No description available.

There is no abstract available for this thesis. / Department of Computer Science

A topic of computer vision that has been recently studied by a substantial number of scientists is the recognition of objects in digitized gray scale images. The primary goal of model-based object recognition research is the efficient and precise matching of features extracted from sensory data with the corresponding features in an object model database. A source of difficulty during the feature extraction is the determination and representation of pertinent attributes from the sensory data of the objects in the image. In addition, features which are visible from a single vantage point are not usually adequate for the unique identification of an object and its orientation. This paper will describe a regimen that can be used to address these problems. Image preprocessing such as edge detection, image thinning, thresholding, etc., will first be addressed. This will be followed by an in depth discussion that will center upon the extraction of local geometric feature vectors and the hypothesis-verification model used for two dimensional object recognition. / Department of Computer Science

In this thesis, we propose a new method for content-aware resizing of videos in real- time. Our approach consists of two steps. First, we compute a set of non-salient pixels in linear time which, when being removed or duplicated, do not alter the general appearance of the video. This is an extension of Avidan and Shamir's [3] greedy seam-carving approach to video. Second, we generate a new representation of the video, so called multi-view videos that allow us to resize the video in real-time, i.e. while being watched. This representation can be computed very effciently, the complexity is linear in the number of frames and linear in the number of pixels in a video. Our technique works on a broad variety of videos and is computationally inexpensive enough to be executed by a vast range of devices. We compare our technique to our own implementation of a current state-of-the-art approach and show several convincing results obtained by our technique.

In this thesis we extend the Mumford-Shah model and propose a new region merging algorithm for image segmentation. The segmentation problem is to determine an optimal partition of an image into constituent regions such that individual regions are homogenous within and adjacent regions have contrasting properties. By optimimal, we mean one that minimizes a particular energy functional. In region merging, the image is initially divided into a very fine grid, with each pixel being a separate region. Regions are then recursively merged until it is no longer possible to decrease the energy functional. In 1994, Koepfler, Lopez and Morel developed a region merging algorithm for segmentating an image. They consider the piecewise constant Mumford-Shah model, where the energy functional consists of two terms, accuracy versus complexity, with the trade - off controlled by a scale parameter. They show that one can efficiently generate a hierarchy of segmentations from coarse to fine. This algorithm is complemented by a sound theoretical analysis of the piecewise constant model, due to Morel and Solimini. The primary motivation for extending the Mumford-Shah model stems from the fact that this model is only suitable for " cartoon " images, where each region is uncomtaminated by any form of noise. Other shortcomings also need to be addressed. In the algorithm of Koepfler et al., it is difficult to determine the order in which the regions are merged and a " schedule " is required in order to determine the number and fine - ness of segmentations in the hierarchy. Both of these difficulties mitigate the theoretical analysis of Koepfler ' s algorithm. There is no definite method for selecting the " optimal " value of the scale parameter itself. Furthermore, the mathematical analysis is not well understood for more complex models. None of these issues are convincingly answered in the literature. This thesis aims to provide some answers to the above shortcomings by introducing new techniques for region merging algorithms and a better understanding of the theoretical analysis of both the mathematics and the algorithm ' s performance. A review of general segmentation techniques is provided early in this thesis. Also discussed is the development of an " extended " model to account for white noise contamination of images, and an improvement of Koepfler ' s original algorithm which eliminates the need for a schedule. The work of Morel and Solimini is generalized to the extended model. Also considered is an application to textured images and the issue of selecting the value of the scale parameter. / Thesis (Ph.D.)--School of Mathematical Sciences, 2005.

Thesis (M. S.)--Electrical and Computer Engineering, Georgia Institute of Technology, 2008. / Committee Chair: Russell Mersereau; Committee Member: Anthony J. Yezzi; Committee Member: Yucel Altunbasak.

Thesis (M.Sc.)--York University, 2006. Graduate Programme in Computer Science. / Typescript. Includes bibliographical references (leaves 128-137). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:MR29550

Thesis (M. S.)--Computing, Georgia Institute of Technology, 2009. / Committee Chair: Essa, Irfan; Committee Member: Dellaert, Frank; Committee Member: Turk, Greg. Part of the SMARTech Electronic Thesis and Dissertation Collection.

No description available.

No description available.