Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine
2011 ◽
Vol 199-200
◽
pp. 1769-1772
◽
Keyword(s):
In response to the dilemma for image identification by the existing classifier toward surface defects of steel ball, an improved support vector machine (SVM) for multiclass problems is proposed. Minimum distance method is presented to resolve the unclassifiable region of the multiclass SVMs. The 16 image features of the surface defects are selected as input vector of the SVMs. The experiment results show that more accurate identification toward surface defects of steel ball was achieved by the improved multiclass SVM and the accuracy can reach 95%.
2011 ◽
Vol 58-60
◽
pp. 2387-2391
2017 ◽
Vol 171
◽
pp. 140-150
◽
Keyword(s):
2018 ◽
Vol 25
(35)
◽
pp. 35693-35706
◽
2013 ◽
Vol 8
(12)
◽