Thesis (M.S.)--University of Alabama at Birmingham, 2007. / Description based on contents viewed Oct. 6, 2008; title from PDF t.p. Includes bibliographical references (p. 51-52).

Thesis (M.A.)--York University, 2003. Graduate Programme in Psychology. / Typescript. Includes bibliographical references (leaves 102-107). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://wwwlib.umi.com/cr/yorku/fullcit?pMQ82940.

Thesis (Ph. D.)--University of California, San Diego, 1999. / Vita. Includes bibliographical references.

Thesis (Ph. D.)--University of Alabama at Birmingham, 2006. / Description based on contents viewed Jan. 24, 2007; title from title screen. Includes bibliographical references (p. 125-129).

Face recognition, although being a popular area of research for over a decade has still many open research challenges. Some of these challenges include the recognition of poorly illuminated faces, recognition under pose variations and also the challenge of capturing sufficient training data to enable recognition under pose/viewpoint changes. With the appearance of cheap and effective multimodal image capture hardware, such as the Microsoft Kinect device, new possibilities of research have been uncovered. One opportunity is to explore the potential use of the depth maps generated by the Kinect as an additional data source to recognize human faces under low levels of scene illumination, and to generate new images through creating a 3D model using the depth maps and visible-spectrum/RGB images that can then be used to enhance face recognition accuracy by improving the training phase of a classification task. With the goal of enhancing face recognition, this research first investigated how depth maps, since not affected by illumination, can improve face recognition, if algorithms traditionally used in face recognition were used. To this effect a number of popular benchmark face recognition algorithms are tested. It is proved that algorithms based on LBP and Eigenfaces are able to provide high level of accuracy in face recognition due to the significantly high resolution of the depth map images generated by the latest version of the Kinect device. To complement this work a novel algorithm named the Dense Feature Detector is presented and is proven to be effective in face recognition using depth map images, in particular under wellilluminated conditions. Another technique that was presented for the goal of enhancing face recognition is to be able to reconstruct face images in different angles, through the use of the data of one frontal RGB image and the corresponding depth map captured by the Kinect, using faster and effective 3D object reconstruction technique. Using the Overfeat network based on Convolutional Neural Networks for feature extraction and a SVM for classification it is shown that a technically unlimited number of multiple views can be created from the proposed 3D model that consists features of the face if captured real at similar angles. Thus these images can be used as real training images, thus removing the need to capture many examples of a facial image from different viewpoints for the training of the image classifier. Thus the proposed 3D model will save significant amount of time and effort in capturing sufficient training data that is essential in recognition of the human face under variations of pose/viewpoint. The thesis argues that the same approach can also be used as a novel approach to face recognition, which promises significantly high levels of face recognition accuracy base on depth images. Finally following the recent trends in replacing traditional face recognition algorithms with the effective use of deep learning networks, the thesis investigates the use of four popular networks, VGG-16, VGG-19, VGG-S and GoogLeNet in depth maps based face recognition and proposes the effective use of Transfer Learning to enhance the performance of such Deep Learning networks.

Active illumination systems use a controllable light source and a light sensor to measure properties of a scene. For such a system to work reliably across a wide range of environments it must be able to handle the effects of global light transport, bright ambient light, interference from other active illumination devices, defocus, and scene motion. The goal of this thesis is to develop computational techniques and hardware arrangements to make active illumination devices based on commodity-grade components that work under real world conditions. We aim to combine the robustness of a scanning laser rangefinder with the speed, measurement density, compactness, and economy of a consumer depth camera. Towards this end, we have made four contributions. The first is a computational technique for compensating for the effects of motion while separating the direct and global components of illumination. The second is a method that combines triangulation and depth from illumination defocus cues to increase the working range of a projector-camera system. The third is a new active illumination device that can efficiently image the epipolar component of light transport between a source and sensor. The device can measure depth using active stereo or structured light and is robust to many global light transport effects. Most importantly, it works outdoors in bright sunlight despite using a low power source. Finally, we extend the proposed epipolar-only imaging technique to time-of-flight sensing and build a low-power sensor that is robust to sunlight, global illumination, multi-device interference, and camera shake. We believe that the algorithms and sensors proposed and developed in this thesis could find applications in a diverse set of fields including mobile robotics, medical imaging, gesture recognition, and agriculture.

No description available.

The growth of barrier-type anodic alumina films formed by anodizing relatively rough substrates has been shown to proceed by high field ionic conduction. As a result of the ionic transport and the induced plasticity, smoothing of the oxide surfaces and the metal/oxide interfaces arises. However, such a smoothing model was deduced from topographical observations and, therefore little insight was gained about the transport mechanism leading to the flattening of the anodized specimens. Recently, the development of porous anodic alumina has been demonstrated to proceed by coupled ionic migration and material flow resulting from the field-induced mechanical stress. For rough metal surfaces, the electric field distribution is non-uniform across the specimen surface. Considering the square-dependence of the electrostrictive stress on the electric field and the distribution of the electric field across surface, a significant gradient of mechanical stress may arise across the anodic oxide layer during anodizing. As a result, stress-driven transport may participate, in addition to high field ionic conduction, to the smoothing of the specimen surface. Transport mechanisms were investigated during anodizing of patterned superpure aluminium specimens, by examination of the distributions of incorporated species, used as markers and tracers. The nature of the migration processes have been determined in correlation with the changes in the concentration of the tracer profiles as well as the variations in the anodic oxide film compositions.

In arid lands, a major contribution to water loss is by soil water evaporation. Desert sand dunes in arid regions are devoid of runoff and have high rates of infiltration. Rainwater is commonly stored within them because of the low permeability soils in the underlying desert pavement. In such cases, moisture is confined in the sand dune below a depth, termed as the “extinction depth”, where it is protected from evaporation during long dry periods. Moreover, desert sand dunes have sparse vegetation, which results in low transpiration losses from the stored water. The water accumulated below the extinction depth of the sand dunes can be utilized for various purposes such as in irrigation to support desert agriculture. In this study, field experiments were conducted in Western Saudi Arabia to monitor the soil moisture gradients and determine the diffusive extinction depth of dune sand. The dune sand was saturated with water and was exposed to natural conditions (evaporation and precipitation). The decline of the water level in the sand column was continuously recorded using transducers and sensors installed at different depths monitored the temporal variation of temperature and moisture content within the sand. The hydrological simulator HYDRUS-1D was used to construct the vertical profiles of soil water content and temperature and the results obtained from HYDRUS-1D were compared to the gradients monitored by the sensors.

Calculations of fluvial flows are strongly influenced by geometry complexity and large overall uncertainty on every single measurable property, such as velocity and shear. Moreover, a considerable portion of the data obtained from computational simulations arose from two-dimensional, steady-state models. The present work states a different approach to perform computer-based simulations and analyze fluvial flows. For the first part, the suitability of OpenFOAM to be used as the main CFD solver to analyze fluvial flows is studied. Initially, two well documented channel configurations are computationally studied using OpenFOAM. Finally, these results are compared to the output obtained from one of the widely used quasi-3D CFD solvers used to perform studies about environmental hydraulics.