Li Ngai. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references. / Abstracts in English and Chinese. / Chapter Chapter 1. --- Introduction --- p.1-1 / Chapter 1.1. --- A Brief Review on Pattern Matching --- p.1-1 / Chapter 1.2. --- Objective of the Research Work --- p.1-5 / Chapter 1.3. --- Organization of the Thesis --- p.1-6 / Chapter 1.4. --- Notes on Publications --- p.1-7 / Chapter Chapter 2. --- Background Information --- p.2-1 / Chapter 2.1. --- Introduction --- p.2-1 / Chapter 2.2. --- Review of Block Based Pattern Matching --- p.2-3 / Chapter 2.2.1 --- Gradient Descent Strategy --- p.2-3 / Chapter 2.2.2 --- Simplified Matching Operations --- p.2-10 / Chapter 2.2.3 --- Fast Full-Search Methods --- p.2-14 / Chapter 2.2.4 --- Transform-domain Manipulations --- p.2-19 / Chapter Chapter 3. --- Statistical Rejection Threshold for Pattern Matching --- p.3-1 / Chapter 3.1. --- Introduction --- p.3-1 / Chapter 3.2. --- Walsh Hadamard Transform --- p.3-3 / Chapter 3.3. --- Coarse-to-fine Pattern Matching in Walsh Hadamard Domain --- p.3-4 / Chapter 3.3.1. --- Bounding Euclidean Distance in Walsh Hadamard Domain --- p.3-5 / Chapter 3.3.2. --- Fast Projection Scheme --- p.3-9 / Chapter 3.3.3. --- Using the Projection Scheme for Pattern Matching --- p.3-17 / Chapter 3.4. --- Statistical Rejection Threshold --- p.3-18 / Chapter 3.5. --- Experimental Results --- p.3-22 / Chapter 3.6. --- Conclusions --- p.3-29 / Chapter 3.7. --- Notes on Publication --- p.3-30 / Chapter Chapter 4. --- Fast Walsh Search --- p.4-1 / Chapter 4.1. --- Introduction --- p.4-1 / Chapter 4.2. --- Approximating Sum-of-absolute Difference Using PS AD --- p.4-3 / Chapter 4.3. --- Two-level Threshold Scheme --- p.4-6 / Chapter 4.4. --- Block Matching Using SADDCC --- p.4-10 / Chapter 4.5. --- Optimization of Threshold and Number of Coefficients in PSAD --- p.4-15 / Chapter 4.6. --- Candidate Elimination by the Mean of PSAD --- p.4-23 / Chapter 4.7. --- Computation Requirement --- p.4-28 / Chapter 4.8. --- Experimental Results --- p.4-32 / Chapter 4.9. --- Conclusions --- p.4-45 / Chapter 4.10. --- Notes on Publications --- p.4-46 / Chapter Chapter 5. --- Conclusions & Future Works --- p.5-1 / Chapter 5.1. --- Contributions and Conclusions --- p.5-1 / Chapter 5.1.1. --- Statistical Rejection Threshold for Pattern Matching --- p.5-2 / Chapter 5.1.2. --- Fast Walsh Search --- p.5-3 / Chapter 5.2. --- Future Works --- p.5-4 / References --- p.I

Cao Liangliang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 64-69). / Abstracts in English and Chinese. / Chapter 1 --- Introduction and Related Work --- p.1 / Chapter 1.1 --- Reconstruction from Single Line Drawings and the Applications --- p.1 / Chapter 1.2 --- Optimization-based Reconstruction --- p.2 / Chapter 1.3 --- Other Reconstruction Methods --- p.2 / Chapter 1.3.1 --- Line Labeling and Algebraic Methods --- p.2 / Chapter 1.3.2 --- CAD Reconstruction --- p.3 / Chapter 1.3.3 --- Modelling from Images --- p.3 / Chapter 1.4 --- Finding Faces of Line Drawings --- p.4 / Chapter 1.5 --- Generalized Cylinder --- p.4 / Chapter 1.6 --- Research Problems and Our Contribution --- p.5 / Chapter 1.6.1 --- A New Criteria --- p.5 / Chapter 1.6.2 --- Recover Objects from Line Drawings without Hidden Lines --- p.6 / Chapter 1.6.3 --- Reconstruction of Curved Objects --- p.6 / Chapter 1.6.4 --- Planar Limbs Assumption and the Derived Models --- p.6 / Chapter 2 --- A New Criteria for Reconstruction --- p.8 / Chapter 2.1 --- Introduction --- p.8 / Chapter 2.2 --- Human Visual Perception and the Symmetry Measure --- p.10 / Chapter 2.3 --- Reconstruction Based on Symmetry and Planarity --- p.11 / Chapter 2.3.1 --- Finding Faces --- p.11 / Chapter 2.3.2 --- Constraint of Planarity --- p.11 / Chapter 2.3.3 --- Objective Function --- p.12 / Chapter 2.3.4 --- Reconstruction Algorithm --- p.13 / Chapter 2.4 --- Experimental Results --- p.13 / Chapter 2.5 --- Summary --- p.18 / Chapter 3 --- Line Drawings without Hidden Lines: Inference and Reconstruction --- p.19 / Chapter 3.1 --- Introduction --- p.19 / Chapter 3.2 --- Terminology --- p.20 / Chapter 3.3 --- Theoretical Inference of the Hidden Topological Structure --- p.21 / Chapter 3.3.1 --- Assumptions --- p.21 / Chapter 3.3.2 --- Finding the Degrees and Ranks --- p.22 / Chapter 3.3.3 --- Constraints for the Inference --- p.23 / Chapter 3.4 --- An Algorithm to Recover the Hidden Topological Structure --- p.25 / Chapter 3.4.1 --- Outline of the Algorithm --- p.26 / Chapter 3.4.2 --- Constructing the Initial Hidden Structure --- p.26 / Chapter 3.4.3 --- Reducing Initial Hidden Structure --- p.27 / Chapter 3.4.4 --- Selecting the Most Plausible Structure --- p.28 / Chapter 3.5 --- Reconstruction of 3D Objects --- p.29 / Chapter 3.6 --- Experimental Results --- p.32 / Chapter 3.7 --- Summary --- p.32 / Chapter 4 --- Curved Objects Reconstruction from 2D Line Drawings --- p.35 / Chapter 4.1 --- Introduction --- p.35 / Chapter 4.2 --- Related Work --- p.36 / Chapter 4.2.1 --- Face Identification --- p.36 / Chapter 4.2.2 --- 3D Reconstruction of planar objects --- p.37 / Chapter 4.3 --- Reconstruction of Curved Objects --- p.37 / Chapter 4.3.1 --- Transformation of Line Drawings --- p.37 / Chapter 4.3.2 --- Finding 3D Bezier Curves --- p.39 / Chapter 4.3.3 --- Bezier Surface Patches and Boundaries --- p.40 / Chapter 4.3.4 --- Generating Bezier Surface Patches --- p.41 / Chapter 4.4 --- Results --- p.43 / Chapter 4.5 --- Summary --- p.45 / Chapter 5 --- Planar Limbs and Degen Generalized Cylinders --- p.47 / Chapter 5.1 --- Introduction --- p.47 / Chapter 5.2 --- Planar Limbs and View Directions --- p.49 / Chapter 5.3 --- DGCs in Homogeneous Coordinates --- p.53 / Chapter 5.3.1 --- Homogeneous Coordinates --- p.53 / Chapter 5.3.2 --- Degen Surfaces --- p.54 / Chapter 5.3.3 --- DGCs --- p.54 / Chapter 5.4 --- Properties of DGCs --- p.56 / Chapter 5.5 --- Potential Applications --- p.59 / Chapter 5.5.1 --- Recovery of DGC Descriptions --- p.59 / Chapter 5.5.2 --- Deformable DGCs --- p.60 / Chapter 5.6 --- Summary --- p.61 / Chapter 6 --- Conclusion and Future Work --- p.62 / Bibliography --- p.64

視覺質量評估在各種多媒體應用中起到了關鍵性的作用。因為人類的視覺系統是視覺信號的最終接收髓，王觀視覺質量評估被認為是最可靠的視覺質量評估方法。然而，王觀視覺質量評估耗時、昂貴，並且不適合線上應用。因此，自動的、客觀的視覺質量評估方法已經被開發並被應用於很多實用埸合當中。最廣泛使用的客觀視覺質量度量方法，如均方差(MSE) 、峰值信噪比(PSNR) 等與人IN對視覺信號質量的判斷相距甚遠。因此，開發更準確的客觀質量度量算法將會成為未來視覺信號處理和傳輸應用成功與否的重要因素。 / 該論文主要研究全參考客觀視覺質量度量算法。主要內容分為三部分。 / 第一部分討論圖像質量評估。首先研究了一個經典的圖像質量度量算法--SSIM。提出了個新的加權方法並整合至IjSSIM 當中，提升了SSIM自可預測精度。之後，受到前面這個工作的故發，設計7 個全新的圖像質量度量算法，將噪聲分類為加性噪聲和細節失兩大類。這個算法在很多主觀質量圓像資料庫上都有很優秀的預測表現。 / 第二部分研究視頻質量評估。首先，將上面提到的全新的圓像質量度量算法通過挖掘視頻運動信息和時域相關的人眼視覺特性擴展為視頻質量度量算法。方法包括:使用基於人自民運動的時空域對比敏感度方程，使用基於運動崗量的時域視覺掩蓋，使用基於認知層面的空域整合等等。這個算法被證明對處理標清和高清序列同樣有效。其次，提出了一個測量視頻順間不一致程度的算法。該算法被整合到MSE 中，提高了MSE的預測表現。 / 上面提到的算法只考慮到了亮度噪聲。論文的最後部分通過個具體應用色差立體圓像生成究了色度噪聲。色差立體圖像是三維立體顯示技衛的其中種方法。它使在普通電視、電腦顯示器、甚至印刷品上顯示三維立體效果成為可能。我們提出了一個新的色差立體圖像生成方法。該方法工作在CIELAB彩色空間，並力圖匹配原始圖像與觀測立體圖像的色彩屬性值。 / Visual quality assessment (VQA) plays a fundamental role in multimedia applications. Since the human visual system (HVS) is the ultimate viewer of the visual information, subjective VQA is considered to be the most reliable way to evaluate visual quality. However, subjective VQA is time-consuming, expensive, and not feasible for on-line manipulation. Therefore, automatic objective VQA algorithms, or namely visual quality metrics, have been developed and widely used in practical applications. However, it is well known that the popular visual quality metrics, such as Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), etc., correlate poorly with the human perception of visual quality. The