A fundamental problem in machine vision is the classifcation of objects which may have unknown position, orientation, or a combination of these and other transformations. The massive amount of data required to accurately form an appearance-based model of an object under all values of shift and rotation transformations has discouraged the incorporation of the combination of both transformations into a single model representation. This Master's Thesis documents the theory and implementation of a hierarchical classifier, named the Information Theoretic Decision Tree system, which has the demonstrated ability to form appearance-based models of objects which are shift and rotation invariant which can be searched with a great reduction in evaluations over a linear sequential search. Information theory is utilized to obtain a measure of information gain in a feature space recursive segmentation algorithm which positions hyperplanes to local information gain maxima. This is accomplished dynamically through a process of local optimization based on a conjugate gradient technique enveloped by a simulated annealing optimization loop. Several target model training strategies have been developed for shift and rotation invariance, notably the method of exemplar grouping, in which any combination of rotation and translation transformations of target object views can be simulated and folded into the appearance-based model. The decision tree structure target models produced as a result of this process effciently represent the voluminous training data, according rapid test-time classification of objects.

In recent years there has been great interest in implementing object recognition frame work on mobile phones. This has stemmed from the fact the advances in object recognition algorithm and mobile phone capabilities have built a congenial ecosystem. Application developers on mobile platforms are trying to utilize the object recognition technology to build better human computer interfaces. This approach is in the nascent phase and proper application framework is required. In this thesis, we propose a framework to overcome design challenges and provide an evaluation methodology to assess the system performance. We use the emerging Android mobile platform to implement and test the framework. We performed a case study using the proposal and reported the test result. This assessment will help developers make wise decisions about their application design. Furthermore, the Android API developers could use this information to provide better interfaces to the third party developers. The design and evaluation methodology could be extended to other mobile platforms for a wider consumer base. / by Vivek Kumar Tyagi. / Thesis (M.S.C.S.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

This work explores the process of model-based classification of speech audio signals using low-level feature vectors. The process of extracting low-level features from audio signals is described along with a discussion of established techniques for training and testing mixture model-based classifiers and using these models in conjunction with feature selection algorithms to select optimal feature subsets. The results of a number of classification experiments using a publicly available speech database, the Berlin Database of Emotional Speech, are presented. This includes experiments in optimizing feature extraction parameters and comparing different feature selection results from over 700 candidate feature vectors for the tasks of classifying speaker gender, identity, and emotion. In the experiments, final classification accuracies of 99.5%, 98.0% and 79% were achieved for the gender, identity and emotion tasks respectively. / by Chris Thoman. / Thesis (M.S.C.S.)--Florida Atlantic University, 2009. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2009. Mode of access: World Wide Web.

by Lin Feng. / "June 2003." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2003. / Includes bibliographical references (p. [114]-130). / 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. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

Basic technologies for fingerprint feature extraction and matching have been improved to such a stage that they can be embedded into commercial Automatic Fingerprint Verification Systems (AFVSs). However, the reliability of AFVSs has kept attracting concerns from the society since AFVSs do fail occasionally due to difficulties like problematic fingers, changing environments, and malicious attacks. Furthermore, the absence of a solid theoretical foundation for evaluating AFVSs prevents these failures from been predicted and evaluated. Under the traditional empirical AFVS evaluation framework, repeated verification experiments, which can be very time consuming, have to be performed to test whether an update to an AFVS can really lead to an upgrade in its performance. Also, empirical verification results are often unable to provide deeper understanding of AFVSs. To solve these problems, we propose a novel statistical evaluation model for minutiae-based AFVSs based on the understanding of fingerprint minutiae patterns. This model can predict the verification performance metrics as well as their confidence intervals. The analytical power of our evaluation model, which makes it superior to empirical evaluation methods, can assist system developers to upgrade their AFVSs purposefully. Also, our model can facilitate the theoretical analysis of the advantages and disadvantages of various fingerprint verification techniques. We verify our claims through different and extensive experiments. / Chen, Jiansheng. / "November 2006." / Adviser: Yiu-Sang Moon. / Source: Dissertation Abstracts International, Volume: 68-08, Section: B, page: 5343. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (p. 110-122). / 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.

by Jian-Zhuang Liu. / Thesis (Ph.D.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (p. 183-196). / Microfiche. Ann Arbor, Mich.: UMI, 1998. 3 microfiches ; 11 x 15 cm.

