by Chan Ming-hong. / Bibliography: leaves 67-68 / Thesis (M.Ph.)--Chinese University of Hong Kong, 1986

Wong Chun Nang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (leaves 56-58). / Abstracts in English and Chinese.

Thesis (M.Phil.)--Chinese University of Hong Kong. / Bibliography: leaves 122-126.

A method has been developed using an image analysis system that simulates human print quality perception. Previous work in the area of print quality assessment has only produced methods that measure individual print quality variables, or assess small parts of an image. The image analysis system developed in this investigation is different from the previous work because it analyses the combined effects of different variables using neural network technology. In addition, measurements from an entire image can be obtained and the system can assess images irrespective of their shape. The image analysis system hardware consists of a monochrome CCD camera, a Matrox image acquisition board and a 200 MHz Pentium computer. A data pre-processing program was developed using Visual Basic version 5 to process the image data from the camera. The processed data was fed into a neural network so that empirical models of print quality could be formulated. The neural network code originated from the Matlab neural network toolbox. Backpropagation and radial basis neural network functions were used in the investigation. The hardware and software of the image analysis system were tested for non-impact printing techniques. Images of a square, a circle and text characters with dimensions of 1 cm or less were used as test images for the image analysis system. It was established that it was possible to identify the different printing processes that produced the simple shapes and text characters using the image analysis system. This was achieved by training the neural network using pre-processed image data. This produced multi-dimensional mathematical models that were used to classify the different printing processes. The classification of the different printing processes involved the objective measurement of print quality variables. Different printing processes can produce print that differs in print quality when assessed by observers. Therefore the successful classification of the printing processes demonstrated that the image analysis system could, in some cases, simulate human print quality perception. To consolidate on the preceding printing process identification result, a simulation of print quality perception was made. A neural network was trained using observer assessments of a simple pictorial image of a face. These face images were produced using a variety of different non-impact printing techniques. The neural network model was used to predict the outcomes of a further set of assessments of face images by the same observer. The accuracy of the predictions was 23 out of 24 for both the backpropagation and radial basis function neural network functions used in the test. The investigation also produced two possible practical applications for the system. Firstly, it was shown that the system has the potential to be used as a machine that can objectively assess the print quality from photocopiers. Secondly, it was demonstrated that the system might be used for forensic work, since it can identify different printing processes.

The use of the genetic algorithm for shape recognition has been investigated in relation to features along a shape boundary contour. Various methods for encoding chromosomes were investigated, the most successful of which led to the development of a new technique to input normalised 'perceptually important point' features from the contour into a genetic algorithm. Chromosomes evolve with genes defining various ways of 'observing' different parts of the contour. The normalisation process provides the capability for multi-scale spatial frequency filtering and fine/coarse resolution of the contour features. A standard genetic algorithm was chosen for this investigation because its performance can be analysed by applying schema analysis to the genes. A new method for measurement of gene diversity has been developed. It is shown that this diversity measure can be used to direct the genetic algorithm parameters to evolve a number of 'good' chromosomes. In this way a variety of sections along the contour can be observed. A new and effective recognition technique has been developed which makes use of these 'good' chromosomes and the same fitness calculation as used in the genetic algorithm. Correct recognition can be achieved by selecting chromosomes and adjusting two thresholds, the values of which are found not to be critical. Difficulties associated with the calculation of a shape's fitness were analysed and the structure of the genes in the chromosome investigated using schema and epistatic analysis. It was shown that the behaviour of the genetic algorithm is compatible with the schema theorem of J. H. Holland. Reasons are given to explain the minimum value for the mutation probability that is required for the evolution of a number of' good' chromosomes. Suggestions for future research are made and, in particular, it is recommended that the convergence properties of the standard genetic algorithm be investigated.

