Interactive image segmentation based on the appearance model and orientation energy

Tang et al. (2013) proposed a graph-based image segmentation model by minimizing the distance between the object and background appearance overlap models. This model is very effective for interactive image segmentation. However, it is prone to isolated nodes when the colors or other appearances characteristic of the object and background are very similar. To improve the performance of this algorithm and related algorithms, we add new spatial distance and contour orientation energy terms to the energy function. Accordingly, we modify the construction of the energy graph. We add terminal nodes S and T and add prior constraints. Finally, we use the pseudoflow algorithm proposed by Hochbaum to calculate the maximum flow of the new energy graph. A large number of experiments on the MSRA dataset, BSD dataset and GrabCut dataset show that the results of the proposed method are better than those of many recently proposed image segmentation methods. The code is available at https://github.com/powerhope/AMOE.

Automated summary

The paper proposes a graph-based image segmentation model and improves its performance by adding spatial distance and contour orientation energy terms and modifying the construction of the energy graph. Experimental results show that the proposed method outperforms many other methods on multiple datasets.