Topological Voting Method for Image Segmentation

Image segmentation is one of the main problems in image processing. In order to improve the accuracy of segmentation, one often creates a number of masks (annotations) for a same image and then uses some voting methods on these masks to obtain a more accurate mask. In this paper, we propose a voting method whose voting rule is not pixel-wise but takes into account the natural geometric-topological properties of the masks. On three concrete examples, we show that our voting method outperforms the usual arithmetical voting method.