圖像相似性度量準則是一個傳統的研究領域。大量經典的圖像處理技術被用來為各種類型的圖像設計相似性度量準則，這些圖像包括了線條圖，灰度圖，彩圖以及高動態範圍圖像。儘管已有的度量準則在指定的條件下可以實現優良的圖像相似度比較，這些度量準則極少系統地考慮或檢驗自身與人類視覺感知之間的一致性。而與人類知覺的一致性是由大量實際應用提出的共同需求。隨著三維立體設備的廣泛應用，圖像的相似性已經不只是傳統的可視差別，更包括了人眼利用三維立體設備同時觀看兩張不同的圖片時的視覺可接受度。 / 非嚴謹對準形狀相似性度量準則（AISS）可以比較兩幅具有固定尺寸的線條圖的形狀相似度。對於該度量準則，兩幅待比較圖像的形狀不要求完全對齊，同時，又會考慮到圖像的形變，例如位置，方向和縮放上的變化。 / 雙目觀看舒適度預測器（BVCP）是另一個度量準則。當人的雙眼同時觀看兩幅不同的圖像時，該準則可用以預測視覺的舒適度。根據著名的双眼單视理論，人的視覺可以將兩幅具有細節、對比度以及亮度差別的圖像合成一幅圖像，只要這些差別在限定的程度之內。在計算機圖形學領域，BVCP 首次嘗試去預測雙目的圖像差別會否引起觀看的不舒適。 / 在本論文中，實用的應用程序也被提出用以衡量AISS 和BVCP。AISS 被用在了一個名為“基於結構的ASCII 藝術的應用程序中，該應用程序可以利用ASCII 字符的形狀近似地表現參考圖像的線條結構信息。而BVCP 則被用在一個創新地應用框架中，該框架可以從單幅高動態範圍圖像中生成一組（兩幅）低動態範圍圖像。當這一組低動態範圍圖像組被人的雙眼同時觀看時，可以比傳統的單幅低動態範圍圖像保留更多的人類可感知視覺信息。可信的結果和使用者研究也用來證明SSIM 和BVCP 的有效性以及與人類知覺的一致性。 / Image similarity metric is a traditional research field. Classical image processing techniques are used to design similarity metrics for all kinds of images, such as line drawings, gray or color image and even high-dynamic range (HDR) images. While existing metrics perform well for the tasks of comparing images in specified situations, few of them have systematically considered or examined the consistency with human perception required by practical applications. With the blooming of stereo devices, the similarity to be measured is not only the traditional visual difference between two images, but also the visual acceptance of two images when they are viewed simultaneously with 3D devices. This thesis presents two image similarity metrics motivated by perceptual principles, also with applications to demonstrate their novelty and practical values. / Alignment-Insensitive Shape Similarity Metric (AISS) measures shape similarity of line drawings. This metric can tolerate misalignment between two shapes and, simultaneously, accounts for the differences in transformation such as, position, orientation and scaling. / Binocular Viewing Comfort Predictor (BVCP) is another metric proposed to measure visual discomfort when human's two eyes view two different images simultaneously. According to a human vision phenomenon - binocular single vision, human vision is able tofuse two images with differences in detail, contrast and luminance, up to a certain limit. BVCP makes a first attempt in computer graphics to predict such visual comfort limit. / Applications are also proposed to evaluate AISS and BVCP. AISS is utilized in an application of Structure-based ASCII Art, which approximates line structure of the reference image content with the shapes of ASCII characters. BVCP is utilized in a novel framework - Binocular Tone Mapping which generates a binocular low-dynamic range (LDR) image pair from one HDR image. Such binocular LDR pair can be viewed with stereo devices and can preserve more human-perceivable visual content than traditional one single LDR image. Convincing results and user studies are also shown to demonstrate that both AISS and BVCP are consistent with human perception and effective in practical usage. / 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, Linling. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 122-132). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese. / Abstract --- p.i / Acknowledgement --- p.v / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Alignment-Insensitive Shape Similarity Metric --- p.8 / Chapter 2.1 --- Related Work --- p.10 / Chapter 2.2 --- Design of AISS --- p.13 / Chapter 2.2.1 --- Misalignment Tolerance --- p.14 / Chapter 2.2.2 --- Transformation Awareness --- p.16 / Chapter 2.2.3 --- Parameter Setting --- p.17 / Chapter 2.3 --- Results and Discussion --- p.18 / Chapter 2.4 --- Discussion --- p.20 / Chapter 3 --- Application for AISS: Structure-based ASCII Art --- p.21 / Chapter 3.1 --- Overview --- p.24 / Chapter 3.2 --- Optimization --- p.28 / Chapter 3.3 --- User Study and Discussion --- p.35 / Chapter 3.3.1 --- Metrics Comparison --- p.35 / Chapter 3.3.2 --- Comparison to Existing Work --- p.38 / Chapter 3.3.3 --- User Study --- p.40 / Chapter 3.4 --- Summary --- p.44 / Chapter 4 --- Binocular Viewing Comfort Predictor --- p.48 / Chapter 4.1 --- Background --- p.51 / Chapter 4.2 --- Design of BVCP --- p.54 / Chapter 4.2.1 --- Fusional Area --- p.55 / Chapter 4.2.2 --- Contour Fusion --- p.58 / Chapter 4.2.3 --- Contour and Regional Contrasts --- p.68 / Chapter 4.2.4 --- Failure of Rivalry --- p.70 / Chapter 4.2.5 --- The Overall Fusion Predictor --- p.74 / Chapter 4.3 --- User Study --- p.77 / Chapter 4.4 --- Discussion and Limitations --- p.84 / Chapter 5 --- Application for BVCP: Binocular Tone Mapping --- p.86 / Chapter 5.1 --- Framework --- p.90 / Chapter 5.1.1 --- Overview --- p.90 / Chapter 5.1.2 --- Optimization --- p.93 / Chapter 5.2 --- Results and Discussion --- p.96 / Chapter 5.2.1 --- Results --- p.96 / Chapter 5.2.2 --- User Study --- p.103 / Chapter 5.2.3 --- Incorporating Stereopsis --- p.106 / Chapter 5.2.4 --- Limitations --- p.109 / Chapter 5.3 --- Summary --- p.112 / Chapter 6 --- Conclusion --- p.113 / Chapter A --- User Study for ASCII art --- p.117 / Bibliography --- p.122

