Sports Image Classification and Application based on SIFT Algorithm

Abstract

The research on moving image classification and application based on SIFT algorithm is an important research work. This is the first time to conduct this type of research in the field of computer vision. SIFT algorithm is a method for finding key points in an image. It works by finding edges that are similar to each other and then identifying the relationship between them. The more similar two images are, the closer they are on the image. The main purpose of this study is to develop a model that can classify moving images with high accuracy and low computational cost. This method uses SIFT feature descriptor to divide sports images into four categories: football, basketball, volleyball and football. This method has been tested with other standard methods.