Paper Title:
Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine
  Abstract

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%.

  Info
Periodical
Advanced Materials Research (Volumes 199-200)
Edited by
Jianmin Zeng, Zhengyi Jiang, Taosen Li, Daoguo Yang and Yun-Hae Kim
Pages
1769-1772
DOI
10.4028/www.scientific.net/AMR.199-200.1769
Citation
Y. W. Yu, G. F. Yin, L. Q. Du, "Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine", Advanced Materials Research, Vols. 199-200, pp. 1769-1772, 2011
Online since
February 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Dong Di Chen, Jia Wei Xiang, Yong Teng Zhong
Abstract:Fault diagnosis of machinery is in essence a kind of classification problem. Utilizing the desirable classification ability of support vector...
4257
Authors: Yun Hui Yang, Yi Ping Ji
Chapter 6: Measurement Technology and Instrument
Abstract:Distinguishing of wool and cashmere is one of the toughest problems in fiber identification area. Support Vector Machine (SVM) was advanced...
1198
Authors: Ling Zhang
Chapter 18: Mechanical and Electronic Engineering Control
Abstract:Aiming at the deficiency of the local minimum occurring in neural network used for speech recognition, the paper employs support vector...
7516
Authors: Jian Hua Zhang
Chapter 12: Computer-Aided Design, Manufacturing and Engineering
Abstract:That Support Vector Machines applies to image recognition have good results,But the kernel function C and parameters of the SVM which...
4124
Authors: Ling Jian Li, Min Fang Peng, Ke Xin Zhao
Chapter 5: Control and Automation, Fault Diagnosis
Abstract:This paper presents a genetic algorithm to optimize support vector machine parameters for grounding grid fault diagnosis method. Grounding...
909