Zhang Wei. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 73-78). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.ii / List of Figures --- p.viii / List of Tables --- p.ix / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Previous work --- p.2 / Chapter 1.1.1 --- Learning-based approaches --- p.3 / Chapter 1.1.2 --- Feature-based approaches --- p.7 / Chapter 1.2 --- Thesis objective --- p.12 / Chapter 1.3 --- The proposed detector --- p.13 / Chapter 1.4 --- Thesis outline --- p.14 / Chapter 2 --- The Edge Merging Algorithm --- p.16 / Chapter 2.1 --- Edge detection --- p.16 / Chapter 2.2 --- Edge breaking --- p.18 / Chapter 2.2.1 --- Cross detection --- p.20 / Chapter 2.2.2 --- Corner detection --- p.20 / Chapter 2.3 --- Curve merging --- p.23 / Chapter 2.3.1 --- The search region --- p.25 / Chapter 2.3.2 --- The merging cost function --- p.27 / Chapter 2.4 --- Ellipse fitting --- p.30 / Chapter 2.5 --- Discussion --- p.33 / Chapter 3 --- The Face Verifier --- p.35 / Chapter 3.1 --- The face box --- p.35 / Chapter 3.1.1 --- Face box localization --- p.36 / Chapter 3.1.2 --- Conditioning the face box --- p.42 / Chapter 3.2 --- Eye-mouth triangle search --- p.45 / Chapter 3.3 --- Face model matching --- p.48 / Chapter 3.3.1 --- Face model construction --- p.48 / Chapter 3.3.2 --- Confidence of detection --- p.51 / Chapter 3.4 --- Dealing with overlapped detections --- p.51 / Chapter 3.5 --- Discussion --- p.53 / Chapter 4 --- Experiments --- p.55 / Chapter 4.1 --- The test sets --- p.55 / Chapter 4.2 --- Experimental results --- p.56 / Chapter 4.2.1 --- The ROC curves --- p.56 / Chapter 4.3 --- Discussions --- p.61 / Chapter 5 --- Conclusions --- p.69 / Chapter 5.1 --- Conclusions --- p.69 / Chapter 5.2 --- Suggestions for future work --- p.70 / List of Original Contributions --- p.72 / Bibliography --- p.73

by Wong Yin Shung. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 62-64). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.7 / Chapter 2 --- Fundamentals --- p.9 / Chapter 2.1 --- Representation of a digital image --- p.9 / Chapter 2.2 --- Salt-and-pepper --- p.10 / Chapter 2.3 --- Resolution of a gray digital image --- p.11 / Chapter 3 --- Filters --- p.14 / Chapter 3.1 --- Median filter --- p.15 / Chapter 3.2 --- Adaptive median filter --- p.15 / Chapter 3.3 --- Multi-state median filter --- p.16 / Chapter 3.4 --- Directional difference-based switching median filter --- p.18 / Chapter 3.5 --- Improved switching median filters --- p.20 / Chapter 3.6 --- Variational method --- p.21 / Chapter 3.7 --- Two-phase method --- p.22 / Chapter 4 --- New Two Phase Methods --- p.25 / Chapter 4.1 --- Triangule-based interpolation --- p.25 / Chapter 4.1.1 --- Delaunay triangulation --- p.26 / Chapter 4.1.2 --- Linear interpolation --- p.28 / Chapter 4.1.3 --- Cubic interpolation --- p.29 / Chapter 4.2 --- Gradient estimation --- p.32 / Chapter 4.3 --- Regularization method --- p.33 / Chapter 4.3.1 --- Least square method with Laplacian regularization --- p.33 / Chapter 4.3.2 --- Lagrange multipliers --- p.35 / Chapter 4.4 --- Fast transform for finding the inverse of Laplacian matrix --- p.38 / Chapter 5 --- Inpainting and Zooming --- p.39 / Chapter 5.1 --- Inpainting --- p.39 / Chapter 5.2 --- Zooming --- p.40 / Chapter 5.2.1 --- Bilinear interpolation --- p.40 / Chapter 5.2.2 --- Bicubic interpolation --- p.41 / Chapter 6 --- Results --- p.46 / Chapter 6.1 --- Results of denoising --- p.47 / Chapter 6.2 --- Results of inpainting --- p.47 / Chapter 6.3 --- Results of zooming --- p.48 / Chapter 6.4 --- Conclusions --- p.51

