Research on Foreign Body Detection for Granular Material Based on Feature Weighted OCSVM of Color Recognition

Abstract:

In granular materials processing, how to efficiently recognize and remove foreign bodies is very important. Training data including H,I mean and I standard deviation of target material are distinguished to be foreign bodies or not by training model, which is established using FWOCSVM method, while taking into account the characteristics of foreign body detection. A way to introduce the weight value reflecting the importance degree of attribute with its mean square deviation is developed to solve the problem, that is, attribute weights are not considered in OCSVM. The results show that FWOCSVM has more excellent performance than that of threshold or OCSVM .And color features adopted in the paper have excellent identification performance in above foreign bodies detection.

• Periodical: Advanced Materials Research (Volumes 734-737)
• Pages: 2983-2989
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.734-737.2983
• Online since: August 2013
• Authors: Ji Mei Zhou, Ze Zhang, Yan Li Xiang
• Keywords: Color Feature, Foreign Granule Detection, OCSVM, Unit Recognition

References

[1] Scholkopf B. Estimating The support of a high-dimensional distribution. Neural Computation, 13(2001)1443-1471.

[2] Ding-hai Wu, Pei-lin Zhang, Ren Guo-quan, Chen Fei. Review of one-class classification method based on support vector. Computer Engineering, 5 (2011)187-189.

[3] Aimin Feng, Chen Song-Can. Study on one-class classifiers based on kernel method. Journal of Nanjing Normal University, 12 (2008)1-6.

[4] Fu-guang Yao. Key technologies research on intelligent high-speed on-line foreign material recognition and sorting. Chongqing University, (2009).

[5] Wen-tao Chen. Key Research on tobacco foreign material online high-speed pattern recognition and eliminate technique. Chongqing University, (2003).

[6] Pan-chi Li, Shao-hua Xu. Support vector machine and kernel function characteristic analysis in pattern recognition. Computer Engineering and Design, 26 (2005) 302-304.

[7] Yuan-yuan Gao, Qiang-guo Liu. The wine quality evaluation model based on LIBSVM. Journal of Sichuan University, 10 (2010) 530-332.

[8] Yu-xia Luo, Jin-gang Liu. Program behavior control system based on one-class SVM with adjusted kernel using RST. Computer Engineering, 3 (2008) 154-156.

[9] Zhang Shuai, Zhang Ze. Research of locating robot color patch based on color vector analysis algorithm. Electronics, Communications and Control (ICECC), (2011) 395-398.

DOI: 10.1109/icecc.2011.6067839