光子学报 ›› 2020, Vol. 49 ›› Issue (10): 1015002-1015002.doi: 10.3788/gzxb20204910.1015002

• 计算机视觉 • 上一篇    下一篇

基于改进孪生支持向量机的齿廓图像边缘失真分类研究

孙禾1,2(), 赵文珍1(), 赵文辉1, 段振云1   

  1. 1.沈阳工业大学 机械工程学院,沈阳 110870
    2.辽宁科技学院 电气与信息工程学院,辽宁 本溪 117004
  • 收稿日期:2020-08-10 接受日期:2020-09-17 出版日期:2020-10-25 发布日期:2020-10-13
  • 通讯作者: 赵文珍 E-mail:sunhe0616@163.com;zhaowz1031@sina.com
  • 作者简介:孙禾(1973—),男,副教授,博士研究生,主要研究方向为视觉测量、模式识别与智能系统. Email: sunhe0616@163.com|赵文珍(1956—),男,教授,博士,主要研究方向为视觉测量、复杂曲面加工与测量. Email: zhaowz1031@sina.com
  • 基金资助:
    “十二五”国家科技支撑计划(2014BAF08B01);辽宁省自然科学基金指导计划(20170540474);特殊环境机器人技术四川省重点实验室开放基金(19kftk03)

Classification of Edge Distortion of Tooth Profile Image Based on Improved Twin Support Vector Machine

He SUN1,2(), Wen-zhen ZHAO1(), Wen-hui ZHAO1, Zhen-yun DUAN1   

  1. 1.School of Mechanical Engineering,Shenyang University of Technology,Shenyang 110870,China
    2.School of Electrical and Information Engineering,Liaoning Institute of Science and Technology,Benxi,Liaoning 117004,China
  • Received:2020-08-10 Accepted:2020-09-17 Online:2020-10-25 Published:2020-10-13
  • Contact: Wen-zhen ZHAO E-mail:sunhe0616@163.com;zhaowz1031@sina.com
  • Supported by:
    National Science and Technology Support Program of the 12th Five-Year Plan(2014BAF08B01);Liaoning Provincial Natural Science Foundation(20170540474);Fund of Robot Technology Used for Special Environment Key Laboratory of Sichuan Province(19kftk03)

摘要:

提出了一种基于最优分类特征的偏二叉树孪生支持向量机多分类算法(OCF-PBT-TWSVM),以实现针对齿廓图像边缘失真的非平稳瞬态随机信号进行有效分类,满足齿轮视觉测量实时性和失真补偿精度的要求.选择边缘动态分量信号最大值vm、边缘失真信号位置qu、边缘失真率rlv构成特征向量,组成训练样本集和测试样本集;以失真补偿需求为目标定义变权值特征向量测度γ,按照γ递减原则自顶向下完成OCF-PBT-TWSVM算法构建;采用粒子群优化方法进行算法参数优化,使c1,c2,g参数的性能达到最优.试验结果表明:在小样本数据情况下,提出的OCF-PBT-TWSVM多分类算法的最终分类准确率达96.96%,与PBT-SVM多分类算法相比具有更好的分类效果、训练速度也更快,能够满足后续失真补偿测量精度和齿轮视觉测量实时性的需求.

关键词: 图像边缘失真, 偏二叉树, 孪生支持向量机, 粒子群优化, 多分类

Abstract:

Proposed a partial binary tree twin support vector machine multi-classification algorithm based on optimal classification features (OCF-PBT-TWSVM) to achieve effective classification of non-stationary transient random signals with edge distortion of tooth profile images, and to meet the requirements of real-time gear vision measurement and distortion compensation accuracy Claim. Selected the maximum value vm of the edge dynamic component signal, the position of the edge distortion signal qu, and the edge distortion rate rlv to formed the feature vector,which constituted the training sample set and the test sample set at the same time; defined the variable weight feature vector measure γ with the target of distortion compensation, and completed the construction of the OCF-PBT-TWSVM algorithm according to γ decreasing; used the particle swarm optimization method to optimize the algorithm parameters to optimize the performance of the c1c2, and g parameters. The test results show that, the final classification accuracy of the OCF-PBT-TWSVM multi-classification algorithm proposed in this paper is 96.96% in the case of small sample data, which has better classification effect and training speed than the PBT-SVM multi-classification algorithm. It is faster and can satisfy the requirements of subsequent distortion compensation measurement accuracy and real-time gear vision measurement.

Key words: Distortion of image edges, Twin support vector machine, Partial binary tree, Particle swarm optimization, Multi-classification

中图分类号: