This thesis summarises research on the improved design, integration and expansion of past cortex-like computer vision models, following biologically-inspired methodologies. By adopting early theories and algorithms as a building block, particular interest has been shown for algorithmic parameterisation, feature extraction, invariance properties and classification. Overall, the major original contributions of this thesis have been: 1. The incorporation of a salient feature-based method for semantic feature extraction and refinement in object recognition. 2. The design and integration of colour features coupled with the existing morphological-based features for efficient and improved biologically-inspired object recognition. 3. The introduction of the illumination invariance property with colour constancy methods under a biologically-inspired framework. 4. The development and investigation of rotation invariance methods to improve robustness and compensate for the lack of such a mechanism in the original models. 5. Adaptive Gabor filter design that captures texture information, enhancing the morphological description of objects in a visual scene and improving the overall classification performance. 6. Instigation of pioneering research on Spiking Neural Network classification for biologically-inspired vision. Most of the above contributions have also been presented in two journal publications and five conference papers. The system has been fully developed and tested in computers using MATLAB under a variety of image datasets either created for the purposes of this work or obtained from the public domain. / © Cranfield University

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

Hand gesture recognition is an expansive and evolving field. Previous work addresses methods for tracking hand gestures primarily with specialty gaming/desktop environments in real time. The method proposed here focuses on enhancing performance for mobile GPU platforms with restricted resources by limiting memory use/transfers and by reducing the need for code branches. An encoding scheme has been designed to allow contour processing typically used for finding fingertips to occur efficiently on a GPU for non-touch, remote manipulation of on-screen images. Results show high resolution video frames can be processed in real time on a modern mobile consumer device, allowing for fine grained hand movements to be detected and tracked. / Graduate

M.Ing. / A machine vision system must, by definition, be intelligent, adaptable and reliable to satisfY the objectives of a system that is highly interactive with its dynamic environment and therefore prone to outside error factors. A machine vision system is described that utilizes a 2D captured web cam image for the purpose of intelligent object recognition, gripping and handling. The system is designed to be generic in its application and adaptable to various gripper configurations and handling configurations. This is achieved by using highly adaptable and intelligent recognition algorithms the gathers as much information as possible from a 2D colour web cam image. Numerous error-checking abilities are also built into the system to account for possible anomalies in the working environment. The entire system is designed around four separate but tightly integrated systems, namely the Recognition, Gripping and Handling structures and the Component Database which acts as the backbone of the system. The Recognition system provides all the input data that is then used for the Gripping and Handling systems. This integrated system functions as a single unit but a hierarchical structure has been used so that each of the systems can function as a stand-alone unit. The recognition system is generic in its ability to provide information such as recognized object identification, position and other orientation information that could be used by another handling system or gripper configuration. The Gripping system is based on a single custom designed gripper that provides basic gripping functionality. It is powered by a single motor and is highly functional with respect to the large range of object sizes that it can grip. The Handling Sub-system controls gripper positioning and motion. The Handling System incorporates control of the robot and the execution of both predetermined and online adaptable handling algorithms based on component data. It receives data from the Component database. The database allows the transparent ability to add and remove objects for recognition as well as other basic abilities. Experimental verification of the system is performed using a fully integrated and automated program and hardware control system developed for this purpose. The integration of the proposed system into a flexible and reconfigurable manufacturing system is explained.

M.Sc. (Computer Science) / This dissertation examines the field of computer vision, with special attention being given to vision systems that support digitized video image analysis. The study may be broadly divided into three main sections. The first part offers an introduction to standard vision systems, focusing on the hardware architectures and the image analysis techniques used on them. Hardware configurations depend mainly on the selected frame-grabber and processor type. Parallel architectures are highlighted, as they represent the most suitable platform for a real-time digitized video image analysis system. The image analysis techniques discussed include: image preprocessing, segmentation, edge detection, optical flow analysis and optical character recognition. The second part of the study covers a number of real-world computer vision applications, and commercially available development environments. Several traffic surveillance systems are discussed in detail, as they relate to the practical vehicle identification system developed in the third part of the study. As mentioned above, the development of a Vehicle Identification Prototype, called VIP, forms the basis for the third and final part of this study. The VIP hardware requirements are given, and the software development and use is explained. The VIP's source code is provided so that it may be evaluated, or modified, by any interested parties.

No description available.

