10.1109/TCSVT.2015.2430631, IEEE Transactions on Circuits and Systems for Video Technology JOURNAL OF LATEX CLASS FILES 1 Superpixel Optimization using Higher-Order Energy

Abstract—A novel superpixel extraction algorithm using a higher-order energy optimization framework is proposed in this paper. We first adopt the k-means clustering technique to quickly get an initial superpixel result. Then a higher-order energy function is employed to optimize and refine these initial superpixels. We use a more general higher-order energy function which includes a first-order data term, a second-order smoothness term and a higher-order term. The pre-segments are employed to provide the prior information of sufficient edges and segment regions for our higher-order energy term. According to the texture measurement in different local regions, our algorithm adaptively computes the proper ratios of different energy terms to obtain a better superpixel performance. The experimental results demonstrate that our method using the higher-order energy generates better results with well-aligned boundaries and homogeneous effects than the existing superpixel algorithms. Index Terms—Superpixel, higher-order energy, optimization. I