development of more accurate objective VQA algorithms becomes of paramount importance to the future visual information processing and communication applications. / In this thesis, full-reference objective VQA algorithms are investigated. Three parts of the work are discussed as briefly summarized below. / The first part concerns image quality assessment. It starts with the investigation of a popular image quality metric, i.e., Structural Similarity Index (SSIM). A novel weighting function is proposed and incorporated into SSIM, which leads to a substantial performance improvement in terms of matching subjective ratings. Inspired by this work, a novel image quality metric is developed by separately evaluating two distinct types of spatial distortions: detail losses and additive impairments. The pro- posed method demonstrates the state-of-the-art predictive performance on most of the publicly-available subjective quality image databases. / The second part investigates video quality assessment. We extend the proposed image quality metric to assess video quality by exploiting motion information and temporal HVS characteristics, e.g., eye movement spatio-velocity contrast sensitivity function, temporal masking using motion vectors, temporal pooling considering human cognitive behaviors, etc. It has been experimentally verified that the proposed video quality metric can achieve good performance on both standard-definition and high-definition video databases. We also propose a novel method to measure temporal inconsistency, an essential type of video temporal distortions. It is incorporated into the MSE for video quality assessment, and experiments show that it can significantly enhance MSE's predictive performance. / The aforementioned algorithms only analyze luminance distortions. In the last part, we investigate chrominance distortions for a specific application: anaglyph image generation. Anaglyph image is one of the 3D displaying techniques, which enables stereoscopic perception on traditional TVs, PC monitors, projectors, and even papers. Three perceptual color attributes are taken into account for the color distortion measure, i.e., lightness, saturation, and hue, based on which a novel anaglyph image generation algorithm is developed via approximation in the CIELAB color space. / 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. / Li, Songnan. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 122-130). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese. / Dedication --- p.ii / Acknowledgments --- p.iii / Abstract --- p.vi / Publications --- p.viii / Nomenclature --- p.xii / Contents --- p.xvii / List of Figures --- p.xx / List of Tables --- p.xxii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation and Objectives --- p.1 / Chapter 1.2 --- Overview of Subjective Visual Quality Assessment --- p.3 / Chapter 1.2.1 --- Viewing condition --- p.4 / Chapter 1.2.2 --- Candidate observer selection --- p.4 / Chapter 1.2.3 --- Test sequence selection --- p.4 / Chapter 1.2.4 --- Structure of test session --- p.5 / Chapter 1.2.5 --- Assessment procedure --- p.6 / Chapter 1.2.6 --- Post-processing of scores --- p.7 / Chapter 1.3 --- Overview of Objective Visual Quality Assessment --- p.8 / Chapter 1.3.1 --- Classification --- p.8 / Chapter 1.3.2 --- HVS-model-based metrics --- p.9 / Chapter 1.3.3 --- Engineering-based metrics --- p.21 / Chapter 1.3.4 --- Performance evaluation method --- p.28 / Chapter 1.4 --- Thesis Outline --- p.29 / Chapter I --- Image Quality Assessment --- p.32 / Chapter 2 --- Weighted Structural Similarity Index based on Local Smoothness --- p.33 / Chapter 2.1 --- Introduction --- p.33 / Chapter 2.2 --- The Structural Similarity Index --- p.33 / Chapter 2.3 --- Influence of the Smooth Region on SSIM --- p.35 / Chapter 2.3.1 --- Overall