Thesis (MScEng)--Stellenbosch University, 2002. / ENGLISH ABSTRACT: Flotation is notorious for its susceptibility to process upsets and consequently its poor performance, making successful flotation control systems an elusive goal. The control of industrial flotation plants is often based en the visual appearance of the froth phase, and depends to a large extent on the experience and ability of a human operator. Machine vision systems provide a novel solution to several of the problems encountered in conventional flotation systems for monitoring and control. The rapid development in computer VISIon, computational resources and artificial intelligence and the integration of these technologies are creating new possibilities in the design and implementation of commercial machine vision systems for the monitoring and control of flotation plants. Current machine vision systems are available but not without their shortcomings. These systems cannot deal with fine froths where the bubbles are very small due to the segmentation techniques employed by them. These segmentation techniques are cumbersome and computationally expensive making them slow in real time operation. The approach followed in this work uses neural networks to solve the problems mentioned above. Neural networks are able to extract information from images of the froth phase without regard to the type and structure of the froth. The parallel processing capability of neural networks, ease of implementation and the advantages of supervised or unsupervised training of neural networks make them potentially suited for real-time industrial machine vision systems. In principle, neural network models can be implemented in an adaptive manner, so that changes in the characteristics of processes are taken into account. This work documents the development of linear and non-linear principal component models, which can be used in a real-time machine vision system for the monitoring, and control of froth flotation systems. Features from froth images of flotation processes were extracted via linear and non-linear principal component analysis. Conventional linear principal component analysis and three layer autoassociative neural networks were used in the extraction of linear principal components from froth images. Non-linear principal components were extracted from froth images by a three and five layer autoassociative neural network, as well as localised principal component analysis based on k-means clustering. Three principal components were extracted for each image. The correlation coefficient was used as a measure of the amount of variance captured by each principal component. The principal components were used to classify the froth images. A probabilistic neural network and a feedforward neural network classifier were developed for the classification of the froth images. Multivariate statistical process control models were developed using the linear and non-linear principal component models. Hotellings T2 statistic and the squared prediction error based on linear and non-linear principal component models were used in the development of multivariate control charts. It was found that the first three features extracted with autoassociative neural networks were able to capture more variance in froth images than conventional linear principal components, the features extracted by the five layer autoassociative neural networks were able to classify froth images more accurately than features extracted by conventional linear principal component analysis and three layer autoassociative neural networks. As applied, localised principal component analysis proved to be ineffective, owing to difficulties with the clustering of the high dimensional image data. Finally the use of multivariate statistical process control models to detect deviations from normal plant operations are discussed and it is shown that Hotellings T2 and squared prediction error control charts are able to clearly identify non-conforming plant behaviour. / AFRIKAANSE OPSOMMING: Flottasie is berug daarvoor dat dit vatbaar vir prosesversteurings is en daarom dikwels nie na wense presteer nie. Suksesvolle flottasiebeheerstelsels bly steeds 'n ontwykende doelwit. Die beheer van nywerheidsflottasie-aanlegte word dikwels gebaseer op die visuele voorkoms van die skuimfase en hang tot 'n groot mate af van die ervaring en vaardighede van die menslike operateur. Masjienvisiestelsels voorsien 'n vindingryke oplossing tot verskeie van die probleme wat voorkom by konvensionele flottasiestelsels ten opsigte van monitering en beheer. Die vinnige ontwikkeling van rekenaarbeheerde visie, rekenaarverwante hulpbronne en kunsmatige intelligensie, asook die integrasie van hierdie tegnologieë, skep nuwe moontlikhede in die ontwerp en inwerkingstelling van kommersiële masjienvisiestelsels om flottasie-aanlegte te monitor en te beheer. Huidige masjienvisiestelsels is wel beskikbaar, maar is nie sonder tekortkominge nie. Hierdie stelsels kan nie fyn skuim hanteer nie, waar die borreltjies baie klein is as gevolg van die segmentasietegnieke wat hulle aanwend. Hierdie segmentasietegnieke is omslagtig en rekenaargesproke duur, wat veroorsaak dat dit stadig in reële tyd-aanwendings is. Die benadering wat in hierdie werk gevolg is, wend neurale netwerke aan om die bovermelde probleme op te los. Neurale netwerke is instaat om inligting te onttrek uit beelde van die skuimfase sonder om ag te slaan op die tipe en struktuur van die skuim. Die parallelle prosesseringsvermoëns van neurale netwerke, die gemak van implementering en die voordele van die opleiding van neurale netwerke met of sonder toesig maak hulle potensieel nuttig as reële tydverwante industriële masjienvisiestelsels. In beginsel kan neurale netwerke op 'n aanpassende wyse geïmplementeer word, sodat veranderinge in die kenmerke van die prosesse deurlopend in aanmerking geneem word. Kenmerke van die beelde van die skuim tydens die flottasieproses is verkry by wyse van lineêre en nie-lineêre hootkomponentsanalise. Konvensionele lineêre hoofkomponentsanalise en drie-laag outo-assosiatiewe neurale netwerke is gebruik in die onttrekking van lineêre hoofkomponente uit die beelde van die skuim. Nie-lineêre hoofkomponente is uit die beelde van die skuim onttrek by wyse van 'n drie- en vyf-laag outo-assosiatiewe neurale netwerk, asook deur 'n gelokaliseerde hoofkomponentsanalise wat op k-gemiddelde trosanalise gebaseer is. Drie hoofkomponente is vir elke beeld onttrek. Die korrelasiekoëffisiënt is gebruik as 'n maatstaf van die afwyking wat deur elke hoofkomponent aangetoon is. Die hoofkomponente is gebruik om die beelde van die skuim te klassifiseer. 'n Probalistiese neurale netwerk en 'n voorwaarts voerende neurale netwerk is vir die klassifisering van die beelde van die skuim ontwerp. Multiveranderlike statistiese prosesbeheermodelle is ontwerp met die gebruik van die lineêre en nie-lineêre hoofkomponentmodelle. Hotelling se T2 statistiek en die gekwadreerde voorspellingsfout, gebaseer op lineêre en nie-lineêre hoofkomponentmodelle, is gebruik in die ontwikkeling van multiveranderlike kontrolekaarte. Dit is gevind dat die eerste drie eienskappe wat met behulp van die outo-assosiatiewe neurale netwerke onttrek is, instaat was om meer variansie by beelde van skuim vas te vang as konvensionele lineêre hoofkomponente. Die eienskappe wat deur die vyf-laag outo-assosiatiewe neurale netwerke onttrek is, was instaat om beelde van skuim akkurater te klassifiseer as daardie eienskappe wat by wyse van konvensionele lineêre hoofkomponentanalalise en drie-laag outo-assosiatiewe neurale netwerke onttrek is. Soos toegepas, het dit geblyk dat gelokaliseerde hoofkomponentsanalise nie effektief is nie, as gevolg van die probleme rondom die trosanalise van die hoë-dimensionele beelddata. Laastens word die aanwending van multiveranderlike statistiese prosesbeheermodelle, om afwykings in normale aanlegoperasies op te spoor, bespreek. Dit word aangetoon dat Hotelling se T2 statistiek en gekwadreerdevoorspellingsfoutbeheerkaarte instaat is om afwykende aanlegwerksverrigting duidelik aan te dui.

