Thesis (Ph. D.)--Florida State University, 2006. / Advisor: Xiuwen Liu, Florida State University, College of Arts and Sciences, Dept. of Computer Science. Title and description from dissertation home page (viewed Sept. 20, 2006). Document formatted into pages; contains xi, 109 pages. Includes bibliographical references.

Thesis (M.S.)--Rochester Institute of Technology, 2006. / Typescript. Includes bibliographical references (leaves 76-78).

Thesis (Ph. D.)--Lehigh University, 2006. / Includes vita. Includes bibliographical references (leaves 114-124).

Masters of Science / The SASL project at the University of the Western Cape aims at developing a fully automated translation system between English and South African Sign Language (SASL). Three important aspects of this system require SASL documentation and knowledge. These are: recognition of SASL from a video sequence, linguistic translation between SASL and English and the rendering of SASL. Unfortunately, SASL documentation is a scarce resource and no official or complete documentation exists. This research focuses on creating an online collaborative video annotation knowledge management system for SASL where various members of the community can upload SASL videos to and annotate them in any of the sign language notation systems, SignWriting, HamNoSys and/or Stokoe. As such, knowledge about SASL structure is pooled into a central and freely accessible knowledge base that can be used as required. The usability and performance of the system were evaluated. The usability of the system was graded by users on a rating scale from one to five for a specific set of tasks. The system was found to have an overall usability of 3.1, slightly better than average. The performance evaluation included load and stress tests which measured the system response time for a number of users for a specific set of tasks. It was found that the system is stable and can scale up to cater for an increasing user base by improving the underlying hardware. / South Africa

Masters of Science / Recognising and estimating gestures is a fundamental aspect towards translating from a sign language to a spoken language. It is a challenging problem and at the same time, a growing phenomenon in Computer Vision. This thesis presents two approaches, an example-based and a learning-based approach, for performing integrated detection, segmentation and 3D estimation of the human upper body from a single camera view. It investigates whether an upper body pose can be estimated from a database of exemplars with labelled poses. It also investigates whether an upper body pose can be estimated using skin feature extraction, Support Vector Machines (SVM) and a 3D human body model. The example-based and learning-based approaches obtained success rates of 64% and 88%, respectively. An analysis of the two approaches have shown that, although the learning-based system generally performs better than the example-based system, both approaches are suitable to recognise and estimate upper body poses in a South African sign language recognition and translation system. / South Africa

Masters of Science / This thesis presents a system for performing whole gesture recognition for South African Sign Language. The system uses feature vectors combined with Hidden Markov models. In order to constuct a feature vector, dynamic segmentation must occur to extract the signer's hand movements. Techniques and methods for normalising variations that occur when recording a signer performing a gesture, are investigated. The system has a classification rate of 69%. / South Africa

M.Ing. / Nearest neighbour classifiers are well suited for use in practical pattern recognition applications for a number of reasons, including ease of implementation, rapid training, justifiable decisions and low computational load. However their generalisation performance is perceived to be inferior to that of more complex methods such as neural networks or support vector machines. Closer inspection shows however that the generalisation performance actually varies widely depending on the dataset used. On certain problems they outperform all other known classifiers while on others they fail dismally. In this thesis we allege that their sensitivity to the metric used is the reason for their mercurial performance. We also discuss some of the remedies for this problem that have been suggested in the past, most notably the variable-kernel similarity metric learning technique, and introduce our own extension to this technique. Finally these metric learning techniques are evaluated on an aircraft recognition task and critically compared.

Magister Scientiae - MSc / Much work has been done in building systems that can recognize gestures, e.g. as a component of sign language recognition systems. These systems typically use whole gestures as the smallest unit for recognition. Although high recognition rates have been reported, these systems do not scale well and are computationally intensive. The reason why these systems generally scale poorly is that they recognize gestures by building individual models for each separate gesture; as the number of gestures grows, so does the required number of models. Beyond a certain threshold number of gestures to be recognized, this approach become infeasible. This work proposed that similarly good recognition rates can be achieved by building models for subcomponents of whole gestures, so-called cheremes. Instead of building models for entire gestures, we build models for cheremes and recognize gestures as sequences of such cheremes. The assumption is that many gestures share cheremes and that the number of cheremes necessary to describe gestures is much smaller than the number of gestures. This small number of cheremes then makes it possible to recognized a large number of gestures with a small number of chereme models. This approach is akin to phoneme-based speech recognition systems where utterances are recognized as phonemes which in turn are combined into words. / South Africa

A long standing debate in computer vision community concerns the link between segmentation and recognition. The question I am trying to answer here is, Does image segmentation as a preprocessing step help image recognition? In spite of a plethora of the literature to the contrary, some authors have suggested that recognition driven by high quality segmentation is the most promising approach in image recognition because the recognition system will see only the relevant features on the object and not see redundant features outside the object (Malisiewicz and Efros 2007; Rabinovich, Vedaldi, and Belongie 2007). This thesis explores the following question: If segmentation precedes recognition, and segments are directly fed to the recognition engine, will it help the recognition machinery? Another question I am trying to address in this thesis is of scalability of recognition systems. Any computer vision system, concept or an algorithm, without exception, if it is to stand the test of time, will have to address the issue of scalability.

Indiana University-Purdue University Indianapolis (IUPUI) / One of the biggest hurdles to the development of an effective driver state monitor is the that there is no real-time eye-gaze detection. This is primarily due to the fact that such systems require calibration. In this thesis the various aspects that comprise an eye gaze tracker are investigated. From that we developed an eye gaze tracker for automobiles that does not require calibration. We used a monocular camera system with IR light sources placed in each of the three mirrors. The camera system created the bright-pupil effect for robust pupil detection and tracking. We developed an SVM based algorithm for initial eye candidate detection; after that the eyes were tracked using a hybrid Kalman/Mean-shift algorithm. From the tracked pupils, various features such as the location of the glints (reflections in the pupil from the IR light sources) were extracted. This information is then fed into a Generalized Regression Neural Network (GRNN). The GRNN then maps this information into one of thirteen gaze regions in the vehicle.