performance analysis --- p.35 / Chapter 2.3.2 --- Performance analysis for individual distortion types --- p.37 / Chapter 2.4 --- The Proposed Weighted-SSIM --- p.40 / Chapter 2.5 --- Experiments --- p.41 / Chapter 2.6 --- Summary --- p.43 / Chapter 3 --- Image Quality Assessment by Decoupling Detail Losses and Additive Impairments --- p.44 / Chapter 3.1 --- Introduction --- p.44 / Chapter 3.2 --- Motivation --- p.45 / Chapter 3.3 --- Related Works --- p.47 / Chapter 3.4 --- The Proposed Method --- p.48 / Chapter 3.4.1 --- Decoupling additive impairments and useful image contents --- p.48 / Chapter 3.4.2 --- Simulating the HVS processing --- p.56 / Chapter 3.4.3 --- Two quality measures and their combination --- p.58 / Chapter 3.5 --- Experiments --- p.59 / Chapter 3.5.1 --- Subjective quality image databases --- p.59 / Chapter 3.5.2 --- Parameterization --- p.60 / Chapter 3.5.3 --- Overall performance --- p.61 / Chapter 3.5.4 --- Statistical significance --- p.62 / Chapter 3.5.5 --- Performance on individual distortion types --- p.64 / Chapter 3.5.6 --- Hypotheses validation --- p.66 / Chapter 3.5.7 --- Complexity analysis --- p.69 / Chapter 3.6 --- Summary --- p.70 / Chapter II --- Video Quality Assessment --- p.71 / Chapter 4 --- Video Quality Assessment by Decoupling Detail Losses and Additive Impairments --- p.72 / Chapter 4.1 --- Introduction --- p.72 / Chapter 4.2 --- Related Works --- p.73 / Chapter 4.3 --- The Proposed Method --- p.74 / Chapter 4.3.1 --- Framework --- p.74 / Chapter 4.3.2 --- Decoupling additive impairments and useful image contents --- p.75 / Chapter 4.3.3 --- Motion estimation --- p.76 / Chapter 4.3.4 --- Spatio-velocity contrast sensitivity function --- p.77 / Chapter 4.3.5 --- Spatial and temporal masking --- p.79 / Chapter 4.3.6 --- Two quality measures and their combination --- p.80 / Chapter 4.3.7 --- Temporal pooling --- p.81 / Chapter 4.4 --- Experiments --- p.82 / Chapter 4.4.1 --- Subjective quality video databases --- p.82 / Chapter 4.4.2 --- Parameterization --- p.83 / Chapter 4.4.3 --- With/without decoupling --- p.84 / Chapter 4.4.4 --- Overall predictive performance --- p.85 / Chapter 4.4.5 --- Performance on individual distortion types --- p.88 / Chapter 4.4.6 --- Cross-distortion performance evaluation --- p.89 / Chapter 4.5 --- Summary --- p.91 / Chapter 5 --- Temporal Inconsistency Measure --- p.92 / Chapter 5.1 --- Introduction --- p.92 / Chapter 5.2 --- The Proposed Method --- p.93 / Chapter 5.2.1 --- Implementation --- p.93 / Chapter 5.2.2 --- MSE TIM --- p.94 / Chapter 5.3 --- Experiments --- p.96 / Chapter 5.4 --- Summary --- p.97 / Chapter III --- Application related to Color and 3D Perception --- p.98 / Chapter 6 --- Anaglyph Image Generation --- p.99 / Chapter 6.1 --- Introduction --- p.99 / Chapter 6.2 --- Anaglyph Image Artifacts --- p.99 / Chapter 6.3 --- Related Works --- p.101 / Chapter 6.3.1 --- Simple anaglyphs --- p.101 / Chapter 6.3.2 --- XYZ and LAB anaglyphs --- p.102 / Chapter 6.3.3 --- Ghosting reduction methods --- p.103 / Chapter 6.4 --- The Proposed Method --- p.104 / Chapter 6.4.1 --- Gamma transfer --- p.104 / Chapter 6.4.2 --- Converting RGB to CIELAB --- p.105 / Chapter 6.4.3 --- Matching color appearance attributes in CIELAB color space --- p.106 / Chapter 6.4.4 --- Converting CIELAB to RGB --- p.110 / Chapter 6.4.5 --- Parameterization --- p.111 / Chapter 6.5 --- Experiments --- p.112 / Chapter 6.5.1 --- Subjective tests --- p.112 / Chapter 6.5.2 --- Results and analysis --- p.113 / Chapter 6.5.3 --- Complexity --- p.115 / Chapter 6.6 --- Summary --- p.115 / Chapter 7 --- Conclusions --- p.117 / Chapter 7.1 --- Contributions of the Thesis --- p.117 / Chapter 7.2 --- Future Research Directions --- p.120 / Bibliography --- p.122

