基于SVM的输送带钢丝绳芯图像的缺陷分类 |
| |
引用本文: | 刘厚鹏,苗长云,李现国.基于SVM的输送带钢丝绳芯图像的缺陷分类[J].电脑与微电子技术,2012(20):21-23,27. |
| |
作者姓名: | 刘厚鹏 苗长云 李现国 |
| |
作者单位: | 天津工业大学电子与信息工程学院,天津300387 |
| |
基金项目: | 天津市高等学校科技发展基金重点项目(No.2006ZD38) |
| |
摘 要: | 输送带钢丝绳芯缺陷一般分为:内部钢丝绳的划伤,铜丝绳芯的锈蚀,断裂,钢丝绳芯与胶带粘合力下降而导致的胶带脱落等故障。对常见的划伤和断裂的x光图像进行缺陷分类。使用机器学习方法学习图像特征,自动建立图像类的模型已成为一种有效的方法。采用支持向量机(SVM)方法通过训练特征向量,建立模型,对划伤和断裂的x光缺陷图像进行自动分类。实验结果表明基于SVM的算法适合X光钢丝绳芯图像的缺陷分类。
|
关 键 词: | 支持向量机 缺陷分类 输送带钢丝绳芯 |
Defect Classification of Steel Rope Cord Conveyer Belt Images Based on SVM |
| |
Authors: | LIU Hou-peng MIAO Chang-yun LI Xian-guo |
| |
Affiliation: | (School of Electronics and Information Engineering, Tianjin Polytechnic University,Tianjin 300387) |
| |
Abstract: | The defects of the steel rope cord conveyor belt generally are the internal steel cord's scratch, steel cord's corrosion, steel cord's fracture, tap off that result from steel cord and adhesive tape's adhesive force down and so on. Makes the classification of the X-ray images of the usual scratch and fracture. Using machine learning method to learn image features and to automati- cally construct models for image classes is a promising way. Through training feature vector and building model, uses SVM method to classifies the scratch and fracture's X-ray image defect. The experimental result shows that the algorithm based on SVM is suitable for the defect clas- sification of X-ray steel cord image. |
| |
Keywords: | SVM Defect Classification Steel Cord Conveyor Belt |
本文献已被 维普 等数据库收录! |