The application of Ball Vector Machine for image segmentation

Aimed at standard Support Vector Machine (SVM) having a high training complexity for image segmentation, a new method based on Ball Vector Machine (BVM) for image segmentation is proposed in this paper. The experimental results show that two methods for image segmentation have the same effect, but the training time of BVM is significantly lesser than that of SVM. It is verified and validated that BVM for image segmentation can significantly improve the performance of image segmentation.