Thesis (M.A.) in Mathematics--University of Maine, 2008. / Includes vita. Includes bibliographical references (leaves 39-40).

Thesis (Ph. D.)--University of Washington, 1999. / Vita. Includes bibliographical references (leaves 79-86).

Thesis (MScIng)--University of Stellenbosch, 2005. / Bibliography. Also available via the Internet.

Thesis (Ph. D.)--Oregon State University, 2008. / Printout. Includes bibliographical references (leaves 140-146). Also available on the World Wide Web.

No description available.

Mirrors are often studied for camera calibration since they provide symmetric relationship for object which can guarantee synchronization in multiple views. However, it is sometimes difficult to compute the reflection matrices of mirrors. This thesis aims to solve the problem of camera calibration and shape recovery from a two-mirror system which is able to generate five views of an object. It firstly studies the similarity relationship of the motion formed by the five views in two-mirror system with the circular motion. It is shown that the motion formed by the five views can be regarded as two circular motions so that we can avoid computing the reflection matrices of mirrors. This thesis then shows the most important problem which is to recover the vanishing line of rotation plane and the imaged circular points by two unknown equal angles via metric rectification. After that, it is easy to recover the imaged rotation axis and the vanishing points X-axis via imaged circular points. Different from the state-of-the-art algorithm, this thesis avoid computing vanishing points X-axis at first because it will cause accumulative error when recovering the imaged rotation axis. By now it is enough to compute the camera intrinsics which is the main objective of this thesis. At last, a 3D visual hull model of object could be reconstructed once all the projective matrices of views were computed. This thesis uses a short video instead of static snapshots so that the reconstructed 3D visual hull model of each frame can be put together based on the motion sequence of object to make a 3D animation. This animation can help to boost the accuracy of action recognition in contrast to 2D video. In general, the action recognition by 2D videos always distinguishes action according to the side of human taken by videos but cannot do for the side does not appear in videos. It then requires to store every direction for human actions of video into database which causes redundancy. The 3D animation can deal with this problem since the reconstructed model can be seen in every direction so that only one 3D animation of human action is needed to store in database. The experimental results show that the more frames are used, the less error of camera intrinsics will occur and the reconstructed 3D model shows the feasibility of the approach.

The time required to identify a common object depends on several factors, especially pre-existing knowledge and episodic representations newly established as a result of a prior study. My research examined how these factors contribute to identification of objects (both studied and non-studied) and to performance on explicit memory tests. The overall goal was to explore the link between memory and object perception. One series of experiments examined influences due to object orientation in the plane of the page. Subjects were shown color photos of objects, and memory was assessed either with an old/new recognition test or with a test that required them to identify objects that were slowly faded in on a computer monitor. The critical variables were the type of photo — each showing either an object with a predominant or cardinal orientation (e.g., helicopter) or a non-cardinal object (e.g., pencil), and the orientation at which the photos were displayed at study and at test (e.g., rotated 0°, 120°, or 240°). For non-studied targets, identification test performance showed a large effect due to display orientation, but only for cardinal objects. For studied targets, study-to-test changes in orientation influenced priming for both non-cardinal and cardinal objects, but orientation specific priming effects (larger priming when study and test orientations matched rather than mismatched) were much larger with cardinal than non-cardinal objects, especially, when their display orientation, at test was unusual (i.e., 120°, 240°). A second series of experiments examined influences due to object size (size of an object presented alone) and relative size (size of an object relative to another object). Size manipulations had a large effect on identification of non-studied objects but study-to- test changes in size had only a minimal effect on priming. In contrast, study1to-test changes in relative size influenced recognition decision speed which is an index of priming. The combined findings suggest that both semantic and episodic representations behave as if they coded orientation but only for cardinal objects. They also suggest that episodic representations code relative size but not size information. The findings are explained by the instance views of memory. / Arts, Faculty of / Psychology, Department of / Graduate

A real-time character recognition system was developed to recognize upper case handprinted characters in a real-time small machine environment. The recognition system consists of two major components: namely, a data acquisition system and a pattern recognition system. The data acquisition system was designed and implemented to allow the real world data flow into the computer from a COMPUTER writing tablet in real time. The pattern recognition system was also designed and implemented to yield a decision on the input character in real time (user time). A curve optimization technique originally devised by Reumann and Witkam was modified to extract only the significant data that describes a character. Computations were minimized through mathematical simplifications, hardware-software trade-off, and special programming techniques at the machine level. In addition, the preprocessor operated concurrently with the data acquisition routine to reduce data storage requirements as well as to-provide fast response to handprinted inputs. A non-uniform quantization plane was proposed and implemented to discriminate pen directions. Stroke patterns of a character were recognized using a syntactic approach. Finally, recognized stroke patterns within a character were classified as one of the known pattern classes by two classification methods: dictionary look-up and a modified nearest neighbor rule, both guided by special geometric measurements on some character pairs. Character patterns were defined in the dictionary such that no user training or personalized dictionary is required for future use. A test was conducted using the ACM proposed upper case handprinted character set and a recognition rate of 98.3% was obtained from over 2300 characters of sizes varying from 1/4 inch tall to 3/4 inch tall from 10 people. It Is observed that the approach taken in this thesis can also be applied to recognized handprinted patterns other than the standard one proposed by the ACM. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

This dissertation presents the development and performance of a few algorithms used for automated scene matching. The objective is to recognise and predict the location of a template (reference image) inside a degraded scene image (sensed image). A set of perspective, projective optical images of relatively well defined man-made objects located in areas of varying background is used as database. Perturbations to the grey levels of the image cause artefacts that easily destroy the unique match location and generate false fixes. Therefore, suitable enhancement and noise removal techniques are applied first. Several different types of features are investigated to decide upon those that are best suited to describe the original content of the scene. Statistical features, such as invariant moments are chosen for one of the algorithms, Multibcmd Ima^e using Moments (MBIMOM). The second one, Spatial Multiband Image (SMBI) algorithm, uses the spatial correlation of the pixels within a neighbourhood as initial descriptive features. Each algorithm uses either Principal Components transform or Maximum Noise Fraction transform for dimensionality and noise reduction. A normalised correlation coefficient of 1.00 was achieved by the SMBI algorithm. The final design of the algorithms is a trade-off between speed and accuracy.

No description available.