Research on Adaptive Segmentation Algorithm of Sports Image based on Support Vector Machine

Image segmentation is an important problem in image analysis and pattern recognition. The so-called image segmentation refers to distinguishing different regions with special significance in the image, so that these regions do not intersect with each other and satisfy certain similarity criteria. At present, many different types of image segmentation methods have been proposed, such as those based on thresholds, regions, and edges. The threshold method is simple to calculate and thus the segmentation speed is fast, the area method is ideal for processing relatively uniform images, and the edge method is suitable for processing images with less noise. With the development of image segmentation theory, image segmentation methods combined with specific theories have emerged, such as fuzzy C-means theory and support vector machine theory. Some scholars have tried to improve the SVM algorithm and reduce the influence of noise by using the ideas of image neighborhood information or relaxing segmentation boundaries. The support vector machine method (SVM) is a common method to solve the problem of image segmentation. In this paper, support vector machine is used to perform adaptive image segmentation, which has strong generalization ability and can handle image segmentation problems with fewer sample points.