This thesis is concerned with fundamental algorithms for estimating parameters of geometric models that are particularly relevant to computer vision. A general framework is considered which accommodates several important problems involving estimation in a maximum likelihood setting. By considering a special form of a commonly used cost function, a new, iterative, estimation method is evolved. This method is subsequently expanded to enable incorporation of a so-called ancillary constraint. An important feature of these methods is that they can serve as a basis for conducting theoretical comparison of various estimation approaches. Two specific applications are considered: conic fitting, and estimation of the fundamental matrix (a matrix arising in stereo vision). In the case of conic fitting, unconstrained methods are first treated. The problem of producing ellipse-specific estimates is subsequently tackled. For the problem of estimating the fundamental matrix, the new constrained method is applied to generate an estimate which satisfies the necessary rank-two constraint. Other constrained and unconstrained methods are compared within this context. For both of these example problems, the unconstrained and constrained methods are shown to perform with high accuracy and efficiency. The value of incorporating covariance information characterising the uncertainty of measured image point locations within the estimation process is also explored. Covariance matrices associated with data points are modelled, then an empirical study is made of the conditions under which covariance information enables generation of improved parameter estimates. Under the assumption that covariance information is, in itself, subject to estimation error, tests are undertaken to determine the effect of imprecise information upon the quality of parameter estimates. Finally, these results are carried over to experiments to assess the value of covariance information in estimating the fundamental matrix from real images. The use of such information is shown to be of potential benefit when the measurement process of image features is considered. / Thesis (Ph.D.)--School of Computer Science, 2004.

Thesis (Ph. D.)--University of Hong Kong, 2006. / Title proper from title frame. Also available in printed format.

<p>It is difficult for people to recognize currencies from different countries. Our aim is to help people solve this problem. However, currency recognition systems that are based on image analysis entirely are not sufficient. Our system is based on image processing and makes the process automatic and robust. We use SEK and Chinese RMB as examples to illustrate the technique. Color and shape information are used in our algorithm.</p>

To interface between the one-dimensional scanning of an image, and the applications of a two-dimensional operator, an intermediate storage is required. For a square image of size n2, and a square operator of size m2, the minimum intermediate storage is shown to be n .(m-1). An interface of this size can be conveniently realized by using a serpentine delay line. New kinds of imagers would be required to reduce the size of the intermediate storage below n.(m-1).

Thesis (Ph.D.)--Hong Kong University of Science and Technology, 2007. / Includes bibliographical references (leaves 139-148). Also available in electronic version.

Thesis (Ph.D)--Stanford University, 1999. / Title from pdf t.p. (viewed May 9, 2002). "May 1999." "Adminitrivia V1/Prg/19990823"--Metadata.

Thesis (M.S.)--University of Missouri-Columbia, 2006. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file viewed on (February 23, 2007) Includes bibliographical references.

Thesis (Ph. D.)--University of Texas at Austin, 2006. / Vita. Includes bibliographical references.

Thesis (Ph. D.)--Carnegie-Mellon University, 1982. / "CMU-RI-TR-82-7." Includes bibliographical references (p. 221-226).

Image-based face recognition has attained wide applications during the past decades in commerce and law enforcement areas, such as mug shot database matching, identity authentication, and access control. Existing face recognition techniques (e.g., Eigenface, Fisherface, and Elastic Bunch Graph Matching, etc.), however, do not perform well when the following case inevitably exists. The case is that, due to some variations in imaging conditions, e.g., pose and illumination changes, face images of the same person often have different appearances. These variations make face recognition techniques much challenging. With this concern in mind, the objective of my research is to develop robust face recognition techniques against variations. This thesis addresses two main variation problems in face recognition, i.e., pose and illumination variations. To improve the performance of face recognition systems, the following methods are proposed: (1) a face feature extraction and representation method using non-uniformly selected Gabor convolution features, (2) an illumination normalization method using adaptive region-based image enhancement for face recognition under variable illumination conditions, (3) an eye detection method in gray-scale face images under various illumination conditions, and (4) a virtual pose generation method for pose-invariant face recognition. The details of these proposed methods are explained in this thesis. In addition, we conduct a comprehensive survey of the existing face recognition methods. Future research directions are pointed out.