The data used by a computer to represent and display a picture conventionally requires very large amounts of dedicated storage. As the trend continues towards high resolution graphics employing a wide range of colours the associated volume of data often expands to a point where sophisticated techniques become essential to maintain a practical interactive system. Considerable research has been conducted into coding schemes which compress the volume of picture data. These methods are clearly of great value in reducing the delay which results from transmitting picture data between sites. Codes which also serve directly as a source for real-time display are better still. The quadtree method of picture encoding, which has previously been successfully employed in the field of picture processing, is shown in this thesis to provide the basis for an integrated approach to data compression in the field of computer graphics. The display of colour pictures from quadtree code is performed by customised hardware which operates in conjunction with a general purpose processor. A prototype system is described which provides efficient downloading of pictures from a host and rapid display of locally stored pictures. The amenability of quadtree code to manipulation is demonstrated by incorporating a limited capability to pan and zoom on a picture. Application of the method to picture archive retrieval is examined.

For face identification, especially by human, it is desirable to render a high-resolution (HR) face image from the low-resolution (LR) one, which is called face hallucination or face super-resolution. A number of super-resolution techniques have been proposed in recent years. However, for face hallucination the utilization of the special properties of the faces is conductive to generate the HR face images. / In this thesis, we propose a new face hallucination framework based on image patches, which integrates two novel statistical super-resolution models. Considering that image patches reflect the combined effect of personal characteristics and patch-location, we first formulate a TensorPatch model based on multilinear analysis to explicitly model the interaction between multiple constituent factors. Motivated by Locally Linear Embedding, we develop an enhanced multilinear patch hallucination algorithm, which efficiently exploits the local distribution structure in the sample space. To better preserve face subtle details, we derive the Coupled PCA algorithm to learn the relation between HR residue and LR residue, which is utilized for compensate the error residue in hallucinated images. Experiments demonstrate that our framework not only well maintains the global facial structures, but also recovers the detailed facial traits in high quality. (Abstract shortened by UMI.) / In this thesis, we propose a novel dimensionality reduction algorithm called graph-regularized projection (GRP) to tackle the problem of semi-supervised dimensionality reduction that is rarely investigated in the literature. Given partially labeled data points, GRP aims at learning a not only smooth but also discriminative projection from high-dimensional data vectors to their latent low-dimensional representations. Motivated by recent semi-supervised learning process: graph regularization, we develop a graph-based regularization framework to enforce smoothness along the graph of the desired projection initiated by margin maximization. As a result, GRP has a natural out-of-sample extension to novel examples and thus can be generalized to the entire high-dimensional space. Extensive experiments on a synthetic dataset and several real databases demonstrate the effectiveness of our algorithm. / Next, this thesis addresses the problem of how to learn an appropriate feature representation from video to benefit video-based face recognition. By simultaneously exploiting the spatial and temporal information, the problem is posed as learning Spatio-Temporal Embedding (STE) from raw videos. STE of a video sequence is defined as its condensed version capturing the essence of space-time characteristics of the video. Relying on the co-occurrence statistics and supervised signatures provided by training videos, STE preserves the intrinsic temporal structures hidden in video volume, meanwhile encodes the discriminative cues into the spatial domain. To conduct STE, we propose two novel techniques, Bayesian keyframe learning and nonparametric discriminant embedding (NDE), for temporal and spatial learning, respectively. In terms of learned STEs, we derive a statistical formulation to the recognition problem with a probabilistic fusion model. On a large face video database containing more than 200 training and testing sequences, our approach consistently outperforms the state-of-the-art methods, achieving a perfect recognition accuracy. / Liu, Wei. / "August 2007." / Advisers: Xiaoou Tang; Jianzhuang Liu. / Source: Dissertation Abstracts International, Volume: 69-02, Section: B, page: 1110. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (p. 140-151). / 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. / Abstract in English and Chinese. / School code: 1307.