by Law Tak Ming. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1996. / Includes bibliographical references (leaves 91-96). / by Law Tak Ming. / Chapter 1. --- INTRODUCTION --- p.1 / Chapter 1.1 --- The Structure of Chinese Characters --- p.3 / Chapter 1.1.1 --- Pixels (像素) --- p.4 / Chapter 1.1.2 --- Strokes (筆劃) --- p.4 / Chapter 1.1.3 --- Basic Stroke Types (Segment Type)基本筆劃（筆段) --- p.4 / Chapter 1.1.4 --- Compound-segment Stroke (複合筆劃) --- p.5 / Chapter 1.1.5 --- Total Stroke types --- p.6 / Chapter 1.1.6 --- Stroke Sequence (筆順) --- p.6 / Chapter 1.1.7 --- Segments as Basic Features --- p.7 / Chapter 1.1.8 --- Geographic Structure of Components --- p.7 / Chapter 1.2 --- Stroke Distribution of Chinese Characters --- p.10 / Chapter 1.3 --- Radical --- p.10 / Chapter 1.4 --- The Comparison between ON-line and Off-line Chinese Character Recognition Approach --- p.11 / Chapter 1.5 --- Commercial Product Comparison --- p.14 / Chapter 1.6 --- Related Works --- p.17 / Chapter 1.7 --- Objectives --- p.29 / Chapter 2. --- PREPROCESSING --- p.31 / Chapter 2.1 --- Smoothing and Sampling --- p.32 / Chapter 2.2 --- Interpolation --- p.34 / Chapter 2.3 --- DEHOOKING --- p.37 / Chapter 2.4 --- Stroke Segmentation --- p.39 / Chapter 3. --- DATA LEARNING --- p.41 / Chapter 3.1 --- Definition of Terms --- p.41 / Chapter 3.2 --- Definition of Direction type --- p.42 / Chapter 3.3 --- Data Base Structure --- p.43 / Chapter 3.4 --- Learning Algorithms of Segments --- p.45 / Chapter 3.4.1 --- Learning of the Coordinates --- p.48 / Chapter 3.4.2 --- Learning of Direction Type --- p.48 / Chapter 3.4.3 --- Learning of Slope Angle --- p.50 / Chapter 3.5 --- Learning of the Tolerance of Coordinate --- p.50 / Chapter 3.6 --- Stroke Relation Coding --- p.51 / Chapter 4. --- PRECLASSIFICATION --- p.54 / Chapter 4.1 --- Decision Path Classification --- p.56 / Chapter 4.2 --- First-Two-Ending-One Classification Method --- p.57 / Chapter 4.3 --- Stroke Type Matching Algorithm --- p.61 / Chapter 5. --- RECOGNITION STAGE --- p.64 / Chapter 5.1 --- Connected Strokes Handling --- p.65 / Chapter 5.2 --- Stroke Sequence Free Matching Algorithm --- p.70 / Chapter 5.3 --- Preliminary Character Distance Measure --- p.72 / Chapter 5.4 --- Detailed Matching Techniques --- p.74 / Chapter 5.5 --- Segments Sequence Within a Compound-segment Stroke Compatibility --- p.75 / Chapter 5.5.1 --- Length and Slope Orientation Similarities --- p.78 / Chapter 5.5.2 --- Segment Similarity Measure Function --- p.79 / Chapter 5.6 --- Stroke Relation Influences --- p.79 / Chapter 5.7 --- Final Character Similarity Measure --- p.81 / Chapter 6. --- RESULTS AND CONCLUSIONS --- p.83 / Chapter 6.1 --- Experiment Results --- p.83 / Chapter 6.2 --- Analysis --- p.85 / Chapter 6.3 --- Conclusion --- p.87

A new algorithm is proposed which uses the Hough Transform to recognize two dimensional objects independent of their orientations, sizes and locations. The binary image of an object is represented by a set of straight lines. Features of the straight lines, namely the lengths and the angles of their normals, their lengths and the end point positions are extracted using the Hough Transform. A data structure for the extracted lines is constructed so that it is efficient to match the features of the lines of one object to those of another object, and determine if one object is a rotated and/or scaled version of the other. Finally a generalized Hough Transform is used to match the end points of the two sets of lines. The simulation experiments show good results for objects with significant linear features .

For the last several years, convolutional neural network (CNN) based object detection systems have used a regression technique to predict improved object bounding boxes based on an initial proposal using low-level image features extracted from the CNN. In spite of its prevalence, there is little critical analysis of bounding-box regression or in-depth performance evaluation. This thesis surveys an array of techniques and parameter settings in order to further optimize bounding-box regression and provide guidance for its implementation. I refute a claim regarding training procedure, and demonstrate the effectiveness of using principal component analysis to handle unwieldy numbers of features produced by very deep CNNs.

In the design of autonomous mobile robots, databases have been used mainly to store information on the environment in which the device is to operate. For most of the models and ready systems, the database when used, is not a stand alone component in the system, rather it is only intended to keep static information on the disposition and properties of objects on the map.