Wei Dan. / Thesis submitted in: October 2005. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 93-101). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Our applications --- p.1 / Chapter 1.3 --- Structure of the thesis --- p.2 / Chapter 2 --- The Programmable Graphics Hardware --- p.4 / Chapter 2.1 --- Introduction --- p.4 / Chapter 2.2 --- The evolution of programmable graphics hardware --- p.4 / Chapter 2.3 --- Benefit of GPU --- p.6 / Chapter 2.4 --- Architecture of programmable graphics hardware --- p.9 / Chapter 2.4.1 --- The graphics hardware pipeline --- p.9 / Chapter 2.4.2 --- Programmable graphics hardware --- p.10 / Chapter 2.5 --- Data Mapping in GPU --- p.12 / Chapter 2.6 --- Some limitations of current GPU --- p.13 / Chapter 2.7 --- Application and Related Work --- p.16 / Chapter 3 --- Image-based Relighting on GPU --- p.18 / Chapter 3.1 --- Introduction --- p.18 / Chapter 3.2 --- Image based relighting --- p.20 / Chapter 3.2.1 --- The plenoptic illumination function --- p.20 / Chapter 3.2.2 --- Sampling and Relighting --- p.21 / Chapter 3.3 --- Linear Approximation Function --- p.22 / Chapter 3.3.1 --- Spherical harmonics basis function --- p.22 / Chapter 3.3.2 --- Radial basis function --- p.23 / Chapter 3.4 --- Data Representation --- p.23 / Chapter 3.5 --- Relighting on GPU --- p.24 / Chapter 3.5.1 --- Directional light source relighting --- p.27 / Chapter 3.5.2 --- Point light source relighting --- p.28 / Chapter 3.6 --- Experiment --- p.32 / Chapter 3.6.1 --- Visual Evaluation --- p.32 / Chapter 3.6.2 --- Statistic Evaluation --- p.33 / Chapter 3.7 --- Conclusion --- p.34 / Chapter 4 --- Texture Compression on GPU --- p.40 / Chapter 4.1 --- Introduction --- p.40 / Chapter 4.2 --- The Feature of Texture Compression --- p.41 / Chapter 4.3 --- Implementation --- p.42 / Chapter 4.3.1 --- Encoding --- p.43 / Chapter 4.3.2 --- Decoding --- p.46 / Chapter 4.4 --- The Texture Compression based Relighting on GPU --- p.46 / Chapter 4.5 --- An improvement of the existing compression techniques --- p.48 / Chapter 4.6 --- Experiment Evaluation --- p.50 / Chapter 4.7 --- Conclusion --- p.51 / Chapter 5 --- Environment Relighting on GPU --- p.55 / Chapter 5.1 --- Overview --- p.55 / Chapter 5.2 --- Related Work --- p.56 / Chapter 5.3 --- Linear Approximation Algorithm --- p.58 / Chapter 5.3.1 --- Basic Architecture --- p.58 / Chapter 5.3.2 --- Relighting on SH --- p.60 / Chapter 5.3.3 --- Relighting on RBF --- p.61 / Chapter 5.3.4 --- Sampling the Environment --- p.63 / Chapter 5.4 --- Implementation on GPU --- p.64 / Chapter 5.5 --- Evaluation --- p.66 / Chapter 5.5.1 --- Visual evaluation --- p.66 / Chapter 5.5.2 --- Statistic evaluation --- p.67 / Chapter 5.6 --- Conclusion --- p.69 / Chapter 6 --- Neocognitron on GPU --- p.70 / Chapter 6.1 --- Overview --- p.70 / Chapter 6.2 --- Neocognitron --- p.72 / Chapter 6.3 --- Neocognitron on GPU --- p.75 / Chapter 6.3.1 --- Data Mapping and Connection Texture --- p.76 / Chapter 6.3.2 --- Convolution and Offset Computation --- p.77 / Chapter 6.3.3 --- Recognition Pipeline --- p.80 / Chapter 6.4 --- Experiments and Results --- p.81 / Chapter 6.4.1 --- Performance Evaluation --- p.81 / Chapter 6.4.2 --- Feature Visualization of Intermediate-Layer --- p.84 / Chapter 6.4.3 --- A Real-Time Tracking Test --- p.84 / Chapter 6.5 --- Conclusion --- p.87 / Chapter 7 --- Conclusion --- p.90 / Bibliography --- p.93

Ding, Ning. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 215-225). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts also in Chinese.

