Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine
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%.
Jianmin Zeng, Zhengyi Jiang, Taosen Li, Daoguo Yang and Yun-Hae Kim
Y. W. Yu et al., "Image Identification for Surface Defects of Steel Ball Based on Support Vector Machine", Advanced Materials Research, Vols. 199-200, pp. 1769-1772, 2011