Chan Chi Hang. / Thesis submitted in: August 2004. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 105-114). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Problem Statement --- p.3 / Chapter 1.2 --- Major Contributions --- p.5 / Chapter 1.3 --- Publication List --- p.6 / Chapter 1.4 --- Thesis Organization --- p.7 / Chapter 2 --- Background Survey --- p.9 / Chapter 2.1 --- Relevance Feedback Framework --- p.9 / Chapter 2.1.1 --- Relevance Feedback Types --- p.11 / Chapter 2.1.2 --- Data Distribution --- p.12 / Chapter 2.1.3 --- Training Set Size --- p.14 / Chapter 2.1.4 --- Inter-Query Learning and Intra-Query Learning --- p.15 / Chapter 2.2 --- History of Relevance Feedback Techniques --- p.16 / Chapter 2.3 --- Relevance Feedback Approaches --- p.19 / Chapter 2.3.1 --- Vector Space Model --- p.19 / Chapter 2.3.2 --- Ad-hoc Re-weighting --- p.26 / Chapter 2.3.3 --- Distance Optimization Approach --- p.29 / Chapter 2.3.4 --- Probabilistic Model --- p.33 / Chapter 2.3.5 --- Bayesian Approach --- p.39 / Chapter 2.3.6 --- Density Estimation Approach --- p.42 / Chapter 2.3.7 --- Support Vector Machine --- p.48 / Chapter 2.4 --- Presentation Set Selection --- p.52 / Chapter 2.4.1 --- Most-probable strategy --- p.52 / Chapter 2.4.2 --- Most-informative strategy --- p.52 / Chapter 3 --- Biased Support Vector Machine for Content-Based Image Retrieval --- p.57 / Chapter 3.1 --- Motivation --- p.57 / Chapter 3.2 --- Background --- p.58 / Chapter 3.2.1 --- Regular Support Vector Machine --- p.59 / Chapter 3.2.2 --- One-class Support Vector Machine --- p.61 / Chapter 3.3 --- Biased Support Vector Machine --- p.63 / Chapter 3.4 --- Interpretation of parameters in BSVM --- p.67 / Chapter 3.5 --- Soft Label Biased Support Vector Machine --- p.69 / Chapter 3.6 --- Interpretation of parameters in Soft Label BSVM --- p.73 / Chapter 3.7 --- Relevance Feedback Using Biased Support Vector Machine --- p.74 / Chapter 3.7.1 --- Advantages of BSVM in Relevance Feedback . . --- p.74 / Chapter 3.7.2 --- Relevance Feedback Algorithm By BSVM --- p.75 / Chapter 3.8 --- Experiments --- p.78 / Chapter 3.8.1 --- Synthetic Dataset --- p.80 / Chapter 3.8.2 --- Real-World Dataset --- p.81 / Chapter 3.8.3 --- Experimental Results --- p.83 / Chapter 3.9 --- Conclusion --- p.86 / Chapter 4 --- Self-Organizing Map-based Inter-Query Learning --- p.88 / Chapter 4.1 --- Motivation --- p.88 / Chapter 4.2 --- Algorithm --- p.89 / Chapter 4.2.1 --- Initialization and Replication of SOM --- p.89 / Chapter 4.2.2 --- SOM Training for Inter-Query Learning --- p.90 / Chapter 4.2.3 --- Incorporate with Intra-Query Learning --- p.92 / Chapter 4.3 --- Experiments --- p.93 / Chapter 4.3.1 --- Synthetic Dataset --- p.95 / Chapter 4.3.2 --- Real-World Dataset --- p.95 / Chapter 4.3.3 --- Experimental Results --- p.97 / Chapter 4.4 --- Conclusion --- p.98 / Chapter 5 --- Conclusion --- p.102 / Bibliography --- p.104

