Classification of appearance defects based on WMD multicore learning

ZHANG Shuhang; LIAN Xiaofeng; WANG Kun

doi:10.13873/J.1000-9787(2020)10-0129-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Classification of appearance defects based on WMD multicore learning

更新时间：2025-09-11

- Classification of appearance defects based on WMD multicore learning
- Issue 10, Pages: 129-131+134(2020)
- 作者机构：
  
  北京工商大学计算机与信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2020)10-0129-03
  CLC： TP181;TP391.41
- Published：2020
- 稿件说明：
移动端阅览
ZHANG Shuhang, LIAN Xiaofeng, WANG Kun. Classification of appearance defects based on WMD multicore learning[J]. 2020, (10): 129-131+134.
DOI：

ZHANG Shuhang, LIAN Xiaofeng, WANG Kun. Classification of appearance defects based on WMD multicore learning[J]. 2020, (10): 129-131+134. DOI： 10.13873/J.1000-9787(2020)10-0129-03.

摘要

基于马氏距离的支持向量机(MD-SVM)因具有考虑样本总体分布、消除各特征之间的耦合关系、与量纲无关等特性

在工业产品外观缺陷分类中应用广泛。考虑到马氏距离(MD)中总体协方差矩阵的类内、类间协方差矩阵对分类结果的影响不同

因此给两者设置不同权重系数

提出一种加权马氏距离支持向量机(WMD-SVM)模型。训练样本集得到最优权重系数;针对不同缺陷图像特征选择合适的核函数

并将提出的改进模型应用于各核函数

构成多核学习模型。用模糊约束理论求解模型中各核函数权重。实验结果表明:所提改进方法具有更优的分类精度和实时性。

Abstract

The support vector machine（ SVM） based on Mahalanobis distance（ MD） is widely used in classification of industrial product appearance defects because it has the characteristics of considering the overall distribution of samples

eliminating the coupling relationship between various features

and not related to dimension. Considering that the internal and inter-class covariance matrices of the total association variance matrix in MD have different effects on the classification results

different weight coefficients are set for the two

and then a weighted MD-SVM（ WMD-SVM） model is proposed. Trained sample set obtain optimal weight coefficients. Suitable kernel function is selected for different defect image features

and the proposed improved model is applied to each kernel function

which constitutes multi-core learning model. The fuzzy constraint theory is used to solve the weight of each kernel function in the model. Experimental results show that the improved method has better classification precision and real-time performance.

关键词

Keywords

references

Views

172

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

DPC algorithm based on sub-cluster fusion and LDA

Study on fault diagnosis for spectroscope amplifier based on GSA-SVM

Research on sleeping posture recognition method based on flexible pressure sensor

Gearbox fault diagnosis based on multi-channel input CNN-SVM

Study on fault diagnosis for current amplifier based on PSO-SVM

Related Author

LIU Xiaokang

ZHANG Jing

ZHANG Yanchi

LIU Dongmei

WANG Haoran

LIU Chun

LIU Zhiqiang

LIU Jinyue

Related Institution

School of Electronic and Electrical Engineering,Shanghai University of Engineering Science

School of Electrical Engineering, Shanghai Dianji University

School of Electrical and Automation Engineering, Hefei University of Technology

School of Mechanical Engineering,Hebei University of Technology

Hebei Key Laboratory of Smart Sensing and Human-Robot Interaction

⁰