In this research three innovative registration systems were designed with the configurations of the mutual information and optimization technique: (1) mutual information combined with the downhill simplex method of optimization. (2) the derivative of mutual information combined with Quasi-Newton method. (3) mutual information combined with hybrid genetic algorithm (large-space random search) to avoid local maximum during the optimization. These automatic registration systems were evaluated with a variety of images, dimensions and voxel resolutions. Experiments demonstrate that registration system combined with mutual information and hybrid genetic algorithm can provide robust and accurate alignments to obtain a composite activation map for functional MRI analysis.

Typescript (photocopy). / Digitized by Kansas Correctional Industries / Department: Computer Science.

Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1982. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Bibliography: leaf 56. / by Ricardo Eugenio Velez. / M.S.

This work is concerned with the problem of 3-D object recognition and orientation determination from single 2-D image frames in which objects may be noisy, partially occluded or both. Global descriptors of shape such as moments and Fourier descriptors rely on the whole shape being present. If part of a shape is missing then all of the descriptors will be affected. Consequently, such approaches are not suitable when objects are partially occluded, as results presented here show. Local methods of describing shape, where distortion of part of the object affects only the descriptors associated with that particular region, and nowhere else, are more likely to provide a successful solution to the problem. One such method is to locate points of maximum curvature on object boundaries. These are commonly believed to be the most perceptually significant points on digital curves. However, results presented in this thesis will show that estimators of point curvature become highly unreliable in the presence of noise. Rather than attempting to locate such high curvature points directly, an approach is presented which searches for boundary segments which exhibit significant linearity; curvature discontinuities are then assigned to the junctions between boundary segments. The resulting object descriptions are more stable in the presence of noise. Object orientation and recognition is achieved through a directed search and comparison to a database of similar 2-D model descriptions stored at various object orientations. Each comparison of sensed and model data is realised through a 2-D pose-clustering procedure, solving for the coordinate transformation which maps model features onto image features. Object features are used both to control the amount of computation and to direct the search of the database. In conditions of noise and occlusion objects can be recognised and their orientation determined to within less than 7 degrees of arc, on average.

by Hu, Chen. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 36-39). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Noise Model --- p.1 / Chapter 1.1.1 --- Impulse Noise --- p.1 / Chapter 1.2 --- Removing Impulse Noise --- p.2 / Chapter 1.2.1 --- Nonlinear Filter --- p.3 / Chapter 1.2.2 --- Variational Method --- p.4 / Chapter 1.3 --- Organization of the Dissertation --- p.5 / Chapter 2 --- Review of ACWMF and DPVM --- p.7 / Chapter 2.1 --- Review of ACWMF --- p.7 / Chapter 2.2 --- Review of DPVM --- p.9 / Chapter 2.2.1 --- Minimization Scheme --- p.9 / Chapter 3 --- Two-Phase Iterative Method --- p.12 / Chapter 3.1 --- Introduction --- p.12 / Chapter 3.2 --- Two-Phase Scheme --- p.13 / Chapter 3.2.1 --- Detection Phase --- p.13 / Chapter 3.2.2 --- Restoration Phase --- p.13 / Chapter 3.2.3 --- Summary of the Algorithm --- p.14 / Chapter 4 --- Nonlinear Equation Solver --- p.16 / Chapter 4.1 --- Introduction --- p.16 / Chapter 4.2 --- Newton's Method --- p.17 / Chapter 4.2.1 --- Newton's Method --- p.17 / Chapter 4.2.2 --- Order of Convergence --- p.17 / Chapter 4.3 --- Secant Method --- p.19 / Chapter 4.3.1 --- Secant Method --- p.19 / Chapter 4.3.2 --- Order of Convergence --- p.19 / Chapter 4.4 --- Secant-like Method --- p.21 / Chapter 4.4.1 --- Secant-like Method --- p.21 / Chapter 4.4.2 --- Order of Convergence --- p.24 / Chapter 5 --- Numerical Experiments --- p.27 / Chapter 5.1 --- Removing Noise --- p.27 / Chapter 5.2 --- Complexity of Algorithm --- p.33 / Chapter 6 --- Concluding Remarks --- p.35 / Bibliography --- p.36

