Visual object categorization based on the fusion of region and local features

This paper presents a novel approach for visual object categorization using region based features and statistical measures based image modeling. Our region-based features are extracted from coarse regions obtained by the Gestalt theory inspired region segmentation algorithm and they capture visually significant information such as segments and colors. The modeling of the visual content of an image relies upon some statistical measures over sparse region-based features, thus avoiding the major difficulty of the popular “bag-of-local features” approach which needs to fix a visual vocabulary size. Several classification schemes, including feature selection techniques (e.g. PCA or Adaboost) and fusion strategies, are also implemented and compared. Experimented on a subset of Pascal VOC dataset, we show that by separating features extracted from different sources in different “channels”, and then to combine them using an early fusion, we can actually improve classification performance. Moreover, experimental results demonstrate that our region-based features can be combined with SIFT features to reinforce performance, suggesting that our features managed to extract information which is complementary to the one of SIFT features.