Lau Tsz Yam. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 91-94). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Characterization of Colour Deficiency --- p.7 / Chapter 2.1 --- Mechanism of colour vision --- p.7 / Chapter 2.2 --- Quantitative specification of colour --- p.10 / Chapter 2.3 --- Discrimination ellipses --- p.17 / Chapter 2.4 --- Colour perception of colour deficient people --- p.22 / Chapter 2.5 --- Luminance match of colour deficient people --- p.32 / Chapter 2.6 --- Diagnosis of colour deficiency --- p.32 / Chapter 2.7 --- Dichromat simulation algorithm --- p.35 / Chapter 3 --- Monocular Compensation --- p.37 / Chapter 3.1 --- Principle --- p.37 / Chapter 3.2 --- Potential problems without monocular compensation --- p.39 / Chapter 3.3 --- Existing monocular compensation implementations --- p.45 / Chapter 3.4 --- Compensation algorithm for monocular compensation --- p.47 / Chapter 4 --- Stereo Visual Display Unit - Monocular Compensation --- p.48 / Chapter 4.1 --- Gamut-based palette compression --- p.49 / Chapter 4.2 --- Compensation level --- p.56 / Chapter 4.3 --- Realizing transformed chromaticities --- p.59 / Chapter 5 --- Evaluation --- p.64 / Chapter 5.1 --- Extensiveness of compensation --- p.65 / Chapter 5.2 --- Combination of discriminations from the two eyes --- p.68 / Chapter 5.3 --- Discrimination improvement and visual comfort --- p.72 / Chapter 6 --- Conclusion and Future Works --- p.82 / Chapter A --- Raw Data of Experiment 53 --- p.85 / Bibliography --- p.91

Yuan Tianqiang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 51-55). / Abstracts in English and Chinese. / abstract --- p.i / acknowledgments --- p.iv / table of contents --- p.v / list of figures --- p.vii / list of tables --- p.ix / Chapter Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Reflectional Symmetry Detection --- p.1 / Chapter 1.2 --- Research Progress on Face Analysis --- p.2 / Chapter 1.2.1 --- Face Detection --- p.3 / Chapter 1.2.2 --- Face Alignment --- p.4 / Chapter 1.2.3 --- Face Recognition --- p.6 / Chapter 1.3 --- Organization of this thesis --- p.8 / Chapter Chapter 2 --- Local reflectional symmetry detection --- p.9 / Chapter 2.1 --- Proposed Method --- p.9 / Chapter 2.1.1 --- Symmetry measurement operator --- p.9 / Chapter 2.1.2 --- Potential regions selection --- p.10 / Chapter 2.1.3 --- Detection of symmetry axes --- p.11 / Chapter 2.2 --- Experiments --- p.13 / Chapter 2.2.1 --- Parameter setting and analysis --- p.13 / Chapter 2.2.2 --- Experimental Results --- p.14 / Chapter Chapter 3 --- Global perspective reflectional symmetry detection --- p.16 / Chapter 3.1 --- Introduction of camera models --- p.16 / Chapter 3.2 --- Property of Symmetric Point-Pair --- p.18 / Chapter 3.3 --- analysis and Experiment --- p.20 / Chapter 3.3.1 --- Confirmative Experiments --- p.20 / Chapter 3.3.2 --- Face shape generation with PSI --- p.22 / Chapter 3.3.3 --- Error Analysis --- p.24 / Chapter 3.3.4 --- Experiments of Pose Estimation --- p.25 / Chapter 3.4 --- Summary --- p.28 / Chapter Chapter 4 --- Pre-processing of face analysis --- p.30 / Chapter 4.1 --- Introduction of Hough Transform --- p.30 / Chapter 4.2 --- Eye Detection --- p.31 / Chapter 4.2.1 --- Coarse Detection --- p.32 / Chapter 4.2.2 --- Refine the eyes positions --- p.34 / Chapter 4.2.3 --- Experiments and Analysis --- p.35 / Chapter 4.3 --- Face Components Detection with GHT --- p.37 / Chapter 4.3.1 --- Parameter Analyses --- p.38 / Chapter 4 3.2 --- R-table Construction --- p.38 / Chapter 4.3.3 --- Detection Procedure and Voting Strategy --- p.39 / Chapter 4.3.4 --- Experiments and Analysis --- p.41 / Chapter Chapter 5 --- Pose estimation with face symmetry --- p.45 / Chapter 5.1 --- Key points selection --- p.45 / Chapter 5.2 --- Face Pose Estimation --- p.46 / Chapter 5.2.1 --- Locating eye corners --- p.46 / Chapter 5.2.2 --- Analysis and Summary --- p.47 / Chapter Chapter 6 --- Conclusions and future work --- p.49 / bibliography --- p.51

