高壓縮影像常常並不只有圖像過小的問題，還包括壓縮失真的問題，例如塊效應(blocking artifact)和震鈴效應(ringing artifact)。所以如果我們直接對這些高壓縮影像做超解析度(super-resolution)，那麼此時將同時放大這些失真，所以只能得到一個很差的結果。但如果我們先去除這些失真的話，我們能得到一張沒有失真的影像，然後再對這張影像做超解析度，但一樣沒有好結果，因為在去除失真的同時我們也會去掉部分圖片細節，這些細節可能包含許多對超解析度有用的訊息。但若先做超解析度再去除失真，由於失真已經被放大強化過，所以很難清乾淨，所以結果影像不是有失真殘留就是為去除失真導致過度平滑。綜上所述，我們發現分開做超解析度和去除失真無法有好的結果，所以我們試著將這兩件事合成一個。
在這篇論文我們提出一個基於自我學習的高壓縮影像之超解析度及去塊技術框架。在我們的方法中首先進行高低分辨率之間關係模型的自我學習，這邊要注意的是我們學習時將資料分成有無塊效應兩種並分開學習模型，然後再利用圖像型態分量分析和稀疏表示來重建影像，並用實驗來證實方法的可行性。

Highly compressed images are usually not only of low-resolution, but also suffer from compression artifacts, e.g., blocking artifacts; ringing artifact. So if we do image super-resolution (SR) to a highly compressed image directly, we will also simultaneously magnify the artifacts, and get unpleasing visual quality. But we find that if we individually performing deblocking followed by SR to an image, it would lose some image details which may be useful for SR when deblocking, and resulting in worse SR result. If we performing SR followed by deblocking, it will magnify the blocking artifacts, and we will hardly to deblocking well for the SR result, so the result will remain blocking artifact or over smooth. In summary of above, we find that we can't get a good result if we individually performing deblocking and SR, so we want to find a method which can combine SR and deblocking in one operation.
In this thesis, we propose a self-learning-based SR framework to simultaneously achieve single-image SR and blocking artifact removal for highly compressed images. In our method, we propose to self-learn image sparse representation for modeling the relationship between low and high-resolution image patches in terms of the learned dictionaries, respectively, for image patches with and without blocking artifacts. As a result, image SR and deblocking can be simultaneously achieved via sparse representation and MCA (morphological component analysis)-based image decomposition. Experimental results demonstrate the efficacy of the proposed algorithm.

Content
摘 要 ii
Abstract iii
Content iv
Chapter 1 Introduction 6
1.1 Research Background 6
1.2 Motivation and Objective 9
1.3 Thesis Organization 11
Chapter 2 Related Work 12
2.1 MCA-based Image Decomposition 12
2.2 Blocking Artifact Detection 13
2.3 Sparse Representation 14
2.4 Dictionary Learning 15
2.5 Image Deblocking 16
Chapter 3 Proposed Method 18
3.1 Dictionary Learning's Pretreatment 19
3.2 Dictionary Learning 20
3.3 Deblocking Method 21
3.4 Reconstruction 24
Chapter 4 Experimental results 26
4.1 Setting 26
4.2 Still Image Result 26
4.3 Video Result 31
4.4 Discussion 35
Chapter 5 Conclusion 40
References 41

[1] S. C. Park et al., “Super-resolution image reconstruction: a technical overview,” IEEE Signal Process. Mag., vol. 20, no. 3, pp. 21-36, 2003.
[2] M. Y. Shen and C. C. J. Kuo, “Review of postprocessing techniques for compression artifacts removal,” J. Vis. Commun. Image Rep., 1998.
[3] S. Farsiu et al., “Fast and robust multiframe super resolution,” IEEE Trans. Image Process., vol. 13, no. 10, pp. 1327-1344, Oct. 2004.
[4] H. S. Hou and H. C. Andrews, “Cubic splines for image interpolation and digital filtering,” IEEE Trans. Signal Process., vol. 26, no. 6, 1978.
[5] W. T. Freeman, T. R. Jones, and E. C. Pasztor, “Example-based super-resolution,” IEEE Computer Graphics and Applications, vol. 22, 2002.
[6] D. Glasner, S. Bagon, and M. Irani, “Super-resolution from a single image,” Proc. IEEE Int. Conf. Comput. Vis., Sept. 2009, pp. 349-356.
[7] G. Freedman and R. Fattal, “Image and video upscaling from local self-examples,” ACM Trans. Graph., vol. 30, no. 2, Article 12, 2011.
[8] J. Yang, J. Wright, T. Huang, and Y. Ma, “Image super-resolution via sparse representation,” IEEE Trans. Image Process., vol. 19, 2010.
[9] J. Yang et al., “Coupled dictionary training for image super-resolution,” IEEE Trans. Image Process., vol. 21, no. 8, pp. 3467-3478, Aug. 2012.
[10] C.-Y. Yang et al., “Exploiting self-similarities for single frame super-resolution,” Proc. Asian Conf. Comput. Vis., 2010.
[11] M.-C. Yang and Y.-C. F. Wang, “A self-learning approach to single image super-resolution,” IEEE Trans. Multimedia, vol. 15, no. 3, 2013.
[12] Z. Xiong, X. Sun, and F. Wu, “Robust web image/video super-resolution,” IEEE Trans. Image Process., vol. 19, no. 8, Aug. 2010.
[13] T. Q. Pham et al., “Resolution enhancement of low quality videos using a high-resolution frame,” Proc. SPIE, vol. 6077, 2006.
[14] F. Liu, J. Wang, S. Zhu, M. Gleicher, and Y. Gong, “Noisy video super-resolution,” Proc. ACM Multimedia, 2008, pp. 713-716.
[15] G. A. Triantafyllidis et al., “Blocking artifact detection and reduction in compressed data,” IEEE Trans. Circuits Syst. Video Technol., 2002.
[16] P. List et al., “Adaptive deblocking filter,” IEEE Trans. Circuits Syst. Video Technol., vol. 13, no. 7, pp. 614−619, July 2003.
[17] Y.-W. Chiou et al., “Efficient image/video deblocking via sparse representation,” Proc. IEEE Visual Commun. Image Process., 2012.
[18] J. M. Fadili et al., “Image decomposition and separation using sparse representations: an overview,” Proc. IEEE, vol. 98, no. 6, June 2010.
[19] L.-W. Kang et al., “Automatic single-image-based rain streaks removal via image decomposition,” IEEE Trans. Image Process., vol. 21, 2012.
[20] K. Dabov et al., “Image denoising by sparse 3D transform-domain collaborative filtering,” IEEE Trans. Image Process., vol. 16, 2007.
[21] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2005.