基于SVM的输送带钢丝绳芯图像的缺陷分类

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。

Defect Classification of Steel Rope Cord Conveyer Belt Images Based on SVM

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.