Ho Chung Wa. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references. / Abstracts in English and Chinese. / Introduction --- p.6 / Paper I --- p.13 / Paper II --- p.34 / Concluding Remark --- p.51

Cheung Man Ting. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 69-71). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- The Emergence of ASIP --- p.1 / Chapter 1.1.1 --- Related Work --- p.3 / Chapter 1.2 --- Motivation --- p.6 / Chapter 1.3 --- ASIP Design Methodologies --- p.7 / Chapter 1.4 --- Fundamentals of Speech Recognition --- p.8 / Chapter 1.5 --- Thesis outline --- p.10 / Chapter 2 --- Automatic Speech Recognition --- p.11 / Chapter 2.1 --- Overview of ASR system --- p.11 / Chapter 2.2 --- Theory of Front-end Feature Extraction --- p.12 / Chapter 2.3 --- Theory of HMM-based Speech Recognition --- p.14 / Chapter 2.3.1 --- Hidden Markov Model (HMM) --- p.14 / Chapter 2.3.2 --- The Typical Structure of the HMM --- p.14 / Chapter 2.3.3 --- Discrete HMMs and Continuous HMMs --- p.15 / Chapter 2.3.4 --- The Three Basic Problems for HMMs --- p.17 / Chapter 2.3.5 --- Probability Evaluation --- p.18 / Chapter 2.4 --- The Viterbi Search Engine --- p.19 / Chapter 2.5 --- Isolated Word Recognition (IWR) --- p.22 / Chapter 3 --- Design of ASIP Platform --- p.24 / Chapter 3.1 --- Instruction Fetch --- p.25 / Chapter 3.2 --- Instruction Decode --- p.26 / Chapter 3.3 --- Datapath --- p.29 / Chapter 3.4 --- Register File Systems --- p.30 / Chapter 3.4.1 --- Memory Hierarchy --- p.30 / Chapter 3.4.2 --- Register File Organization --- p.31 / Chapter 3.4.3 --- Special Registers --- p.34 / Chapter 3.4.4 --- Address Generation --- p.34 / Chapter 3.4.5 --- Load and Store --- p.36 / Chapter 4 --- Implementation of Speech Recognition on ASIP --- p.37 / Chapter 4.1 --- Hardware Architecture Exploration --- p.37 / Chapter 4.1.1 --- Floating Point and Fixed Point --- p.37 / Chapter 4.1.2 --- Multiplication and Accumulation --- p.38 / Chapter 4.1.3 --- Pipelining --- p.41 / Chapter 4.1.4 --- Memory Architecture --- p.43 / Chapter 4.1.5 --- Saturation Logic --- p.44 / Chapter 4.1.6 --- Specialized Addressing Modes --- p.44 / Chapter 4.1.7 --- Repetitive Operation --- p.47 / Chapter 4.2 --- Software Algorithm Implementation --- p.49 / Chapter 4.2.1 --- Implementation Using Base Instruction Set --- p.49 / Chapter 4.2.2 --- Implementation Using Refined Instruction Set --- p.54 / Chapter 5 --- Simulation Results --- p.56 / Chapter 6 --- Conclusions and Future Work --- p.60 / Appendices --- p.62 / Chapter A --- Base Instruction Set --- p.62 / Chapter B --- Special Registers --- p.65 / Chapter C --- Chip Microphotograph of ASIP --- p.67 / Chapter D --- The Testing Board of ASIP --- p.68 / Bibliography --- p.69