Based on the fixed block size FWS algorithm, we further proposed a fast full-pel variable block size motion estimation algorithm called Fast Walsh Search in Variable Block Size (FWS-VBS). As in FWS, FWS-VBS employs the PSAD as the error measure to identify likely mismatches. Mismatches are rejected by thresholding method and the thresholds are determined adaptively to cater for different activity levels in each block. Early termination techniques are employed to further reduce the number of candidates and modes to be searched of each block. FWS-VBS performs equally well to the exhaustive full search algorithm in the reference H.264/AVC encoder and requires only about 10% of the computation time. / Furthermore, we modified our proposed segmentation algorithm to handle video sequences that are already encoded in the H.264 format. Since the video is compressed, no spatial information is available. Instead, quantized transform coefficients of the residual frame are used to approximate spatial information and improve segmentation result. The computation time of the segmentation process is merely about 16ms per frame for CIF frame size video, allowing the algorithm to be applied in real-time applications such as video surveillance and conferencing. / In the first part of our research, we proposed a block matching algorithm called Fast Walsh Search (FWS) for video motion estimation. FWS employs two new error measures defined in Walsh Hadamard domain, which are partial sum-of-absolute difference (PSAD) and sum-of-absolute difference of DC coefficients (SADDCC). The algorithm first rejects most mismatched candidates using PSAD which is a coarse measure requiring little computation. Because of the energy packing ability of Walsh Hadamard transform (WHT) and the utilization of fast WHT computation algorithm, mismatched candidates are identified and rejected efficiently. Then the proposed algorithm identifies the matched candidate from the remaining candidates using SADDCC which is a more accurate measure and can reuse computation performed for PSAD. Experimental results show that FWS can give good visual quality to most of video scene with a reasonable amount of computation. / In the second part of our research, we developed a real-time video object segmentation algorithm. The motion information is obtained by FWS-VBS to minimize the computation time while maintaining an adequate accuracy. The algorithm makes use of the motion information to identify background motion model and moving objects. In order to preserve spatial and temporal continuity of objects, Markov random field (MRF) is used to model the foreground field. The block-based foreground object mask is obtained by minimizing the energy function of the MRF. The resulting object mask is then post-processed to generate a smooth object mask. Experimental results show that the proposed algorithm can effectively extract moving objects from different kind of sequences, at a speed of less than 100ms per frame for CIF frame size video. / Motion estimation is an important part in many video processing applications, such as video compression, object segmentation, and scene analysis. In all video compression applications, motion information is used to reduce temporal redundancy between frames, thus significantly reduce the required bitrate for transmission and storage of compressed video. In addition, in object-based video coding, video object can be automatically identified by its motion against the background. / Mak, Chun Man. / "June 2008." / Adviser: Wai-Kuen Cham. / Source: Dissertation Abstracts International, Volume: 70-03, Section: B, page: 1849. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references. / 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, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in English and Chinese. / School code: 1307.

