Building Regionally Spatial Appearance Model by Topological Color Histogram

Color histogram is widely used in the appearance modeling. However the lack of spatial information makes the features less distinctive. In this paper, we propose to detect local region relationship based on segmentation in the color space. After efficiently computing the region's spatial information, a novel topological color histograms is used to represent the spatial context. Through the experimental observation, we find the region based spatial appearance model make the object's feature more discriminative.