Entropy Rate Superpixel Segmentation
Abstract: We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters with similar sizes. We present a novel graph construction for images and show that this construction induces a matroid--- a combinatorial structure that generalizes the concept of linear independence in vector spaces. The segmentation is then given by the graph topology that maximizes the objective function under the matroid constraint. By exploiting submodular and monotonic properties of the objective function, we develop an efficient greedy algorithm. Furthermore, we prove an approximation bound of $\frac{1}{2}$ for the optimality of the solution. Extensive experiments on the Berkeley segmentation benchmark show that the proposed algorithm outperforms the state of the art in all the standard evaluation metrics.
Code: We provide an implementation of the entropy rate superpixel segmentation algorithm for the academic community. The code is released as a Matlab wrapper and made compatible to most of the c compilers. To compile the code, simply type make in Matlab console. To see the usage, please check the demo program in the released package.
Version 0.1 : MATLAB Wrapper [ers_matlab_wrapper_v0.1.zip]
This is the implementation used for reporting the performance in the CVPR paper.
Version 0.2.1 : MATLAB Wrapper [ers_matlab_wrapper_v0.2.1.zip]
New features: (1) Superpixel segmentation on RGB image and (2) Support 4-connected image grid structure.
Related Publications
-
Entropy Rate Superpixel Segmentation
Ming-Yu Liu, Oncel Tuzel, Srikumar Ramalingam, and Rama Chellappa
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11) , Colorado Spring, June 2011.
Abstract: We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters with similar sizes. We present a novel graph construction for images and show that this construction induces a matroid--- a combinatorial structure that generalizes the concept of linear independence in vector spaces. The segmentation is then given by the graph topology that maximizes the objective function under the matroid constraint. By exploiting submodular and monotonic properties of the objective function, we develop an efficient greedy algorithm. Furthermore, we prove an approximation bound of $\frac{1}{2}$ for the optimality of the solution. Extensive experiments on the Berkeley segmentation benchmark show that the proposed algorithm outperforms the state of the art in all the standard evaluation metrics.
Code: We provide an implementation of the entropy rate superpixel segmentation algorithm for the academic community. The code is released as a Matlab wrapper and made compatible to most of the c compilers. To compile the code, simply type make in Matlab console. To see the usage, please check the demo program in the released package. Related Publications
Entropy Rate Superpixel Segmentation
Version 0.1 : MATLAB Wrapper [ers_matlab_wrapper_v0.1.zip]
This is the implementation used for reporting the performance in the CVPR paper.
Version 0.2.1 : MATLAB Wrapper [ers_matlab_wrapper_v0.2.1.zip]
New features: (1) Superpixel segmentation on RGB image and (2) Support 4-connected image grid structure.
Ming-Yu Liu, Oncel Tuzel, Srikumar Ramalingam, and Rama Chellappa
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11) , Colorado Spring, June 2011.