A Visual Semantic Template of Background for Scene Image
一种图像背景视觉语义模板的生成方法

Interpreting background is very important in natural scene images- This paper addresses the automatic classification of background region by using visual semantic template. The method to create the templates is introduced first. Then we use these templates to classify background regions, and the results are analyzed. We also use these templates to locate background objects in images, and to determine whether an image contains certain kind of background. The result is promising in object locating. Some approaches to improve the ability of these templates are also discussed.