Please read the abstract in the section 00front of this document / Thesis (PhD (Electronic Engineering))--University of Pretoria, 2007. / Electrical, Electronic and Computer Engineering / unrestricted

Humans spend a large amount of their time interacting with computers of one type or another. However, computers are emotionally blind and indifferent to the affective states of their users. Human-computer interaction which does not consider emotions, ignores a whole channel of available information. Faces contain a large portion of our emotionally expressive behaviour. We use facial expressions to display our emotional states and to manage our interactions. Furthermore, we express and read emotions in faces effortlessly. However, automatic understanding of facial expressions is a very difficult task computationally, especially in the presence of highly variable pose, expression and illumination. My work furthers the field of automatic facial expression tracking by tackling these issues, bringing emotionally aware computing closer to reality. Firstly, I present an in-depth analysis of the Constrained Local Model (CLM) for facial expression and head pose tracking. I propose a number of extensions that make location of facial features more accurate. Secondly, I introduce a 3D Constrained Local Model (CLM-Z) which takes full advantage of depth information available from various range scanners. CLM-Z is robust to changes in illumination and shows better facial tracking performance. Thirdly, I present the Constrained Local Neural Field (CLNF), a novel instance of CLM that deals with the issues of facial tracking in complex scenes. It achieves this through the use of a novel landmark detector and a novel CLM fitting algorithm. CLNF outperforms state-of-the-art models for facial tracking in presence of difficult illumination and varying pose. Lastly, I demonstrate how tracked facial expressions can be used for emotion inference from videos. I also show how the tools developed for facial tracking can be applied to emotion inference in music.

Measurements of vibrations, such as sound hitting an object or running a motor, are widely used in industry and research. Traditional methods need either direct contact with the object or a laser vibrometer. Although computer vision methods have been applied to solve this problem, high speed cameras are usually preferred. This study employs a consumer level rolling shutter camera for extracting main frequency components of small vibrations. A rolling shutter camera exposes continuously over time on the vertical direction of the sensor, and produces images with shifted rows of objects. We utilize the rolling shutter effect to boost our capability to extract vibration frequencies higher than the frame rate. Assuming the vibration amplitude of the target results in a horizontal fronto-parallel component in the image, we compute the displacement of each row from a reference frame by our novel phase matching approach in the complex-valued Shearlet transform domain. So far the only way to process rolling shutter video for vibration extraction is with the Steerable Pyramid in a motion magnification framework. However, the Shearlet transform is well localized in scale, location and orientation, and hence better suited to vibration extraction than the Steerable Pyramid used in the high speed video approach. Using our rolling shutter approach, we manage to recover signals from 75Hz to 500Hz from videos of 30fps. We test our method by controlled experiments with a loudspeaker. We play sounds with certain frequency components and take videos of the loudspeaker's surface. Our approach recovers chirp signals as well as single frequency signals from rolling shutter videos. We also test with music and speech. Both experiments produce identifiable recovered audio.

This thesis presents a theory of multi-scale, curvature and torsion based shape representation for planar and space curves. The theory presented has been developed to satisfy various criteria considered useful for evaluating shape representation methods in computer vision. The criteria are: invariance, uniqueness, stability, efficiency, ease of implementation and computation of shape properties. The regular representation for planar curves is referred to as the curvature scale space image and the regular representation for space curves is referred to as the torsion scale space image. Two variants of the regular representations, referred to as the renormalized and resampled curvature and torsion scale space images, have also been proposed. A number of experiments have been carried out on the representations which show that they are very stable under severe noise conditions and very useful for tasks which call for recognition of a noisy curve of arbitrary shape at an arbitrary scale or orientation. Planar or space curves are described at varying levels of detail by convolving their parametric representations with Gaussian functions of varying standard deviations. The curvature or torsion of each such curve is then computed using mathematical equations which express curvature and torsion in terms of the convolutions of derivatives of Gaussian functions and parametric representations of the input curves. Curvature or torsion zero-crossing points of those curves are then located and combined to form one of the representations mentioned above. The process of describing a curve at increasing levels of abstraction is referred to as the evolution or arc length evolution of that curve. This thesis contains a number of theorems about evolution and arc length evolution of planar and space curves along with their proofs. Some of these theorems demonstrate that evolution and arc length evolution do not change the physical interpretation of curves as object boundaries and others are in fact statements on the global properties of planar and space curves during evolution and arc length evolution and their representations. Other theoretical results shed light on the local behavior of planar and space curves just before and just after the formation of a cusp point during evolution and arc length evolution. Together these results provide a sound theoretical foundation for the representation methods proposed in this thesis. / Science, Faculty of / Computer Science, Department of / Graduate