Integrated image representation based natural scene classification

Natural scene classification (NSC) is a challenging pattern classification problem. As one of state-of-the-art techniques, the bag-of-feature (BOF) model has received extensive considerations in characterizing the image. To boost the flexibility during visterm construction in BOF model, an integrated scheme for image representation is proposed by adaptive analysis on the local visual complexity of image itself. First, the flatness of each scene category is determined by the total flatness of all images belonging to this category. Then the new integrated image representation of the scene category is built by weighting the two representations (based on a pixels gray value descriptor and a dense SIFT descriptor) through the normalized coefficients computed by the flatness of the category. Finally, a hierarchical generative model is exploited to learn natural scene categories. Experimental results demonstrate that the satisfactory classification accuracy achieves about 83.67% on a large set of 15 categories of complex scenes.

► We propose an integrated image representation by adaptive analysis on the local visual complexity.
► We determine the flatness of each scene category by the total flatness of all images belonging to this category.
► We build the integrated image representation by weighting the pixels gray value description and dense SIFT description.
► We use a hierarchical generative model to learn natural scene categories.