Tong Kai Man. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 76-80). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Previous and related works --- p.2 / Chapter 1.3 --- The Proposed Method --- p.4 / Chapter 1.4 --- Thesis outline --- p.6 / Chapter 2. --- Global deformation --- p.8 / Chapter 2.1 --- Feature points --- p.8 / Chapter 2.2 --- The deformation --- p.9 / Chapter 2.2.1 --- Deformation using affine transformation --- p.9 / Chapter 2.2.2 --- Elastic warping using Radial Basis Functions --- p.12 / Chapter 2.2.3 --- Biharmonic and triharmonic basic functions --- p.16 / Chapter 3. --- Local iterative surface fitting --- p.19 / Chapter 3.1 --- Basic closest point method --- p.19 / Chapter 3.2 --- Regional partitioning method --- p.27 / Chapter 3.2.1 --- Defining the regions --- p.29 / Chapter 3.2.2 --- Propagating from the seeds --- p.31 / Chapter 3.2.3 --- Handling the distortions --- p.36 / Chapter 3.3 --- Combined methods for surface fitting --- p.41 / Chapter 3.3.1 --- Summary of the surface fitting methods --- p.41 / Chapter 3.3.2 --- Combining the methods --- p.43 / Chapter 3.3.3 --- Fine-level fitting results --- p.47 / Chapter 4. --- Enhanced template based 3D Object reconstruction --- p.53 / Chapter 4.1 --- Compactly supported radial basis functions --- p.53 / Chapter 4.2 --- Reconstruction using two templates --- p.55 / Chapter 5. --- Implementations and Results --- p.60 / Chapter 5.1 --- Creation of 3D objects --- p.60 / Chapter 5.2 --- Feature points selection --- p.61 / Chapter 5.3 --- Experiment platform --- p.62 / Chapter 5.4 --- Results --- p.63 / Chapter 6. --- Conclusions --- p.71 / Chapter 6.1 --- Contributions --- p.72 / Chapter 6.2 --- Future developments --- p.72 / Appendix A --- p.73 / Voxel based closest point evaluation --- p.73 / References --- p.76

跨模態圖像的合成和識別已成為計算機視覺領域的熱點。實際應用中存在各種各樣的圖像模態，比如刑偵中使用的素描畫和光照不變人臉識別中使用的近紅外圖像。由於某些模態的圖像很難獲得，模態間的轉換和匹配是一項十分有用的技術，為計算機視覺的應用提供了很大的便利。 / 本論文研究了三個應用：人像素描畫的合成，基於樣本的圖像風格化和人像素描畫識別。 / 我們將人像素描畫的合成的前沿研究擴展到非可控條件下的合成。以前的工作都只能在嚴格可控的條件下從照片合成素描畫。我們提出了一種魯棒的算法，可以從有光照和姿態變化的人臉照片合成素描畫。該算法用多尺度馬爾可夫隨機場來合成局部素描圖像塊。對光照和姿態的魯棒性通過三個部分來實現：基於面部器官的形狀先驗可以抑制缺陷和扭曲的合成效果，圖像塊的特征描述子和魯棒的距離測度用來選擇素描圖像塊，以及像素灰度和梯度的一致性來有效地匹配鄰近的素描圖像塊。在CUHK人像素描數據庫和網上的名人照片上的實驗結果表明我們的算法顯著提高了現有算法的效果。 / 針對基於樣本的圖像風格化，我們提供了一種將模板圖像的藝術風格傳遞到照片上的有效方法。大多數已有方法沒有考慮圖像內容和風格的分離。我們提出了一種通過頻段分解的風格傳遞算法。一幅圖像被分解成低頻、中頻和高頻分量，分別描述內容、主要風格和邊緣信息。接著中頻和高頻分量中的風格從模板傳遞到照片，這一過程用馬爾可夫隨機場來建模。最後我們結合照片中的低頻分量和獲得的風格信息重建出藝術圖像。和其它算法相比，我們的方法不僅合成了風格，而且很好的保持了原有的圖像內容。我們通過圖像風格化和個性化藝術合成的實驗來驗證了算法的有效性。 / 我們為人像素描畫的識別提出了一個從數據中學習人臉描述子的新方向。最近的研究都集中在轉換照片和素描畫到相同的模態，或者設計復雜的分類算法來減少從照片和素描畫提取的特征的模態間差異。我們提出了一種新穎的方法：在提取特征的階段減小模態間差異。我們用一種基於耦合信息論編碼的人臉描述子來獲取有判別性的局部人臉結構和有效的匹配照片和素描畫。通過最大化在量化特征空間的照片和素描畫的互信息，我們設計了耦合信息論投影森林來實現耦合編碼。在世界上最大的人像素描畫數據庫上的結果表明我們的方法和已有最好的方法相比有顯著提高。 / Inter-modality image synthesis and recognition has been a hot topic in computer vision. In real-world applications, there are diverse image modalities, such as sketch images for law enforcement and near infrared images for illumination invariant face recognition. Therefore, it is often useful to transform images from a modality to another or match images from different modalities, due to the difficulty of acquiring image data in some modality. These techniques provide large flexibility for computer vision applications. / In this thesis we study three problems: face sketch synthesis, example-based image stylization, and face sketch recognition. / For face sketch synthesis, we expand the frontier to synthesis from uncontrolled face photos. Previous methods only work under well controlled conditions. We propose a robust algorithm for synthesizing a face sketch from a face photo with lighting and pose variations. It synthesizes local sketch patches using a multiscale Markov Random Field (MRF) model. The robustness to lighting and pose variations is achieved with three components: shape priors specific to facial components to reduce artifacts and distortions, patch descriptors and robust metrics for selecting sketch patch candidates, and intensity compatibility and gradient compatibility to match neighboring sketch patches effectively. Experiments on the CUHK face sketch database and celebrity photos collected from the web show that our algorithm significantly improves the performance of the state-of-the-art. / For example-based image stylization, we provide an effective approach of transferring artistic effects from a template image to photos. Most existing methods do not consider the content and style separately. We propose a style transfer algorithm via frequency band decomposition. An image is decomposed into the low-frequency (LF), mid-frequency (MF), and highfrequency( HF) components, which describe the content, main style, and information along the boundaries. Then the style is transferred from the template to the photo in the MF and HF components, which is formulated as MRF optimization. Finally a reconstruction step combines the LF component of the photo and the obtained style information to generate the artistic result. Compared to the other algorithms, our method not only synthesizes the style, but also preserves the image content well. We demonstrate that our approach performs excellently in image stylization and personalized artwork in experiments. / For face sketch recognition, we propose a new direction based on learning face descriptors from data. Recent research has focused on transforming photos and sketches into the same modality for matching or developing advanced classification algorithms to reduce the modality gap between features extracted from photos and sketches. We propose a novel approach by reducing the modality gap at the feature extraction stage. A face descriptor based on coupled information-theoretic encoding is used to capture discriminative local face structures and to effectively match photos and sketches. Guided by maximizing the mutual information between photos and sketches in the quantized feature spaces, the coupled encoding is achieved by the proposed coupled information-theoretic projection forest. Experiments on the largest face sketch database show that our approach significantly outperforms the state-of-the-art methods. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Zhang, Wei. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 121-137). / Abstract also in Chinese. / Abstract --- p.i / Acknowledgement --- p.v / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Multi-Modality Computer Vision --- p.1 / Chapter 1.2 --- Face Sketches --- p.4 / Chapter 1.2.1 --- Face Sketch Synthesis --- p.6 / Chapter 1.2.2 --- Face Sketch Recognition --- p.7 / Chapter 1.3 --- Example-based Image Stylization --- p.9 / Chapter 1.4 --- Contributions and Summary of Approaches --- p.10 / Chapter 1.5 --- Thesis Road Map --- p.13 / Chapter 2 --- Literature Review --- p.14 / Chapter 2.1 --- Related Works in Face Sketch Synthesis --- p.14 / Chapter 2.2 --- Related Works in Example-based Image Stylization --- p.17 / Chapter 2.3 --- Related Works in Face Sketch Recognition --- p.21 / Chapter 3 --- Lighting and Pose Robust Sketch Synthesis --- p.27 / Chapter 3.1 --- The Algorithm --- p.31 / Chapter 3.1.1 --- Overview of the Method --- p.32 / Chapter 3.1.2 --- Local Evidence --- p.34 / Chapter 3.1.3 --- Shape Prior --- p.40 / Chapter 3.1.4 --- Neighboring Compatibility --- p.42 / Chapter 3.1.5 --- Implementation Details --- p.43 / Chapter 3.1.6 --- Acceleration --- p.45 / Chapter 3.2 --- Experimental Results --- p.47 / Chapter 3.2.1 --- Lighting and Pose Variations --- p.49 / Chapter 3.2.2 --- Celebrity Faces from the Web --- p.54 / Chapter 3.3 --- Conclusion --- p.54 / Chapter 4 --- Style Transfer via Band Decomposition --- p.58 / Chapter 4.1 --- Introduction --- p.58 / Chapter 4.2 --- Algorithm Overview --- p.63 / Chapter 4.3 --- Image Style Transfer --- p.64 / Chapter 4.3.1 --- Band Decomposition --- p.64 / Chapter 4.3.2 --- MF and HF Component Processing --- p.67 / Chapter 4.3.3 --- Reconstruction --- p.74 / Chapter 4.4 --- Experiments --- p.76 / Chapter 4.4.1 --- Comparison to State-of-the-Art --- p.76 / Chapter 4.4.2 --- Extended Application: Personalized Artwork --- p.82 / Chapter 4.5 --- Conclusion --- p.84 / Chapter 5 --- Coupled Encoding for Sketch Recognition --- p.86 / Chapter 5.1 --- Introduction --- p.86 / Chapter 5.1.1 --- Related work --- p.89 / Chapter 5.2 --- Information-Theoretic Projection Tree --- p.90 / Chapter 5.2.1 --- Projection Tree --- p.91 / Chapter 5.2.2 --- Mutual Information Maximization --- p.92 / Chapter 5.2.3 --- Tree Construction with MMI --- p.94 / Chapter 5.2.4 --- Randomized CITP Forest --- p.102 / Chapter 5.3 --- Coupled Encoding Based Descriptor --- p.103 / Chapter 5.4 --- Experiments --- p.106 / Chapter 5.4.1 --- Descriptor Comparison --- p.108 / Chapter 5.4.2 --- Parameter Exploration --- p.109 / Chapter 5.4.3 --- Experiments on Benchmarks --- p.112 / Chapter 5.5 --- Conclusions --- p.115 / Chapter 6 --- Conclusion --- p.116 / Bibliography --- p.121

In the first part, decoder based error concealment methods are discussed. An adaptive partition size (APS) temporal error concealment method is developed for H.264. We propose to use Weighted Double-Sided External Boundary Matching Error (WDS-EBME) to jointly measure the inter-MB boundary discontinuity, inter-partition boundary discontinuity and intra-partition block artifacts in the corrupted MB. By minimizing the WDS-EBME value of each partition, the best motion vectors of each candidate partition mode can be estimated, overall WDS-EBME of the MB concealed by each partition mode can then be evaluated and the best partition