No description available.

by Chan Pak Kei, Bernard. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (leaves 125-127). / Chapter 1 --- Introduction --- p.10 / Chapter 1.1 --- Overview --- p.10 / Chapter 1.2 --- Classification Approaches --- p.11 / Chapter 1.3 --- The Use of Neural Network --- p.12 / Chapter 1.4 --- Motivations --- p.14 / Chapter 1.5 --- Organization of Thesis --- p.16 / Chapter 2 --- Related Work --- p.19 / Chapter 2.1 --- Overview --- p.19 / Chapter 2.2 --- Neural Network --- p.20 / Chapter 2.2.1 --- Backpropagation Feedforward Neural Network --- p.20 / Chapter 2.2.2 --- Training of a Backpropagation Feedforward Neural Network --- p.22 / Chapter 2.2.3 --- Single Hidden-layer Model --- p.27 / Chapter 2.2.4 --- Data Preprocessing --- p.27 / Chapter 2.3 --- Fuzzy Sets --- p.29 / Chapter 2.3.1 --- Fuzzy Linear Regression Analysis --- p.29 / Chapter 2.4 --- Network Architecture Altering Algorithms --- p.31 / Chapter 2.4.1 --- Pruning Algorithms --- p.32 / Chapter 2.4.2 --- Constructive/Growing Algorithms --- p.35 / Chapter 2.5 --- Summary --- p.38 / Chapter 3 --- Hybrid Classification Systems --- p.39 / Chapter 3.1 --- Overview --- p.39 / Chapter 3.2 --- Literature Review --- p.41 / Chapter 3.2.1 --- Fuzzy Linear Regression(FLR) with Fuzzy Interval Analysis --- p.41 / Chapter 3.3 --- Data Sample and Methodology --- p.44 / Chapter 3.4 --- Hybrid Model --- p.46 / Chapter 3.4.1 --- Construction of Model --- p.46 / Chapter 3.5 --- Experimental Results --- p.50 / Chapter 3.5.1 --- Experimental Results on Breast Cancer Database --- p.50 / Chapter 3.5.2 --- Experimental Results on Synthetic Data --- p.53 / Chapter 3.6 --- Conclusion --- p.55 / Chapter 4 --- Searching for Suitable Network Size Automatically --- p.59 / Chapter 4.1 --- Overview --- p.59 / Chapter 4.2 --- Literature Review --- p.61 / Chapter 4.2.1 --- Pruning Algorithm --- p.61 / Chapter 4.2.2 --- Constructive Algorithms (Growing) --- p.66 / Chapter 4.2.3 --- Integration of methods --- p.67 / Chapter 4.3 --- Methodology and Approaches --- p.68 / Chapter 4.3.1 --- Growing --- p.68 / Chapter 4.3.2 --- Combinations of Growing and Pruning --- p.69 / Chapter 4.4 --- Experimental Results --- p.75 / Chapter 4.4.1 --- Breast-Cancer Cytology Database --- p.76 / Chapter 4.4.2 --- Tic-Tac-Toe Database --- p.82 / Chapter 4.5 --- Conclusion --- p.89 / Chapter 5 --- Conclusion --- p.91 / Chapter 5.1 --- Recall of Thesis Objectives --- p.91 / Chapter 5.2 --- Summary of Achievements --- p.92 / Chapter 5.2.1 --- Data Preprocessing --- p.92 / Chapter 5.2.2 --- Network Size --- p.93 / Chapter 5.3 --- Future Works --- p.94 / Chapter A --- Experimental Results of Ch3 --- p.95 / Chapter B --- Experimental Results of Ch4 --- p.112 / Bibliography --- p.125