The broad objective of this work has been to achieve retrieval of images from large unconstrained databases using image content. The problem is typified by the need to locate a target image within a database where no numerical indexing terms exist. Here, retrieval is based on important features within in an image and uses sample images or user sketches to specify a query. A typical query might be framed as "Find all images similar to this one", for example. The aim of this work has been to show how neural networks can provide a practical, flexible and robust solution to this problem. A neural network is basically an adaptive information filter which can be used to extract the salient characteristics of a data set during a training phase. The transformation learnt by the network can map the images into compact indices which support very rapid fuzzy matching of images across the database. This learning process optimises the performance of the code with respect to the contents of the database. We assess the applicability of several neural network architectures and learning rules for a practical coding scheme and investigate how the system parameters affect the performance of the system. We introduce a novel learning law which has a number of advantages over existing paradigms. In-depth mathematical analysis and extensive empirical tests are used to corroborate the arguments presented throughout. This thesis aims to show the nature of the image retrieval problem, how current research trends attempt to tackle it and how neural networks can offer us a real alternative to conventional approaches.

We propose the use of iterated function systems as an isomorphic shape representation scheme for use in a machine vision environment. A concise description of the basic theory and salient characteristics of iterated function systems is presented and from this we develop a formal framework within which to embed a representation scheme. Concentrating on the problem of obtaining automatically generated two-dimensional encodings we describe implementations of two solutions. The first is based on a deterministic algorithm and makes simplifying assumptions which limit its range of applicability. The second employs a novel formulation of a genetic algorithm and is intended to function with general data input. Keywords: Machine Vision, Shape Representation, Iterated Function Systems, Genetic Algorithms.

No description available.

No description available.

A successful lighting design usually results from the skill of the designer in applying professional experience. However, successful designs have been achieved using numerical prediction. It is probable that a blend of both these elements will give the optimum result. Whatever the design approach, the end product will be judged, at least in part, on its aesthetic merits. The first chapter of this thesis introduces the possibility of using a digital computer in conjunction with a colour television monitor to calculate and display the luminance distribution in a lighted room; a system which may offer advantages both for the experienced designer and the student of lighting design. The display system is described briefly, along with some possible shortcomings. An account is given of the methods used for inter-reflection calculation. These inter-reflection calculations are then developed to include colour and techniques of photometric and colorimetric measurement with reference to the television display. A complete description of the display system hardware is also given. This display system as initially designed uses chromaticity as the criterion for colour reproduction. The shortcomings of this approach are discussed. Techniques for perceived colour measurement are described and the results presented for the colour perceived from some simple display images. The possibility of perceived colour prediction is examined and measured colours are compared with those predicted by a non-linear model. Finally, the applications of the display are discussed, both in an educational and design context. Some possible developments and improvements are also outlined.

In this dissertation a biologically plausible system of pitch estimation is proposed. The system is designed from the bottom up to be robust to challenging noise conditions. This robustness to the presence of noise in the signal is achieved by developing a new representation of the speech signal, based on the operation of damped harmonic oscillators, and temporal mode analysis of their output. This resulting representation is shown to possess qualities which are not degraded in presence of noise. A harmonic grouping based system is used to estimate the pitch frequency. A detailed statistical analysis is performed on the system, and performance compared with some of the most established and recent pitch estimation and tracking systems. The detailed analysis includes results of experiments with a variety of noises with a large range of signal to noise ratios, under different signal conditions. Situations where the interfering "noise" is speech from another speaker are also considered. The proposed system is able to estimate the pitch of both the main speaker, and the interfering speaker, thus emulating the phenomena of auditory streaming and "cocktail party effect" in terms of pitch perception. The results of the extensive statistical analysis show that the proposed system exhibits some very interesting properties in its ability of handling noise. The results also show that the proposed system’s overall performance is much better than any of the other systems tested, especially in presence of very large amounts of noise. The system is also shown to successfully simulate some very interesting psychoacoustical pitch perception phenomena. Through a detailed and comparative computational requirements analysis, it is also demonstrated that the proposed system is comparatively inexpensive in terms of processing and memory requirements.

The aim of the present work was to build a novel 3D object recognition system capable of classifying man-made and natural objects based on single 2D views. The approach to this problem has been one motivated by recent theories on biological vision and multiresolution analysis. The project's objectives were the implementation of a system that is able to deal with simple 3D scenes and constitutes an engineering solution to the problem of 3D object recognition, allowing the proposed recognition system to operate in a practically acceptable time frame. The developed system takes further the work on automatic classification of marine phytoplanktons, carried out at the Centre for Intelligent Systems, University of Plymouth. The thesis discusses the main theoretical issues that prompted the fundamental system design options. The principles and the implementation of the coarse data channels used in the system are described. A new multiresolution representation of 2D views is presented, which provides the classifier module of the system with coarse-coded descriptions of the scale-space distribution of potentially interesting features. A multiresolution analysis-based mechanism is proposed, which directs the system's attention towards potentially salient features. Unsupervised similarity-based feature grouping is introduced, which is used in coarse data channels to yield feature signatures that are not spatially coherent and provide the classifier module with salient descriptions of object views. A simple texture descriptor is described, which is based on properties of a special wavelet transform. The system has been tested on computer-generated and natural image data sets, in conditions where the inter-object similarity was monitored and quantitatively assessed by human subjects, or the analysed objects were very similar and their discrimination constituted a difficult task even for human experts. The validity of the above described approaches has been proven. The studies conducted with various statistical and artificial neural network-based classifiers have shown that the system is able to perform well in all of the above mentioned situations. These investigations also made possible to take further and generalise a number of important conclusions drawn during previous work carried out in the field of 2D shape (plankton) recognition, regarding the behaviour of multiple coarse data channels-based pattern recognition systems and various classifier architectures. The system possesses the ability of dealing with difficult field-collected images of objects and the techniques employed by its component modules make possible its extension to the domain of complex multiple-object 3D scene recognition. The system is expected to find immediate applicability in the field of marine biota classification.

No description available.

No description available.

No description available.