A New Image Segmentation Method Based on Support Vector Machine
Yinlong Wang, Yao Lu, Yan Li · 2019
Image segmentation is a hot and difficult research topic in the fields of pattern recognition and computer vision. At present, the method based on support vector machine has been widely used in image segmentation, but the selection of training samples mostly depends on manual selection. This reduces the adaptability of image segmentation, but also affects the classification performance of support vector machine. A new image segmentation method based on support vector machine (SVM) is proposed, which combines the advantages of mean clustering algorithm to automatically obtain training samples, then extracts image color features and texture features respectively, and uses them as training samples of SVM. Finally, the trained classifier is used to segment the image. The experimental results show that the proposed algorithm is better than the traditional support vector machine-based algorithm.