mode for the corrupted Macroblocks (MB) will be determined as the one with the smallest overall WDS-EBME. We also propose a progressive concealment order for the 4x4 partition mode. / In this thesis, techniques for efficient error resilient video coding are investigated. Three parts of the work are discussed in this thesis. / The last part of the thesis concerns the joint encoder-decoder error control method. A joint temporal error control method is proposed for H.264. It combines RDO-based macroblock (MB) classification at the encoder and adaptive partition size error concealment at the decoder. The encoder classifies the MBs by evaluating the sensitivity of the MBs as the RD cost between the concealment error and the bits needed for the additional motion information. Additional motion information such as the original motion vector or motion vector index can be transmitted for the error sensitive MBs. The decoder utilizes the additional motion information if any of these MBs get lost. Non-sensitive MBs and blocks are concealed by the APS method. / The second part of this thesis investigates encoder based error control techniques. Firstly, a VLC/FLC data partitioning method is proposed for MPEG-4. It disables intra AC prediction and groups appropriate fixed length coded (FLC) syntaxes in a video packet (or slice) together to form a new partition. With intra AC prediction disabled, errors occurring in these FLC syntaxes will not cause spatial error propagation. It essentially classifies the syntaxes into two categories according to whether that syntax will cause spatial error propagation when an error occurs. Secondly, a redundant macroblock strategy is proposed for H.264. MB Differential Mean Square Error (DMSE) is employed to evaluate the error sensitivity of MBs. The most sensitive MBs are transmitted separately in additional slices while coarsely quantized copies of the MBs are placed in the original slice. When working with chessboard style Flexible Macroblock reordering (FMO) and fixed length slice mode (FMO-slicing), the scheme performs well against packet loss errors with acceptable overhead and it is highly compatible with original H.264 bitstream. Thirdly, a joint optimal bit allocation and rate control scheme is proposed for H.264 with redundant slice. The optimum ratio between each primary and redundant picture pair is analytically deduced. Rate function and distortion model for both representations are developed, and a simple close-form solution is provided to achieve joint optimum bit allocation. / Video communication and other web-based video applications become popular in recent years. However, the transmission of the compressed video bit stream often suffers from imperfection of the communication channel, like path loss, multipath fading, co-channel interference, congestion, etc. Error resilient video coding techniques need to be employed to mitigate the channel errors, which include error concealment in the decoder, forward error correction in the encoder and joint encoder-decoder error control techniques. / Li, Jie. / Adviser: Ngan King Ngi. / Source: Dissertation Abstracts International, Volume: 73-01, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (leaves 137-146). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [201-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.

