In this paper, we present a 2.5D* body region classification method based on the global refinement of random forest. The refinement of random forest provides the reduction of the size of training model with preserving prediction accuracy. We also incorporate the field-inspired objective to the random forest in consideration of the pairwise spatial relationships between neighboring data points. Numerical and visual experiments with artificial 3D data confirm the usefulness of the proposed method.
In this paper, we introduce a fast adaptive matting method, where the adaptive matting is carried with a parallelized iterative method, instead of a closed-form solution. As one of its applications, we also incorporate a saliency detection into the adaptive matting, which provides an automated way of extracting salient objects from a bundle of images. This is useful for various problems including object based retrieval, classification and so on. Numerical experiments and visual comparison with the publicly available sample images show the effectiveness of the proposed method.