Recognition and Classification of Hot Strip Surface Defect Based on Binary Tree SVM

An Na Wang; Chao Hu; Chang Liang Xue; Hong Rui Zhang

doi:10.4028/www.scientific.net/AMR.538-541.427

Paper Titles

Effects of RE on the Friction and Abrasion Character of Porcelain Enamel Coating
p.410

Low Cost Anti-Reflection Coating for Photovoltaic Application
p.414

Thermal and Flow Modeling of Alkali-Metal Thermoelectric Power Generation (AMTEC)
p.419

Effect of Braided Structure on Mechanical Properties of C_f/SiC Composites
p.423

Recognition and Classification of Hot Strip Surface Defect Based on Binary Tree SVM
p.427

Failure Analysis of Valve Seat Corrosion in a Triplex Plunger Pump
p.431

An Intelligent Decision Model for Spinning Process Optimization
p.439

Process-Parameter Optimization for Fused Deposition Modeling Based on Taguchi Method
p.444

Effect of Nonlinear Kinematic Hardening Model on Draw-Bend Springback Behavior of Dual Phase Steel
p.448

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 538-541Recognition and Classification of Hot Strip...

Recognition and Classification of Hot Strip Surface Defect Based on Binary Tree SVM

Abstract:

The paper presents a new method which uses Binary Tree SVM in the automatic classification of surface defects for hot strip. Two types of Binary Tree SVMs are applied in defect classification. Compared with BP neural network and one-against-one SVM, the algorithm adopted in the paper greatly improved the accuracy of classification and decreased the classification time.