摘要
影像分割技術在影像處理以及電腦視覺相關領域中都是一個重要且具挑戰性的
問題。近年來，在多種不同類型的影像分割方法中，前景分割一直是一個被重點研究的題目。前景物件分割的目標是將一張圖片分成前景及背景兩個部份，目前已經有不少關於前景分割的研究，但是，這些研究通常是屬於監督式的方法，也就是此種方法需要使用者的一些互動才能得出結果，使得便利性不盡理想，而傳統的非監督式影像前景分割方法通常存在一些缺點。
在這篇論文中我們提出了一種基於建議區塊(Object proposal)與顯著性偵測(Saliency detection)的非監督式前景分割方法。 我們提出的方法利用了
建議區塊與顯著性、色彩、梯度等資訊建構了一個目標函式,並在我們的目標
函式中設計了一個用於處理圖片中有多個前景物體的限制項(Constraint)，
接著再藉由簡單的優化方法得到初始的分割結果，然後再將初始的分割結果
用基於像素的圖形分割方法作優化來得到最後的分割結果。

根據我們的實驗結果，我們所提出的方法不僅不需要使用者提供任何額外資訊，相較於其他基於顯著性取閥值與利用顯著性的圖形分割演算法，我們的方法在 MSRA-1000 資料庫上都能得到不錯甚至更好的結果。

In recent years, figure-ground segmentation has been a popular research topic in a number of different types of image segmentation methods. The goal of the figure-ground segmentation is to divide an image into two regions, which are foreground and background. There are many methods which have been proposed for solving figure-ground segmentation problems, but these methods are usually supervised approaches. In other words, the procedures of those methods need some interactions of users. It makes those methods unfavorable. Also, there are some disadvantages in traditional unsupervised image segmentation methods. In this thesis, we propose an unsupervised figure-ground segmentation method based on an object proposal generation algorithm to generate a small number of regions in an image, such that each object is well-represented by at least one region. Then, we combine the saliency map which measures the saliency likelihood of the image, color information, and gradient information to construct an objective function for the situation that only single foreground object exists in an image. Otherwise, the objective function is combined with an overlap constraint to handle the situation that multiple foreground objects appear in an image. Then we use a simple and efficient optimization method to get the initial object-wise segmentation results, and then refine the results by using pixel-wise graph cut. Comparing to other unsupervised figure-ground segmentation approaches, our method in MSRA-1000 database can get good experimental results.

References
[1] I. Endres and D. Hoiem. “Category-independent object proposals with diverse ranking.” In TPAMI, pp. 222–234, 2014.
[2] Chuan.Y, Lihe.Z, Huchuan.L, Xiang.R and Ming-Hsuan.Y “Saliency Detection via Graph-Based Manifold Ranking.” In CVPR, pp.3166 – 3173, 2013.
[3] P. Arbel´aez, J. Pont-Tuset, J. Barron, F. Marques, and J. Malik. “Multiscale combinatorial grouping.” In CVPR, pp. 328–335, 2014
[4] W. Brendel and S. Todorovic. Segmentation as maximum weight independent set. In NIPS, 2010.
[5] N. Dalal and B. Triggs. “Histograms of oriented gradients for human detection.” In CVPR, pp. 886–893, 2005.
[6] Dong.Z, Omar.J and Mubarak.S “Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions.” In CVPR, pp. 815–872, 2013.
[7] T. Ma and L. Latecki. “Maximum weight cliques with mutex constraints for video object segmentation.” In CVPR, pp. 670–677, 2012.
[8] L.Y.Husah and L.W.Chang. “Unsupervised Figure-ground Segmentation using Saliency Detection and Boundary Detection.”, pp. 16-26, 2014.
[9] R. Achanta, S.Hemami, F.Estrada and S.Susstrunk. “Frequency-tuned Salient Region Detection.” In CVPR, pp. 1597 – 1604, 2009.
[10] N. Dalal and B. Triggs. “Histograms of oriented gradients for human detection.” In CVPR, pp 886–893, 2005.
[11] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, “Contour detection and hierarchical image segmentation.” In PAMI, pp. 898–916, 2011.
[12] Huaizu Jiang Jingdong Wang Zejian Yuan “Automatic Salient Object Segmentation Based on Context and Shape Prior.” In BMVC, 2011.
[13] B. Fulkerson, A. Vedaldi, and S. Soatto. “Class segmentation and object localization with superpixel neighborhoods.” In ICCV, pp. 670–677, 2013.
[14] D. Hoiem, A. A. Efros, and M. Hebert, “Geometric context from a single image,” In ICCV, pp. 350–377, 2005.
[15] J. Carreira and C. Sminchisescu. “CPMC: Automatic object segmentation using constrained parametric min-cuts.” In TPAMI, pp.1312–1328, 2012.
[16] C. Rother, V. Kolmogorov, and A. Blake. “Grabcut: Interactive foreground extraction using iterated graph cuts.” In ACM Transactions on Graphics, pp. 309–314, 2004.
[17] H.Fu, D.Xu, S.Lin and J.Liu. “Object-based RGBD Image Co-segmentation with Mutex Constraint.” In CVPR, pp. 4428-4436, 2015.
[18] I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, “Large margin methods for structured and interdependent output variables.” In Journal of Machine Learning Research, pp. 1453–1484, 2005,