臺灣博碩士論文加值系統

我們發展了一個基於學習理論之合成超解度影像系統，讓我們可以由單張低解析影像合成出較高解析度的影像。整個系統分成兩個部分，分別是事先的訓練程序以及合成程序。為了合成出同時包含整體影像架構及細部高頻細節的人臉影像，我們引入了多重解析度之小波合成。在訓練程序中，每一層解析度下的低解析度影像都會被切成許多小區塊，進而由這些小區塊形成的集合建立出相對應的特徵空間(eigenspace)，以減少在相似度比對所需花費的時間。而在合成程序中，我們視這些區塊為一馬可夫網路(Markov network)，並利用最大後驗概率(maximum a posteriori (MAP) )從已建立好的資料庫裡找出最合適的區塊。實驗結果顯示，我們能合成出比由雙立方內插法(bi-cubic interpolation)得到的影像更好的結果。

A learning-based super-resolution system consisting of training and synthesis processes is presented. In the proposed system, a multi-resolution wavelet approach is applied to carry out the robust synthesis of both the global geometric structure and the local high-frequency detailed features of a facial image. In the training process, the input image is transformed into a series of images of increasingly lower resolution using the Haar discrete wavelet transform (DWT). The images at each resolution level are divided into patches, which are then projected onto an eigenspace to derive the corresponding projection weight vectors. In the synthesis process, a low-resolution input image is divided into patches, which are then projected onto the same eigenspace as that used in the training process. Modeling the resulting projection weight vectors as a Markov network, the maximum a posteriori (MAP) estimation approach is then applied to identity the best-matching patches with which to reconstruct the image at a higher level of resolution. The experimental results demonstrate that the proposed reconstruction system yields better results than the bi-cubic spline interpolation method.

Chapter 1. Introduction....................10
1.1. Motivation............................10
1.2. Related Works .........................10
Chapter 2. System Description.............13
Chapter 3. Training Process...............17
3.1. Feature Extraction Using Multi-Resolution Wavelet Analysis ..................................19
3.2. Patch-Based Eigenspace Construction...20
Chapter 4. Synthesis Process..............22
4.1. Wavelets Synthesis and Patch-Based Weight Vector Creation...................................24
4.2. Markov Network: Best Matching Using Maximum a Posterior Approach .........................25
Chapter 5. Experimental Results 29
Chapter 6. Conclusions 34
References 36

