影像分割技術在影像處理以及電腦視覺中都是一個重要且具挑戰性的問題，前景分割是影像分割技術中的一種。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，這種技術可以運用到物件偵測或其他電腦視覺的應用當中。近來，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，亦即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。
不同於傳統圖形切割的方法，在這篇論文中我們提出了一個非監督式的影像前景分割方法，以改善圖形切割的便利性。此方法利用了顯著區域標出前景可能所在的位置，以及利用邊界偵測來與顯著區域獲得圖形切割所需的閾值，將影像分割成前景和背景。我們所提出的方法不僅不需要使用者的介入，根據我們的實驗結果，相較於其他基於顯著區域的圖形切割，結果也相當不錯。

Image segmentation is an essential and challenging problem in computer vision and image processing. Figure-ground segmentation is one of image segmentation that separate image into two labels, which are foreground and background. It can be used in object detection or many other applications. Recently, a lot of methods have been proposed for solving figure-ground segmentation problems. However, most of them are supervised approaches. In other words, the procedures of those methods need some interactions of users. It makes those methods unfavorable. Also, there are some disadvantage in traditional unsupervised image segmentation methods.
We proposed an unsupervised figure-ground approach. It uses the saliency detection method to indicate the position of the foreground, and use the boundary detection method to obtain a suitable threshold for image segmentation automatically. According to our experiment results, our method does not need user interaction and performs well compared with the previous saliency-based segmentation method for segmentation of iCoseg dataset and MSRA-1000 dataset.

[1] Viet-Quoc Pham, Takahashi, K., Naemura, T. "Bounding-Box Based Segmentation with Single Min-cut Using Distant Pixel Similarity" Pattern Recognition (ICPR), 2010 20th International Conference on, Page 4420 – 4423, 2010
[2] Grady, L. “Random Walks for Image Segmentation” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 28, Issue: 11), Page 1768 – 1783, Nov. 2006
[3] Wenxian Yang, Jianfei Cai, Jianmin Zheng, Jiebo Luo “User-Friendly Interactive Image Segmentation Through Unified Combinatorial User Inputs” Image Processing, IEEE Transactions on (Volume: 19, Issue: 9), Page 2470 – 2479, Sept. 2010
[4] Jieyu Zhao, Xiaowei Geng “Interactive image segmentation via multi-cue dynamic integration” Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on, Page 3044 – 3047, 2008
[5] Lempitsky, V., Kohli, P., Rother, C., Sharp, T. ”Image segmentation with a bounding box prior.” Computer Vision, 2009 IEEE 12th International Conference on, Page 277 – 284, 2009
[6] Meng Tang, Gorelick, L., Veksler, O., Boykov, Y. “GrabCut in One Cut” Computer Vision (ICCV), 2013 IEEE International Conference on, Page 1769 – 1776, 2013
[7] Comaniciu, D., Meer, P. “Mean shift: a robust approach toward feature space Analysis” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 24, Issue: 5), Page 603 – 619, May 2002
[8] Cheng, Yizong “Mean shift, mode seeking, and clustering” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 17, Issue: 8), Page 790 – 799, Aug 1995
[9] Soo-Chang Pei, Jian-Jiun Ding “The generalized radial Hilbert transform and its applications to 2-D edge detection” Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on (Volume: 3), Page III - 357-60 vol.3, 2003
[10] Vincent, L., Soille, P. “Watersheds in digital spaces: an efficient algorithm based on immersion simulations” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 13, Issue: 6), Page 583 – 598, Jun 1991
[11] Achanta, R., Hemami, S., Estrada, F., Susstrunk, S. “Frequency-tuned Salient Region Detection” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, Page 1597 – 1604, 2009
[12] Qingshan Li, Yue Zhou, Jie Yang “Saliency based Image Segmentation” Multimedia Technology (ICMT), 2011 International Conference on, Page 5068 – 5071, 2011
[13] Chanho Jung, Changick Kim “A Unified Spectral-Domain Approach for Saliency Detection and Its Application to Automatic Object Segmentation” Image Processing, IEEE Transactions on (Volume: 21, Issue: 3), Page 1272 – 1283, Aug 2011
[14] Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang “Saliency Detection via Graph-Based Manifold Ranking” Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, Page 3166 – 3173, 2013
[15] Dollar, P., Zitnick, C.L. “Structured Forests for Fast Edge Detection” Computer Vision (ICCV), 2013 IEEE International Conference on, Page 1841 – 1848, 2013
[16] Itti, L., Koch, C., Niebur, E. “A model of saliency-based visual attention for rapid scene analysis” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 20, Issue: 11), Page 1254 – 1259, Nov 1998
[17] Perazzi, F., Krahenbuhl, P., Pritch, Y., Hornung, A. ”Contrast based filtering for salient region detection Saliency filters” Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, Page 733 – 740, 2012
[18] Yulin Xie, Huchuan Lu, Ming-Hsuan Yang “Geodesic saliency using background priors” Image Processing, IEEE Transactions on (Volume: 22, Issue: 5), Page 1689 – 1698, Aug 2012
[19] Yining Deng, Manjunath, B.S. “Unsupervised Segmentation of Color-Texture Regions in Images and Video” Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume: 23, Issue: 8), Page 800 – 810, Aug 2001
[20] Yining Deng, Kenney, C., Moore, M.S., Manjunath, B.S. “Peer group filtering and perceptual color image quantization” Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on (Volume: 4), Page 21 - 24 vol.4, Jul 1999
[21] Lim, J.J., Zitnick, C.L., Dollar, P. “Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection” Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, Page 3158 – 3165, 2013