Title :
Research on SVM Based Classification for Welding Defects in Radiographic Testing
Author :
Yan Hanbing ; Zhao Lina ; Ju Hui
Author_Institution :
Coll. of Autom. Control Eng., ChengDu Univ. of Inf. Technol., Chengdu, China
Abstract :
After analysis of the welding defect features, five typical features are successfully extracted from the welding defect features. Binary decision tree is used to make a greatest distinction between welding defects. Therefore, a support vector machines based binary decision tree is proposed, which owns good performance in the classification and the noticeable achievements are made in the classification of welding defects with the proposed method.
Keywords :
decision trees; radiography; support vector machines; welding; SVM based classification; binary decision tree; radiographic testing; support vector machines; welding defect features; Brightness; Classification tree analysis; Decision trees; Radiography; Shape; Strips; Support vector machine classification; Support vector machines; Testing; Welding;
Conference_Titel :
Image and Signal Processing, 2009. CISP '09. 2nd International Congress on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4244-4129-7
Electronic_ISBN :
978-1-4244-4131-0
DOI :
10.1109/CISP.2009.5302010