[1]S. Baker and T. Kanade, “Hallucinating Faces,” Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 83-88, 2000.
[2]S. Baker and T. Kanade, “Limits on Super-Resolution and How to Break Them,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, pp. 1167-1183, 2002.
[3]J. Besag, “Spatial Interaction and The Statistical Analysis of Lattice Systems,” J. Royal Statist. Soc. B, Vol. 36, pp. 192-326, 1974.
[4]C.M. Bishop, Neural Networks for Pattern Recognition, Oxford, 1995.
[5]R. Chan, T. Chan, L. Shen and Z. Shen, “Wavelet Algorithms for High-Resolution Image Reconstruction,” SIAM Journal on Scientific Computing, Vol. 24, No. 4, pp. 1408-1432, 2003.
[6]G. Chen and R. J. P. deFigueiredo, “A Unified Approach to Optimal Image Interpolation Problems Based on Linear Partial Differential Equation Models,” IEEE Transactions Image Processing, Vol. 2, No. 1, pp. 41-49, 1993.
[7]R. Chan, S. Riemenschneider, L. Shen and Z. Shen, “Tight Frame: An Efficient Way for High-Resolution Image Reconstruction,” Applied and Computational Harmonic Analysis, Vol. 17, pp. 91-115, 2004.
[8]S. Farsiu, D. Robinson, M. Elad and P. Milanfar, “Fast and Robust Multi-Frame Super-Resolution,” IEEE Trans. Image Processing, Vol. 13, No. 10, pp. 1327-1344, 2004.
[9]M. Elad and A. Feuer, “Super-resolution Reconstruction of Image Sequences,“ IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 9, pp. 817-834, 1999.
[10]C. Ford and D. Etter, “Wavelet Basis Reconstruction of Nonuniformly Sampled Data,” IEEE Transaction Circuits and Systems II, Vol. 45, No. 8, pp.1165-1168, 1998.
[11]W.T. Freeman, T.R. Jones and E.C. Pasztor, “Example-Based Super-Resolution,” IEEE Computer Graphics and Applications, Vol. 22, No. 2, pp. 56-65, 2002.
[12]W.T. Freeman, E.C. Pasztor and O.T. Carmichael, “Learning Low-Level Vision,” International Journal of Computer Vision, Vol. 40, No. 1, pp. 25-47, 2000.
[13]D. Geiger and F. Girosi, “Parallel and Deterministic Algorithms from MRF’s: Surface Reconstruction,” IEEE Pattern Analysis and Machine Intelligence, Vol. 13, No. 5, pp. 401-412, 1991.
[14]S. Geman and D. Geman, “Stochastic Relaxation, Gibbs Distribution, and The Bayesian Restoration of Images,” IEEE Pattern Analysis and Machine Intelligence, Vol. 6, pp. 721-741, 1984.
[15]A. Haar, “Zur theorie der Orhtogonalen Funktionensysteme,” Math. Annal., Vol. 69, pp. 331-371, 1910.
[16]H.S. Hou, and H.C. Andrew, “Least Squares Image Restoration Using Spline Basis Function,” IEEE Transactions on Computers, Vol. C-26, No. 9, pp. 856-873, 1977.
[17]H.S. Hou and H.C. Andrews, “Cubic Splines for Image Interpolation and Digital Filtring,” IEEE Transactions Acoust, Speech Signal Processing, Vol. 26, No. 6, pp. 508-517, 1978.
[18]W. Liu, D. Lin and X. Tang, “Face hallucination through dual associative learning,” Proceedings of IEEE International Conference on Image Processing, Vol. 1, pp. 873-876, 2005.
[19]C. Liu, H. Shum and C. Zhang, “A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model,” CVPR, Vol. 1, pp. 192-198, 2001.
[20]K.P. Murphy, “An Introduction to Graphical Models,” Intel Research Technical Report, 2001.
[21]N. Nguyen and P. Milanfar, “A Wavelet-Based Interpolation-Restoration Method for Superresolution,” Circuits, System, Signal Processing, Vol. 19, pp. 321-338, 2000.
[22]J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, 1988.
[23]W.K. Pratt, Digital Image Processing, Wiley, New York, 1991.
[24]R.R. Schultz and R.L. Stevenson, “Extraction of High-Resolution Frames from Video Sequences,” IEEE Transactions on Image Processing, Vol. 5, No. 6, pp. 996-1011, 1996.
[25]H. Shekarforoush and R. Chellappa, “Data-Driven Multi-Channel Super-Resolution with Application to Video Sequences,” Journal of the Optical Society of America A, Vol. 16, pp. 481-492, 1999.
[26]L. Shen and Q. Sun, “Bi-orthogonal wavelet system for high-resolution image reconstruction,” IEEE Transactions Signal Process, submitted for publication, 2003.
[27]A.M. Tekalp, M.K. Ozkan and M.I. Sezan, “High-resolution Image Reconstruction from Lower-resolution Image Sequences and Space-varying Image Restoration,” in Proceedings of the IEEE International Conference on Acousics, Speech and Signal Processing (ICASSP), Vol.3, pp. 169-172, 1992.
[28]R. Tsai and T. Huang, “Multiframe image restoration and registration,” Advances in Computer Vision and Image Processing, Vol.1, pp. 317-339, 1984.
[29]M. Unser, A. Aldroubi and M. Eden, “Enlargement or Reduction of Digital Image with Minimum Loss of Information,” IEEE Transactions Image Processing, Vol. 4, pp. 247-258, 1995.