Ungsten Ore Primary Selection Based on Fuzzy Support Vector Machine and D-S Evidence Theory

被引：0
|
作者：
Hu F.-H. [1 ,2 ]
Liu G.-P. [1 ]
Hu R.-H. [1 ]
Dong Z.-W. [1 ]
机构：
[1] School of Mechanical & Electrical Engineering, Nanchang University, Nanchang
[2] School of Mechanical & Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, 341000, Jiangxi
来源：
Liu, Guo-Ping (liuguoping@vip.163com) | 1600年 / Chinese Optical Society卷 / 46期
基金：
中国国家自然科学基金;
关键词：
D-S evidence theory; Decision fusion; Feature extraction; Fuzzy support vector machine; Image processing; Machine vision; Tungsten ore; Tungsten ore primary selection;
D O I：
10.3788/gzxb20174607.0710003
中图分类号：
学科分类号：
摘要：
According to the low accuracy and low stability of the single feature-based method for tungsten ore primary selection, a multi-feature fusion based on fuzzy support vector machine and D-S evidence theory was proposed. Firstly, the three types of vision feature that is color, gray and texture were extracted from the ore image after a series of image processing. Their probability function were acquired according to each type of feature utilizing fuzzy support vector machine and the results were used to D-S evidence theory as evidence. Finally, using D-S combination rule of evidence to achieve the decision fusion and giving final recognition result by classification rules. The experimental results show that the accuracy of multi-feature fusion methods is over 96% and it has good performance on accuracy and stability compared to the single feature-based method in tungsten ore primary selection. The accuracy and stability can meet the requirement of production process. © 2017, Science Press. All right reserved.
引用
收藏
相关论文
共 19 条
  • [1] Wang M.-Y., Jia M.-X., Xiao Y.-W., Et al., The present situation and sustainable development counter measures of tungsten resources in China, Nonferrous Metals Engineering, 4, 2, pp. 76-80, (2014)
  • [2] Long K., Design ofprimary sortingsystemoftungsten orebasedon theDSP, pp. 1-3, (2013)
  • [3] Kaartinen J., Hatonen J., Hyotyiemi H., Et al., Machine vision based control of zinc flotation a case study, Control Engineering Practice, 14, 12, pp. 1455-1466, (2006)
  • [4] Lin X., Research and application of flotation froth image texture extraction, pp. 23-27, (2013)
  • [5] Lin Z.-T., Miao C.-Y., Li X.-G., Et al., Conveyor belt breakage detection algorithm based on machine vision, Journal of Tianjin Polytechinc University, 33, 3, (2014)
  • [6] Xiao L.-L., Huang Z.-H., Research on primary algorithm of wolframite ore based on the physical properties, Mining Research and Development, 35, 9, pp. 36-39, (2015)
  • [7] Hu F.-H., Dong Z.-W., Kuang Y.-S., Online navel orange grading detection system based on machine vision, Journal of China Agricultural University, 21, 3, pp. 112-118, (2016)
  • [8] Ma S., Liu K., Xu G., Illumination analysis of texture image based on color statistics invariance, Computer Applications and Software, 31, 2, pp. 233-237, (2014)
  • [9] Penatti O.A.B., Valle E., Torres R.S., Comparatives study of global and texture descriptors for web image retrieval, Journal Visual Communication and Representation, 23, 2, pp. 359-380, (2012)
  • [10] Li J.N., Allinson M., A comprehensive review of current local features for computer vision, Neurocomputing, 71, 10-12, pp. 1771-1787, (2008)
12