Wang Tong. / Thesis submitted in: June 2004. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 64-69). / Abstracts in English and Chinese. / ABSTRACT --- p.I / 摘要 --- p.IV / ACKNOWLEDGMENTS --- p.VI / TABLE OF CONTENTS --- p.VIII / LIST OF FIGURES --- p.XIIV / Chapter CHAPTER 1 --- INTRODUCTION --- p.1 / Chapter 1.1 --- Hough Transform --- p.2 / Chapter 1.2 --- Template Matching --- p.3 / Chapter 1.3 --- Genetic Algorithms --- p.4 / Chapter 1.4 --- Outline of the Thesis --- p.6 / Chapter CHAPTER 2 --- HOUGH TRANSFORM AND ITS COMMON VARIANTS --- p.7 / Chapter 2.1 --- Hough Transform --- p.7 / Chapter 2.1.1 --- What is Hough Transform --- p.7 / Chapter 2.1.2 --- Parameter Space --- p.7 / Chapter 2.1.3 --- Accumulator Array --- p.9 / Chapter 2.2 --- Gradient-based Hough Transform --- p.10 / Chapter 2.2.1 --- Direction of Gradient --- p.11 / Chapter 2.2.2 --- Accumulator Array --- p.14 / Chapter 2.2.3 --- Peaks in the accumulator array --- p.16 / Chapter 2.2.4 --- Performance of Gradient-based Hough Transform --- p.18 / Chapter 2.3 --- Generalized Hough Transform (GHT) --- p.19 / Chapter 2.3.1 --- What Is GHT --- p.19 / Chapter 2.3.2 --- R-table of GHT --- p.20 / Chapter 2.3.3 --- GHT Procedure --- p.21 / Chapter 2.3.4 --- Analysis --- p.24 / Chapter 2.4 --- Edge Detection --- p.25 / Chapter 2.4.1 --- Gradient-Based Method --- p.25 / Chapter 2.4.2 --- Laplacian of Gaussian --- p.29 / Chapter 2.4.3 --- Canny edge detection --- p.30 / Chapter CHAPTER 3 --- PROBABILISTIC MODELS --- p.33 / Chapter 3.1 --- Randomized Hough Transform (RHT) --- p.33 / Chapter 3.1.1 --- Basics of the RHT --- p.33 / Chapter 3.1.2 --- RHT algorithm --- p.34 / Chapter 3.1.3 --- Advantage of RHT --- p.37 / Chapter 3.2 --- Genetic Model --- p.37 / Chapter 3.2.1 --- Genetic algorithm mechanism --- p.38 / Chapter 3.2.2 --- A Genetic Algorithm for Primitive Extraction --- p.39 / Chapter CHAPTER 4 --- PROPOSED ARBITRARY SHAPE DETECTION --- p.42 / Chapter 4.1 --- Randomized Generalized Hough Transform --- p.42 / Chapter 4.1.1 --- R-table properties and the general notion of a shape --- p.42 / Chapter 4.1.2 --- Using pairs of edges --- p.44 / Chapter 4.1.3 --- Extend to Arbitrary shapes --- p.46 / Chapter 4.2 --- A Genetic algorithm with the Hausdorff distance --- p.47 / Chapter 4.2.1 --- Hausdorff distance --- p.47 / Chapter 4.2.2 --- Chromosome strings --- p.48 / Chapter 4.2.3 --- Discussion --- p.51 / Chapter CHAPTER 5 --- EXPERIMENTAL RESULTS AND COMPARISONS --- p.52 / Chapter 5.1 --- Primitive extraction --- p.53 / Chapter 5.2 --- Arbitrary Shape Detection --- p.54 / Chapter 5.3 --- Summary of the Experimental Results --- p.60 / Chapter CHAPTER 6 --- CONCLUSIONS --- p.62 / Chapter 6.1 --- Summary --- p.62 / Chapter 6.2 --- Future work --- p.63 / BIBLIOGRAPHY --- p.64