In the first part, some efficient algorithms are proposed to reduce the complexity of H.264 encoder, which is the latest state-of-the-art video coding standard. Intra and Inter mode decision play a vital role in H.264 encoder and can reduce the spatial and temporal redundancy significantly, but the computational cost is also high. Here, a fast Intra mode decision algorithm and a fast Inter mode decision algorithm are proposed. Experimental results show that the proposed algorithms not only save a lot of computational cost, but also maintain coding performance quite well. Moreover, a real time H.264 baseline codec is implemented on mobile device. Based on our real time H.264 codec, an H.264 based mobile video conferencing system is achieved. / The objective of this thesis is to develop some efficient and perceptual image and video coding techniques. Two parts of the work are investigated in this thesis. / The second part of this thesis investigates two kinds of perceptual picture coding techniques. One is the just noticeable distortion (JND) based picture coding. Firstly, a DCT based spatio-temporal JND model is proposed, which is an efficient model to represent the perceptual redundancies existing in images and is consistent with the human visual system (HVS) characteristic. Secondly, the proposed JND model is incorporated into image and video coding to improve the perceptual quality. Based on the JND model, a transparent image coder and a perceptually optimized H.264 video coder are implemented. Another technique is the image compression scheme based on the recent advances in texture synthesis. In this part, an image compression scheme is proposed with the perceptual visual quality as the performance criterion instead of the pixel-wise fidelity. As demonstrated in extensive experiments, the proposed techniques can improve the perceptual quality of picture coding significantly. / Wei Zhenyu. / Adviser: Ngan Ngi. / Source: Dissertation Abstracts International, Volume: 73-01, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (leaves 148-154). / 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.

Although significant progress has been made in imaging devices during the past few decades, the photographs acquired by digital cameras are still far from perfection due to the physical limitations of hardware such as aperture, lens and sensor. This fact brings out the demand for study on image enhancement: a computational technique that aims to improve the interpretability or perception of information in photographs for human viewers. The work in this thesis mainly focuses on three tasks in image enhancement. / Finally, since the radiance of the real world spans several orders of magnitude and its dynamic range dramatically exceeds the capability of the current digital cameras, there often exist some undesirable over- or under-exposed regions in a photograph. The third part of this thesis aims at producing one great looking well-exposed image that is virtually impossible with a single exposure by compositing a stack of photos at different exposures taken with a conventional camera. Particularly, a simple but effective method is presented to describe how to take advantage of the gradient information to accomplish exposure composition in both static and dynamic scenes. Compared to conventional high dynamic range (HDR) imaging work, the proposed approach is quite appealing in practice since it is computationally efficient and easy to use, and frees users from the tedious radiometric calibration and tone mapping steps. / Firstly, since the camera sensor has limited resolution, the acquired images cannot capture the scene very detailedly. Hence, people often resort to a postprocessing technique called super-resolution (SR) to enhance the resolution of the captured images. In the first part of this thesis, two approaches are presented to address the challenging single image SR problem, which is to recover a high-resolution (HR) image from one low-resolution (LR) input. Specifically, a novel learning-based framework is designed specifically for face image SR task from the perspective of DCT domain. In addition, an efficient two-step scheme is developed to super-resolve generic image by exploiting the salient edges of the input LR image. / Secondly, due to the limitation of lens and aperture, some cameras cannot produce pleasant photographs with desired focus setting. For example, portrait photography that requires shallow depth of field (DOF) is not allowed when using the compact point-and-shoot cameras. In the second part of this thesis, a new and complete postprocessing-based focus editing system that is able to handle the tasks of focus map estimation, image refocusing and defocusing, is developed to overcome the optical limitations and create different kinds of novel photos with desired focus setting from an imperfect photo. / Throughout this work, extensive experiments on various real and synthetic image data are conducted to evaluate the performance of the proposed algorithms. / Zhang, Wei. / Adviser: Wai-Kuen Chan. / Source: Dissertation Abstracts International, Volume: 73-03, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (leaves 116-125). / 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.

