Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine

被引：2
|
作者：
Yu, Yong Wei [1 ]
Yin, Guo Fu [1 ]
Du, Liu Qing [1 ]
机构：
[1] Sichuan Univ, Chengdu 610064, Peoples R China
来源：
ADVANCES IN MECHANICAL DESIGN, PTS 1 AND 2 | 2011年 / 199-200卷
关键词：
Image Identification; Support Vector Machine; Surface Defect; Steel Ball; REDUCTION;
D O I：
10.4028/www.scientific.net/AMR.199-200.1769
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
In response to the dilemma for image identification by the existing classifier toward surface defects of steel ball, an improved support vector machine (SVM) for multiclass problems is proposed. Minimum distance method is presented to resolve the unclassifiable region of the multiclass SVMs. The 16 image features of the surface defects are selected as input vector of the SVMs. The experiment results show that more accurate identification toward surface defects of steel ball was achieved by the improved multiclass SVM and the accuracy can reach 95%.
引用
收藏
页码：1769 / 1772
页数：4
相关论文
共 50 条
  • [21] Image Classification with Ant Colony Based Support Vector Machine
    Zhao Baoyong
    Qi Yingjian
    2011 30TH CHINESE CONTROL CONFERENCE (CCC), 2011, : 3260 - 3263
  • [22] Natural Image Classification Based on Improved Support Vector Machine
    Qi, Yingjian
    Ou, Zhiwei
    Zhang, Bin
    Liu, Tingzhan
    Li, Ying
    INFORMATION TECHNOLOGY FOR MANUFACTURING SYSTEMS II, PTS 1-3, 2011, 58-60 : 2387 - +
  • [23] Study of nonlinear system identification based on support vector machine
    Zhang, MG
    Yan, WW
    Yuan, ZT
    PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 3287 - 3290
  • [24] Identification method of encrypted traffic based on support vector machine
    Cheng G.
    Chen Y.
    Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition), 2017, 47 (04): : 655 - 659
  • [25] Surface electromyography recognition method based on support vector machine
    Yang Peng
    Chen Ling-ling
    Guo Xin
    Zhao Qi
    Proceedings of 2006 Chinese Control and Decision Conference, 2006, : 321 - 324
  • [26] A multi-class classifier based on support vector hyper-spheres for steel plate surface defects
    Gong, Rongfen
    Chu, Maoxiang
    Yang, Yonghui
    Feng, Yao
    CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2019, 188 : 70 - 78
  • [27] Neural Cell Image Segmentation Method Based on Support Vector Machine
    Niu, Shiwei
    Ren, Kan
    AOPC 2015: IMAGE PROCESSING AND ANALYSIS, 2015, 9675
  • [28] Research of diver sonar image recognition based on support vector machine
    Li Ke
    Li Chonglun
    Zhang Wei
    CURRENT TRENDS IN THE DEVELOPMENT OF INDUSTRY, PTS 1 AND 2, 2013, 785-786 : 1437 - +
  • [29] Research of Detector for Surface Defects of Steel Ball Based on Improved PID Control
    Liu, Y. Z.
    Liu, X. L.
    Wang, P.
    Wang, Y. W.
    Zhu, L.
    Wang, L.
    MANUFACTURING AUTOMATION TECHNOLOGY, 2009, 392-394 : 941 - 945
  • [30] SPATIAL INFORMATION BASED SUPPORT VECTOR MACHINE FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Kuo, Bor-Chen
    Huang, Chih-Sheng
    Hung, Chih-Cheng
    Liu, Yu-Lung
    Chen, I-Ling
    2010 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2010, : 832 - 835
12345