Application of Fuzzy Support Vector Machine in Chalky Rice Identification

Xiang Li; Shang Bing Gao; Ying Quan Chen

doi:10.4028/www.scientific.net/AMR.507.202

Paper Titles

Working Principle and Performance of Wire Electrical Discharge Machining
p.180

The Research and Realization of Image Collection and Compression Technology in Embedded System
p.187

The Non-Equidistant New Information GRM(1,1) and its Application
p.191

Forward Displacement Analysis of 5SPS-1CCS Parallel Manipulator Based on Hyper-Chaotic Newton Method
p.196

Application of Fuzzy Support Vector Machine in Chalky Rice Identification
p.202

Long Jump Technique Based on the Method of Mechanical Analysis
p.208

The Application of 3D Scanner on Whole Body in 3D Clothing Design
p.212

Characteristic Analysis and Optimization of CNC Machine Tool Spindle Based on Finite Element Method
p.217

The Development of Stamping Mold Frame Based on VBA in Auto CAD
p.222

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 507Application of Fuzzy Support Vector Machine in...

Application of Fuzzy Support Vector Machine in Chalky Rice Identification

Abstract:

In order to improve the identification accuracy of fuzzy support vector machine for chalky rice, this paper puts forward a fuzzy support vector machine method based on fuzzy K nearest-neighbor. This method firstly gets a sample center by calculating sample mean aimed at every class sample; and then it calculates the initial membership of sample by calculating the distance between sample and center; finally, it calculates K neighbor points of each sample, calculates the membership of sample according to the fuzzy K neighbor method, and integrates the initial membership with fuzzy K neighbor membership at a certain proportion, to get the ultimate membership values of samples. Combined with image detection problems of rice, verify the validity of this method. Experiments show that this method not only can improve the accuracy of identification but also can improve its speed, with a better result than common fuzzy support vector machine.

You might also be interested in these eBooks

Sport, Arts Materials and Management Science

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 507)

Pages:

202-207

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.507.202

Citation:

Cite this paper

Online since:

April 2012

Authors:

Xiang Li, Shang Bing Gao, Ying Quan Chen

Keywords:

Fuzzy K Neighbors, Fuzzy Support Vector Machine, Rice Image Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WU Qing, LIU San-Yang, DU Zhe. Fuzzy Support Vector Machine Method Based on Border Vector Extraction. Pattern Recognition and Artificial Intelligence, 2008, 21(3): 332-337.

Google Scholar

[2] LIU Tai-an, LIANG Yong-quan, XUE Xin. New Multiclassification Algorithm Based on Fuzzy Support Vector Machines. Application Research of Computers, 2008, (7): 2041-(2042).

Google Scholar

[3] LI Tian-zhen, Zhou Bai-qing. Research on rice-quality inspection basing on computer vision technology. Cereal and Food Industry, 2005, 12(4): 50-55.

Google Scholar

[4] Meir Perez. A Hybrid Fuzzy-SVM classifier, applied to gene expression profiling for automated leukaemia diagnosis. In: IEEE 25th Convention of Digital Object Identifier, 2008: 041-045.

DOI: 10.1109/eeei.2008.4736603

Google Scholar

[5] Joachims T. Makong Large-scale support vector machine learning practical. In:B. Scholkopf, C. J. C. Burges, A. J. Smola, eds. Advances in Kernel Methods- Support Vector Learning, Cambridge, MA, MIT Press. 2006: 1-10.

DOI: 10.7551/mitpress/1130.003.0015

Google Scholar