Discrete Potts Model for Generating Superpixels on Noisy Images

Many computer vision applications, such as object recognition and segmentation, increasingly build on superpixels. However, there have been so far few superpixel algorithms that systematically deal with noisy images. We propose to first decompose the image into equal-sized rectangular patches, which also sets the maximum superpixel size. Within each patch, a Potts model for simultaneous segmentation and denoising is applied, that guarantees connected and non-overlapping superpixels and also produces a denoised image. The corresponding optimization problem is formulated as a mixed integer linear program (MILP), and solved by a commercial solver. Extensive experiments on the BSDS500 dataset images with noises are compared with other state-of-the-art superpixel methods. Our method achieves the best result in terms of a combined score (OP) composed of the under-segmentation error, boundary recall and compactness.