A sparse representation based fast detection method for surface defect detection of bottle caps

被引：46
作者：
Zhou, Wenju [1 ,2 ,4 ,5 ]
Fei, Minrui [1 ,4 ,5 ]
Zhou, Huiyu [3 ]
Li, Kang [3 ,4 ,5 ]
机构：
[1] Shanghai Univ, Shanghai Key Lab Power Stn Automat Technol, Sch Mechatron Engn & Automat, Shanghai 200072, Peoples R China
[2] Ludong Univ, Sch Informat & Elect Engn, Yantai 264025, Peoples R China
[3] Queens Univ Belfast, Sch Elect Elect Engn & Comp Sci, Belfast BT9 5AH, Antrim, North Ireland
[4] Shanghai Univ, UK China Sci Bridge Joint Lab, Shanghai, Peoples R China
[5] Queens Univ Belfast, UK China Sci Bridge Joint Lab, Belfast BT9 5AH, Antrim, North Ireland
来源：
NEUROCOMPUTING | 2014年 / 123卷
基金：
英国工程与自然科学研究理事会; 中国国家自然科学基金;
关键词：
Fast detection; Bottle cap; Surface defect; Circular region projection histogram (CRPH); Sparse representation;
D O I：
10.1016/j.neucom.2013.07.038
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A practical machine-vision-based system is developed for fast detection of defects occurring on the surface of bottle caps. This system can be used to extract the circular region as the region of interests (ROI) from the surface of a bottle cap, and then use the circular region projection histogram (CRPH) as the matching features. We establish two dictionaries for the template and possible defect, respectively. Due to the requirements of high-speed production as well as detecting quality, a fast algorithm based on a sparse representation is proposed to speed up the searching. In the sparse representation, non-zero elements in the sparse factors indicate the defect's size and position. Experimental results in industrial trials show that the proposed method outperforms the orientation code method (OCM) and is able to produce promising results for detecting defects on the surface of bottle caps. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码：406 / 414
页数：9
相关论文
共 29 条
  • [1] K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation
    Aharon, Michal
    Elad, Michael
    Bruckstein, Alfred
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) : 4311 - 4322
  • [2] [Anonymous], 2008, PATTERN RECOGNITION
  • [3] [Anonymous], 2007, P ADV NEUR INF PROC, DOI DOI 10.7551/MITPRESS/7503.003.0081
  • [4] Inspection and grading of agricultural and food products by computer vision systems - a review
    Brosnan, T
    Sun, DW
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2002, 36 (2-3) : 193 - 213
  • [5] An anisotropic diffusion-based defect detection for low-contrast glass substrates
    Chao, Shin-Min
    Tsai, Du-Ming
    [J]. IMAGE AND VISION COMPUTING, 2008, 26 (02) : 187 - 200
  • [6] Sausage Appearance Defect Inspection system based on Machine Vision
    Chen, Shuai
    Ma, Yue
    Shi, Haibo
    [J]. 2010 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-5, 2010, : 2485 - 2489
  • [7] Machine vision technology for agricultural applications
    Chen, YR
    Chao, KL
    Kim, MS
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2002, 36 (2-3) : 173 - 191
  • [8] Flaw detection of cylindrical surfaces in PU-packing by using machine vision technique
    Chiou, Yih-Chih
    Li, Wei-Chen
    [J]. MEASUREMENT, 2009, 42 (07) : 989 - 1000
  • [9] Deans S, 1983, RADON TRANSFORM SOME
  • [10] For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution
    Donoho, DL
    [J]. COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 2006, 59 (06) : 797 - 829
123