影像共分割在影像處理領域中是一種較新的分支，其目的是在一組輸入影像群組中，辨識並切割出相同或相似的物件。過去的研究大多數是以分割出二種類別為目標，也就是分割出一個共同物件，一般稱為前景，以及剩餘的背景，在這種前提下所提出的共分割方法無可避免地會受到一些限制。
本篇論文提出了運用聯盟式合作賽局的概念，來達成分割出多個類別的方法。聯盟式合作賽局代表在一個賽局裡，玩家可以組成聯盟以產生共同報酬。在我們提出的方法中，首先將影像分割為多個較小的區塊，並將這些區塊視為玩家，區塊們擁有與其他區塊結合的能力，相當於組成聯盟，聯盟的報酬即是他們相對於類別模型的分數。接著以聯盟合作賽局中的 Shapley Value 概念將報酬分配給各個聯盟成員，以決定這些區域該分配給何種類別模型來達到總體最佳分割，再利用這些分配結果訓練新的類別模型，如此將區塊分配與訓練模型迭代進行來獲得較高的分割準確率，達到最終的共分割結果。

Image co-segmentation is a relatively new branch of image processing. The goal of image co-segmentation is to separate common objects or similar objects among input image sets. Most existing co-segmentation approaches focus on two-class segmentation,. It means they aim for separating only one common object of a class, usually called foreground, and the remaining background in each of input images. From this binary labeling premise those methods inevitably suffer from some limitations.
In this thesis, we propose a multi-class co-segmentation method which is in favor of coalition game theory. A game which is in a coalition form means that some players in the game can form an alliance to have a joint payoff. Our approach first over-segments input images and treat each region (superpixel) as a player; each region has the ability to ally with others regions to form a coalition. The payoffs of coalitions are determined by the scores of each class model. Therefore, we can take advantage of Shapley values to determine how the payoffs are being distributed among all coalition members. After assigning each region to one of the classes according to their scores, we can achieve the best segmentation result. Therefore, new class models can be trained by using previous region assignment. Performing those region assignment and model training iteratively, we can acquire better co-segmentation.

[1] C. Rother, T. Minka, A. Blake, and V. Kolmogorov. Cosegmentation of Image Pairs by Histogram Matching Incorporating a Global Constraint into MRFs. CVPR, pp. 993 – 1000, 2006.
[2] C. Rother, V. Kolmogorov, and A. Blake. Grabcut – interactive foreground extraction using iterated graph cuts. In SIGGRAPH, 2004.
[3] S. Vicente, V. Kolmogorov, C. Rother. Cosegmentation Revisited: Models and Optinization. ECCV, pp. 465-479, 2010.
[4] Y.Y. Boykov, and M.P. Jolly. Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D images. ICCV, pp. 105-112, 2001.
[5] Y. Boykov and V. Kolmogorov. An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEEE PAMI, vol. 26, no. 9, pp. 1124-1137, 2004.
[6] A. Joulin, F. Bach, and J. Ponce. Discriminative Clustering for Image co-segmentation. CVPR, pp. 1943 – 1950, 2010.
[7] A. Joulin, F. Bach, and J. Ponce. Multi-Class Cosegmentation. CVPR, pp. 542 - 549, 2012.
[8] G. Kim, E. P. Xing, L. Fei-Fei, and T. Kanade, Distributed Cosegmentation via Submodular Optimization on Anisotropic Diffusion, 13th International Conference on Computer Vision. (ICCV 2011), Spain, 2011.
[9] D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen. iCoseg: Interactive Co-segmentation with Intelligent Scribble Guidance. CVPR, pp. 3169 – 3176, 2010.
[10] D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen. Interactively co-segmentating topically related images with intelligent scribble guidance. International Journal of Computer Vision, Volume 93, Issue 3, pp 273-292 2011.
[11] J. Weickert. Anisotropic Diffusion in Image Processing. ECMI Series, Teubner-Verlag, 1998.
[12] S. Jegelka and J. Bilmes. Submodularity beyond submodular energies: coupling edges in graph cuts. CVPR, pp. 1897 – 1904, 2011.
[13] S. Vicente, V. Kolmogorov, and C. Rother. Graph cut based image segmentation with connectivity priors. CVPR, pp. 1 – 8, 2008.
[14] D. Freedman and P. Drineas. Energy minimization via graph cuts: Settling what is possible. CVPR, vol. 2, pp. 939 - 946, 2005.
[15] A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, and K. Siddiqi. TurboPixels: Fast Superpixels Using Geometric Flows. IEEE PAMI, 31(12):2290–2297, 2009.
[16] G. Kim, E. P. Xing. On Multiple Foreground Cosegmentation. CVPR, pp. 837 – 844, 2012.
[17] T. Sandholm, S. Suri, A. Gilpin, and D. Levine. CABOB: A Fast Optimal Algorithm for Winner Determination in Combinatorial Auctions. Manage. Sci., 51:374–390, 2005.
[18] Lloyd S. Shapley. A Value for n-person Games. In Contributions to the Theory of Games, volume II, by H.W. Kuhn and A.W. Tucker, editors. Annals of Mathematical Studies v. 28, pp. 307–317. Princeton University Press, 1953.
[19] S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Prentice Hall, 2009.
[20] P. Cramton, Y. Shoham, and R. Steinberg. Combinatorial Auctions. The MIT Press, 2005.
[21] S. Lazebnik, C. Schmid, and J. Ponce. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. CVPR, pp. 2169-2178, 2006.
[22] P. Cramton, Y. Shoham, and R. Steinberg. Combinatorial Auctions. The MIT Press, 2005.