1. Recognition and Segmentation Method of Adhering Bars Based on Support Vector Machine
- Author
-
Liang Yu Li, Bing Le Liu, and Guo Hua Liu
- Subjects
Engineering ,Structured support vector machine ,business.industry ,Feature vector ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,General Engineering ,Pattern recognition ,Support vector machine ,Radial basis function kernel ,Segmentation ,Computer vision ,Artificial intelligence ,business ,Classifier (UML) - Abstract
This paper proposes a new solution to recognize and segment adhering bars. A support vector machine (SVM) is constructed according to the feature vectors of training samples to recognize the adhesions type of bars. The geometric feature values and moment feature values based on Blob regions in the image are extracted, which are the input feature vectors of support vector machine. The trained classifier is used for identifying the adhesions type of bars in the image. Finally, classification and recognition are realized by support vector machine. The experimental result shows that the recognition accuracy based RBF kernel achieves 100%. The method is feasible and effective for the recognition and segmentation of the adhering bars.
- Published
- 2014