by Wen Jiang. / c.2 author's name on frame header: Wen, Jiang. / Thesis (Ph.D.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (p. 105-[113]). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web.

Hung, Chun Ho. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2011. / Includes bibliographical references (p. 58-63). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Generalized Photometric Stereo --- p.6 / Chapter 2.1 --- Problem Description --- p.6 / Chapter 2.2 --- Related Work --- p.9 / Chapter 2.3 --- Photometric Stereo with Environment Lighting --- p.11 / Chapter 2.4 --- Estimating Surface Normals --- p.13 / Chapter 2.4.1 --- Surface Normal and Albedo Estimation --- p.14 / Chapter 2.5 --- Data Acquisition Configuration --- p.17 / Chapter 2.6 --- Issues --- p.19 / Chapter 2.7 --- Outlier Removal --- p.22 / Chapter 2.8 --- Experimental Results --- p.23 / Chapter 3 --- Generalized Stereo Matching --- p.30 / Chapter 3.1 --- Problem Description --- p.30 / Chapter 3.2 --- Related Work --- p.32 / Chapter 3.3 --- Our Approach --- p.33 / Chapter 3.3.1 --- Notations and Problem Introduction --- p.33 / Chapter 3.3.2 --- Depth and Motion Initialization --- p.35 / Chapter 3.3.3 --- Volume-based Structure Prior --- p.38 / Chapter 3.3.4 --- Objective Function with Volume-based Priors --- p.43 / Chapter 3.3.5 --- Numerical Solution --- p.46 / Chapter 3.4 --- Results --- p.48 / Chapter 4 --- Conclusion --- p.56 / Bibliography --- p.57

隨著數碼相機與移動照相設備的日益普及，現時的拍攝照片數量遠遠超過以前。數碼照相機的內在缺陷使得數字圖像還原領域得到廣泛的興趣。在本論文中，我們將研究圖像去模糊。圖像去模糊旨在從一張模糊的圖像恢復出清晰的圖像。它是一個在計算機視覺和圖形學有理論和實踐影響力的根本問題。單圖反卷積問題是一個十分挑戰的問題因為我們觀察到的信息比要恢復的信息要少。我們討論模糊核估計並分析為什麼現存的算法可以獲得成功。基於這些分析和理解，我們提出了一個創新的統一框架。該框架具有優異的圖像對模糊性能，並且只需使用很少的運算時間。這個框架還被擴展到了非均一的圖像去模糊上，並且取得與最先進算法相當的效果。 / 在現實模糊圖像中，模糊常常是非均一的，這種模糊具有更大的挑戰性。均一模糊的技術發展使得這個問題相對於以前較容易著手。在本論文中，我們對現存的相機抖動模型進行了詳細的研究並討論其中存在的一些問題。我們對相機模型進行歸納總結並且提出了基於每個平面的非均一圖像去模糊框架。基於這個框架，我們解決了一種特殊形式的模糊。這種模糊是產生於外平面運動，常見於用車載，體育和監控相機拍攝的照片。我們在具有挑戰性的網絡圖片和自己拍攝的圖片上進行測試，驗證了我們的方法的正確性。 / With the popularity of digital cameras and mobile phone cameras, much more photos are being taken nowadays than ever before. The imperfection of digital cameras arouses broad interest in digital image restoration. In this thesis, we study an important topic, i.e., image deblurring, which aims to recover a sharp image from only a blurry observation. It is one of the fundamental problems in computer vision and graphics with both theoretical and practical impact. Single image blind deconvolution is challenging since there are more unknowns than observations. We discuss problems involving blur kernel estimation and why state-ofthe-art methods work. These insights lead to a novel unified framework to achieve decent deblurring performance on publicly available datasets in faster speed. The extension of the framework to non-uniform image deblurring also achieves comparable performance to state-of-the-art methods. / Further, in real blurred images, it is quite often that blur is spatiallyvariant, which is very difficult to deal with. Advance in uniform deblurring makes this problem tractable. We make a detailed study of current camera shake models and discuss problems in these models. We also generalize the framework and propose a plane-wise non-uniform image deblurring framework. Based on it, we tackle a specific type of blur involving out-of-plane motion, which typically appears on photos captured using car, sport and surveillance camera. We validate our method on challenging photos obtained from internet and taken by ourselves. