臺灣博碩士論文加值系統

影像切割(image segmentation)問題的目標通常是把一張輸入影像切割成許多不同的區域。大致上而言，影像切割的問題通常可視為標籤決定問題並且根據每一個像素的特徵標示不同的標籤。在此篇論文中，我們會提出一個監督式和互動式的影像切割演算法。
在我們的方法中，我們建構一個由超向素(superpixel)層與高階層所組成的圖解模型。超像素層是由過度切割區域的區域稱為超像素所組成的，高階層則是由邊緣偵測的結果與過度切割的區域所構成的。接下來我們使用建構的圖解模型並且使用隨機漫步演算法來找出每個超像素最大機率的標籤值。我們所提出的方法在自然影像中跟其他常見方法比較下有非常滿意的結果。

The purpose of image segmentation problem is to separate some areas from the input image. In general, image segmentation can be consider as a label decision problem which assign different labels to every pixel according to its features. In this paper, we propose a supervised and interactive image segmentation algorithm.
In our approach, we construct a new graph model which consists of a super-pixel layer and a high order layer. The super-pixel layer is composed by over-segmentation regions called superpixels and the high-order layer is generated by combining edge detection and these over-segmentation regions. Then we construct a graph model and use a random walk algorithm to find the maximum probability label value for each superpixel. The proposed method shows very satisfactory results for some natural images and compares to some conventional methods.

Chapter 1 Introduction
Chapter 2 Related work
Chapter 3 Proposed Method
3.1 The super-pixel layer
3.2 The high-order layer
3.3 Construct Graph
3.4 The Random walker based on superpixels
Experiment
Conclusion
Reference

[1] Tae Hoon Kim; Kyoung Mu Lee ; Sang Uk Lee. “Nonparametric Higher-Order Learning for Interactive Segmentation.” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference , pp. 3201 – 3208 , 2010 June 13-18.
[2] Tae Hoon Kim ; Kyoung Mu Lee ; Sang Uk Lee . “Generative Image Segmentation Using Random Walks with Restart.” In European Conference on Computer Vision , 2008 October.
[3] Achanta, R. ; Shaji, A.; Smith, K.; Lucchi, A. ; Fua, P. ; Süsstrunk, S. “SLIC Superpixels Compared to State-of-the-art Superpixel Methods.” In Pattern Analysis and Machine Intelligence, IEEE Transactions, pp. 2274 – 2282 ,2012 April.
[4] Dollar, P. ; Zitnick, C.L. “Structured Forests for Fast Edge Detection” In Computer Vision (ICCV), 2013 IEEE International Conference pp. 1841 – 1848 2013 December.
[5] Comaniciu, D. ; Meer, P. “Mean Shift: A Robust Approach Toward Feature Space Analysis” Pattern Analysis and Machine Intelligence, IEEE Transactions , pp. 603 – 619 2002 May.
[6] Kanungo, Tapas ; Mount, D.M. ; Netanyahu, N.S. ; Piatko, C.D. ; Silverman, R. ; Wu, A.Y.” An Efficient k-Means Clustering Algorithm:Analysis and Implementation” In Pattern Analysis and Machine Intelligence, IEEE Transactions , pp. 881 – 892 2002 July.
[7] Chuan Yang ; Lihe Zhang ; Huchuan Lu ; Xiang Ruan ; Ming-Hsuan Yang “Saliency Detection via Graph-Based Manifold Ranking” In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference , pp. 3166 – 3173 ,2013 June.
[8] Boykov, Y. ; Veksler, O. ; Zabih, R.” Fast Approximate Energy Minimization via Graph Cuts” In Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference , pp. 377 – 384 ,1999 September.
[9] Grady, L. ” Random Walks for Image Segmentation” In Pattern Analysis and Machine Intelligence, IEEE Transactions pp. 1768 – 1783 ,2006 September.
[10] Kass, M., Witkin, A., Terzopoulos, D. “Snakes: Active contour models.” In Internation Journal of Computer Vision, V1 pp.321-331 ,1988.
[11] Mortensen, E.N., Barrett, W.A.: “Interactive segmentation with intelligent scissors.” Graphical Models in Image Process. 60(5), 349–384 (1998)
[12] Levinshtein, A., Stere, A. ; Kutulakos, K.N. ; Fleet, D.J. ; Dickinson, S.J. ; Siddiqi, K.”TurboPixels: Fast Superpixels Using Geometric Flows.” In Pattern Analysis and Machine Intelligence, IEEE Transactions pp. 2290 – 2297, 2009 March.