Scene Classification Combining Low-level and Semantic Modeling Strategies

Scene classification is an important issue in the field of computer vision. Although considerable progress has been made, it remains a challenging issue. Most of the current scene classification approaches are based on either low-level or semantic modeling strategies. This paper presents a novel scene classification approach based on combining low-level and semantic modeling strategies. The experimental results show that the proposed approach performs competitively against previous methods across three publicly and commonly used data sets.