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Zheng, Shicheng. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 71-79). / Abstracts also in Chinese. / Abstract --- p.i / Acknowledgement --- p.v / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation and Objectives --- p.1 / Chapter 1.2 --- Contributions --- p.5 / Chapter 1.3 --- Thesis Outline --- p.6 / Chapter 2 --- Background --- p.8 / Chapter 2.1 --- Non-blind Image Deconvolution --- p.8 / Chapter 2.2 --- Blind Deconvolution --- p.13 / Chapter 2.3 --- Non-uniform Image Deblurring --- p.14 / Chapter 3 --- Unnatural Representation For Natural Image Deblurring --- p.19 / Chapter 3.0.1 --- Analysis --- p.21 / Chapter 3.0.2 --- Our Contribution --- p.23 / Chapter 3.1 --- Framework --- p.24 / Chapter 3.2 --- Optimization --- p.28 / Chapter 3.2.1 --- Solve for k --- p.28 / Chapter 3.2.2 --- Solve for k{U+1D57}⁺¹ with l{U+1D57}+1 --- p.32 / Chapter 3.2.3 --- Final Image Restoration --- p.34 / Chapter 3.3 --- Discussion --- p.34 / Chapter 3.4 --- Experimental Results --- p.38 / Chapter 3.5 --- Concluding Remarks --- p.41 / Chapter 4 --- Forward Motion Deblurring --- p.43 / Chapter 4.1 --- Background --- p.45 / Chapter 4.2 --- OurModel --- p.51 / Chapter 4.3 --- Forward Motion Deblurring. --- p.55 / Chapter 4.3.1 --- Kernel and Image Restoration --- p.55 / Chapter 4.4 --- Implementation and Discussion --- p.58 / Chapter 4.5 --- Experimental Results --- p.59 / Chapter 4.6 --- Conclusion and Limitation --- p.64 / Chapter 5 --- Conclusion --- p.65 / Chapter A --- New Sparsity Function --- p.67 / Bibliography --- p.71

by Kin-wai Mak. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (leaves 52-54). / Chapter 1 --- Introduction to Parallel Computing --- p.7 / Chapter 1.1 --- Parallel Computer Models --- p.8 / Chapter 1.2 --- Forms of Parallelism --- p.12 / Chapter 1.3 --- Performance Evaluation --- p.15 / Chapter 1.3.1 --- Finding Machine Parameters --- p.15 / Chapter 1.3.2 --- Amdahl's Law --- p.19 / Chapter 1.3.3 --- Gustafson's Law --- p.20 / Chapter 1.3.4 --- Scalability Analysis --- p.20 / Chapter 2 --- Introduction to Image Processing --- p.26 / Chapter 2.1 --- Image Restoration Problem --- p.26 / Chapter 2.1.1 --- Toeplitz Least Squares Problems --- p.29 / Chapter 2.1.2 --- The Need For Regularization --- p.31 / Chapter 2.1.3 --- Guide Star Image --- p.32 / Chapter 3 --- Toeplitz Solvers --- p.34 / Chapter 3.1 --- Introduction --- p.34 / Chapter 3.2 --- Parallel Implementation --- p.38 / Chapter 3.2.1 --- Overview of MasPar --- p.38 / Chapter 3.2.2 --- Design Methodology --- p.39 / Chapter 3.2.3 --- Implementation Details --- p.42 / Chapter 3.2.4 --- Application to Ground Based Astronomy --- p.44 / Chapter 3.2.5 --- Performance Analysis --- p.46 / Chapter 3.2.6 --- The Graphical Interface --- p.48 / Bibliography