published_or_final_version / Civil Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / abstract / Civil Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / abstract / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / abstract / Electrical and Electronic Engineering / Master / Master of Philosophy

published_or_final_version / abstract / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

This dissertation analyzes the different characteristics of color images compared to monochromatic images, combines these characteristics with monochromatic image enhancement techniques, and proposes useful color image enhancement algorithms. Luminance, hue, and saturation (L-H-S) color space is selected for color image enhancement. Color luminance is shown to play the most important role in achieving good image enhancement. Color saturation also exhibits unique features which contribute to the enhancement of high frequency details and color contrast. The local windowing method, one of the most popular image processing techniques, is rigorously analyzed for the effects of window size or weighting values on the visual appearance of an image, and the subjective enhancement afforded by local image processing techniques is explained in terms of the human vision system response. The digital color image enhancement algorithms proposed are based on the observation that the enhanced luminance image results in a good color image in L-H-S color space when the chromatic components (hue, and saturation) are kept the same. The saturation component usually contains high frequency details that are not present in the luminance component. However, processing only the saturation, while keeping the luminance and the hue unchanged, is not satisfactory because the response of human vision system presents a low pass filter to the chromatic components. To exploit high frequency details of the saturation component, we take the high frequency component of the inverse saturation image, which correlates with the luminance image, and process the luminance image proportionally to this inverse saturation image. These proposed algorithms are simple to implement. The main three application areas in image enhancement: contrast enhancement, sharpness enhancement, and noise smoothing, are discussed separately. The computer processing algorithms are restricted to those which preserve the natural appearance of the scene.

The Totally Digital Imaging System (TDIS) is based on system requirements information from the Radiology Department, University of Arizona Health Science Center. This dissertation presents the design of this complex system, the TDIS specification, the system performance requirements, and the evaluation of the system using the computer simulation programs. Discrete event simulation models were developed for the TDIS subsystems, including an image network, imaging equipment, storage migration algorithm, data base archive system, and a control and management network. The simulation system uses empirical data generation and retrieval rates measured at the University Medical Center hospital. The entire TDIS system was simulated in Simscript II.5 using a VAX 8600 computer system. Simulation results show the fiber optical image network to be suitable, however, the optical disk storage system represents a performance bottleneck.

This dissertation presents image processing methods designed to enhance images obtained by angiography, and applied image analysis methods to quantify the vascular diameter. An iterative, non-linear enhancement technique is described for enhancing the edges of blood vessels in unsubtracted angiographic images. The technique uses a median filter and the point spread function of the imaging system to increase the resolution of the image while keeping down noise. Evaluation of the images by radiologists showed that they preferred the processed images over the unprocessed images. Also described is a heuristic, recursive, vessel tracking algorithm. The tracker is intended for use with digital subtraction angiography images. The vascular system is characterized by a tree data structure. Tree structures are inherently recursive structures and thus recursive programming languages are ideally suited for building and describing them. The tracker uses a window to follow the centerlines of the vessels and stores parameters describing the vessels in nodes of a binary tree. Branching of the vascular tree is handled automatically. A least squares fit of a cylindrical model to intensity profiles of the vessel is used to estimate vessel diameter and other parameters. The tracker is able to successfully track vessels with signal-to-noise ratios down to about 4. Several criteria are applied to distinguish between vessel and noise. The relative accuracy of the diameter estimate is about 3% to 8% for a signal-to-noise ratio of 10; the absolute accuracy depends on the magnification (mm per sample). For the clinically significant case of a 25% stenosis (narrowing of the vessel), the absolute error in estimating the percent stenosis is 3.7% of the normal diameter and the relative error is 14.8%. This relative error of 14.8% is a substantial improvement over relative errors of 30% to 70% produced by other methods.

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