimization[J];Chinese Optics Letters;2005年09期
11 谷家扬;吴介;祁恩荣;管义锋;袁宇波;;超大型浮体连接器载荷时域计算(英文)[J];Journal of Marine Science and Application;2015年02期
12 ;A fully automatic registration approach based on contour and SIFT for HJ-1 images[J];Science China(Earth Sciences);2012年10期
13 Yang Yu;Yingchun Guo;Ruili Wang;Susha Yin;Ming Yu;;Registration Based on ORB and FREAK Features for Augmented Reality Systems[J];Transactions of Tianjin University;2017年02期
14 SHI Wei;SU Fenzhen;WANG Ruirui;LU Yongduo;;Optical and SAR image registration based on improved nonsubsampled wavelet transform for sea islands[J];Acta Oceanologica Sinica;2014年05期
15 陶小平;闫峰;;Image improvement based on sub-pixel post-integration for a staring imaging system in geostationary orbit[J];Chinese Optics Letters;2014年04期
16 Takashi Shigenaga,Katsuki Suematsu,Masao Shinoda,Takayuki Ando;Two-Dimensional Super High Density Multi-Fiber Connector[J];光学学报;2003年S1期
17 ;Microchip MCU在MFi中的应用[J];电子产品世界;2013年08期
18 FENG Jing;MA Long;BI FuKun;ZHANG XueJing;CHEN He;;A coarse-to-fine image registration method based on visual attention model[J];Science China(Information Sciences);2014年12期
19 余澜,李润培,舒志;Dynamic Responses of Mobile Offshore Base Connectors[J];China Ocean Engineering;2003年04期
20 金晶;王强;沈毅;;A MNCIE method for registration of ultrasound images[J];Journal of Harbin Institute of Technology;2007年02期
中国重要会议论文全文数据库 前10条
1 CAO Jian;LIANG Jie;XIE Xiao-fang;HU Xun-qiang;;Accelerated Wide Baseline Matching using OpenCL[A];proceedings of 2010 3rd International Conference on Computer and Electrical Engineering (ICCEE 2010 no.2)[C];2012年
2 Zhang Huiqing;Gao Lin;;Image Registration Research Based on SUSAN-SURF Algorithm[A];第26届中国控制与决策会议论文集[C];2014年
3 XIU Ha-ning;ZHU Sheng-ying;CUI Ping-yuan;;Deep Space Moving Target Detection Based on Technology of Image Matching[A];第26届中国控制与决策会议论文集[C];2014年
4 Qiu-Ju Yang;Xue-Mei Xiao;;A New Registration Method Base on Improved Sobel and SIFT Algorithms[A];proceedings of 2010 3rd International Conference on Computer and Electrical Engineering (ICCEE 2010 no.2)[C];2012年
5 FENG Zhen;GUO Yanning;XING Jingyi;HUO Xiang;;The Implementation of Keren Imagie Registration System on Raspberry Pi Platform[A];第36届中国控制会议论文集(G)[C];2017年
6 ;Study to the Influence of Registration Error to Fusion Image Quality[A];中国光学学会2011年学术大会摘要集[C];2011年
7 Chuanying Wang;Jixiang Sun;;An Automatic Registration of UV Images[A];2012年计算机应用与系统建模国际会议论文集[C];2012年
8 Dong Zhao;Qi Wang;Haiyan Sun;Xiaopeng Hu;;A Method of Acceleration Applied in Symmetric-SIFT and SIFT[A];2013年中国智能自动化学术会议论文集(第二分册)[C];2013年
9 高远;童锡良;邓勇;王慧;邓子林;;Amethod for the co-registration of Photoacoustic and Speckle images[A];中国光学学会2011年学术大会摘要集[C];2011年
10 ;Medical image registration based on Phase Congruency and RMI[A];中国生物医学工程学会成立30周年纪念大会暨2010中国生物医学工程学会学术大会壁报展示论文[C];2010年
中国博士学位论文全文数据库 前3条
1 Akram Ismail Mohamed Omara;[D];复旦大学;2013年
2 HOCINE LABIDI;多摄像机下的目标检测、跟踪与识别[D];北京理工大学;2015年
3 MOHAMED BACHIR BOUBEKEUR;针对视频中移动目标检测的背景建模采样方法研究[D];北京理工大学;2015年
中国硕士学位论文全文数据库 前9条
1 Alimbekov Abay;[D];南京理工大学;2017年
2 阿尼斯(Anees Ahmed);使用静态方法对学生java程序评分[D];哈尔滨工业大学;2018年
3 Pedro Rodríguez Pérez;利用后触碰速度匹配的柔性控制捕获自由浮动目标[D];武汉大学;2018年
4 王勤;图的导出匹配可扩性[D];郑州大学;2000年
5 毋伟;[D];郑州大学;2003年
6 Rojanakat Payomrat;基于神经网络的双目视差估计[D];哈尔滨工程大学;2010年
7 孙朝杰;生物组织光透明机理[D];浙江理工大学;2010年
8 IBRAHIMA SORY MAGASSOUBA(索利);彩色结构光三维扫描重构技术研究[D];长春理工大学;2012年
9 VIKTOR PAKHOMOV;[D];华南理工大学;2015年
中国重要报纸全文数据库 前2条
1 王众;Keyssa:数据之吻[N];计算机世界;2016年
2 本报记者 贺骏;谷歌Pixel手机被曝重大漏洞 360公司再度“治未病”[N];证券日报;2018年
 快捷付款方式  订购知网充值卡  订购热线  帮助中心
  • 400-819-9993
  • 010-62982499
  • 010-62783978