In this dissertation, we propose three methods to solve the problems of interactive image segmentation, video completion, and image denoising, which are all formulated as MRF-based energy minimization problems. In our algorithms, different MRF-based energy functions with particular techniques according to the characteristics of different tasks are designed to well fit the problems. With the energy functions, different optimization schemes are proposed to find the optimal results in these applications. In interactive image segmentation, an iterative optimization based framework is proposed, where in each iteration an MRF-based energy function incorporating an estimated initial probabilistic map of the image is optimized with a relaxed global optimal solution. In video completion, a well-defined MRF energy function involving both spatial and temporal coherence relationship is constructed based on the local motions calculated in the first step of the algorithm. A hierarchical belief propagation optimization scheme is proposed to efficiently solve the problem. In image denoising, label relaxation based optimization on a Gaussian MRF energy is used to achieve the global optimal closed form solution. / Many problems in computer vision involve assigning each pixel a label, which represents some spatially varying quantity such as image intensity in image denoising or object index label in image segmentation. In general, such quantities in image processing tend to be spatially piecewise smooth, since they vary smoothly in the object surface and change dramatically at object boundaries, while in video processing, additional temporal smoothness is satisfied as the corresponding pixels in different frames should have similar labels. Markov random field (MRF) models provide a robust and unified framework for many image and video applications. The framework can be elegantly expressed as an MRF-based energy minimization problem, where two penalty terms are defined with different forms. Many approaches have been proposed to solve the MRF-based energy optimization problem, such as simulated annealing, iterated conditional modes, graph cuts, and belief propagation. / Promising results obtained by the proposed algorithms, with both quantitative and qualitative comparisons to the state-of-the-art methods, demonstrate the effectiveness of our algorithms in these image and video processing applications. / Liu, Ming. / Adviser: Xiaoou Tang. / Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (leaves 79-89). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.

Based on the construction of Gabor feature space, which is important in applying pixel similarity computations, we formalize the space using rotation-invariant Gabor filter banks and apply optimizations in texture feature space. In image colorizations, the pixels that have similar Gabor features appear similar colors, our approach can colorize natural images globally, without the restriction of the disjoint regions with similar texture-like appearances. Our approach supports the two-pass colorization processes: coloring optimization in Gabor space and color detailing for progressive effects. We further work on the video colorization using the optimized Gabor flow computing, including coloring keyframes, color propagation by Gabor filtering, and optimized parallel computing over the video. Our video colorization is designed in a spatiotemporal manner to keep temporal coherence, and provides simple closed-form solutions in energy optimization that yield fast colonizations. Moreover, we develop parallel surface texturing of geometric models on GPU, generating spatially-varying visual appearances. We incorporate the Gabor feature space for the searching of 2D exemplars, to determine the k-coherence candidate pixels. The multi-pass correction in synthesis is applied to the local neighborhood for parallel processes. The iso/aniso-scale texture synthesis leverages the strengths of GPU computing, so to synthesize the iso/aniso-scale texturing appearance in parallel over arbitrary surfaces. Our experimental results showed that our approach produces simply controllable texturing effects of surface synthesis, generating texture-similar and spatially-varying visual appearances with GPU accelerated performance. / Texture feature similarity has long been crucial and important topic in VR/graphics applications, such as image and video colorizations, surface texture synthesis and geometry image applications. Generally, the image feature is highly subjective, depending on not only the image pixels but also interactive users. Existing colorization and surface texture synthesis pay little attention to the generation of conforming color/textures that accurately reflect exemplar structures or user's intension. Realistic surface synthesis remains a challenging task in VR/graphics researches. In this dissertation, we focus on the encoding of the Gabor filter banks into texture feature similarity computations and GPU-parallel surface rendering faithfully, including image/vodeo colorizations, parallel texturing of geometric surfaces, and multiresolution rendering on sole-cube maps (SCMs). / We further explore the GPU-based multiresolution rendering on solecube maps (SCMs). Our SCMs on GPU generate adaptive mesh surfaces dynamically, and are fully developed in parallelization for large-scale and complex VR environments. We also encapsulate the differential coordinates in SCMs, reflecting the local geometric characteristics for geometric modeling and interactive animation applications. For the future work, we will work on improving the image/ video feature analysis framework in VR/graphics applications. The further work lying in the surface texture synthesis includes the interactive control of texture orientations by surface vector fields using sketch editing, so to widen the gamut of interactive tools available for texturing artists and end users. / Sheng, Bin. / Adviser: Hanqin Sun. / Source: Dissertation Abstracts International, Volume: 73-04, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2011. / Includes bibliographical references (leaves 128-142). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [201-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.