Wong Wai-Ting Jacqueline. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (p. 115-120). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

Thesis (M.S.)--Mississippi State University. Department of Computer Science. / Title from title screen. Includes bibliographical references.

[Truncated abstract] The development of an automated classification system of wear particles or surfaces is of great interest to the machine condition monitoring industry. The system, once developed, may also find applications in medical diagnostics. Such a tool will be able to replace human experts in the detection of the onset of early machine failure, or in the diagnosis and prognosis of, for example, joint diseases. This will improve efficiency, reliability and also reduce costs of monitoring or diagnostic systems. Current literature available on this topic has included various studies on different classification methods. However, there has been no work conducted on the development of a totally integrated automated classification system. The first part of this thesis presents a study investigating the efficiency and robustness of various pattern recognition methods currently described in literature. A special computer program was developed to test each of the classification methods against both standard image databases and tribological surface images. There are three core components of a pattern recognition system that need to be analysed: (1) feature extraction, (2) feature reduction and (3) classifier. Each of these components provides a vital link that can affect the reliability of the complete classification system. ... The optimal classifier was the Linear Support Vector Classifier. This part of research is described in Paper 2. The second part of this thesis contains work verifying the performance of the automated classification system developed using both tribological and bio-tribological surface images. Experiments were carried out to generate wear particles created under different wear mechanisms (adhesive, abrasive and fatigue wear) and various operating conditions representing different degree of wear severity. The automated classification system developed was able to successfully classify wear particles with respect to both the type of wear mechanism operating and the wear severity. The results of this classification are described in Papers 3 and 5. The success of the automated classification system was also confirmed by its ability to classify different groups of worn (osteoarthritic) cartilage surfaces (Paper 4). This could lead to potential applications of the system for early detection of the onset of osteoarthritis. In conclusion, the automated classification system developed can accurately classify both tribological and bio-tribological surface images. This system could become a vitally important tool in both machine condition monitoring and medical diagnostics.

Thesis (Ph. D.)--Ohio State University, 2008. / Title from first page of PDF file. Includes bibliographical references (p. 105-108).

As recentes tecnologias de desenvolvimento e distribuição de componentes possibilitaram o aumento do número de componentes disponíveis no mercado. No entanto, eles muitas vezes estão dispersos e não publicados adequadamente para a comunidade de pesquisa e desenvolvimento de software. Encontrar componentes apropriados para solucionar um problema particular não é uma tarefa simples e novas técnicas devem ser desenvolvidas para o reuso efetivo de componentes. Um dos maiores desafios em reusar componentes consiste em classificá-los corretamente para futuras consultas. Classificar componentes para possibilitar uma busca eficaz depende da qualidade das informações adquiridas, que viabilizam melhor precisão e cobertura das consultas ao encontrar componentes reutilizáveis em potencial. Ao mesmo tempo, mecanismos de classificação e busca devem ser fáceis o suficiente para convencer os desenvolvedores a reusar componentes. Este trabalho estuda as técnicas de classificação de componentes de software, repositórios e métodos de busca. é apresentada uma proposta de modelo de classificação de componentes que considera não apenas sua função, mas o negócio onde ele está inserido e seus atributos de qualidade. Um método de preenchimento semi-automático das informações é proposto, de modo a diminuir os custos de classificação. O protótipo REUSE+ foi construído para exemplificar o uso do modelo e do método de classificação semi-automática, de forma a validar a proposta, destacando, por fim, as principais contribuições do trabalho. / The recent developments on components technologies have increased the number of components available to the market. These components are, however, distributed overall the world and not properly advertised to the research and development communities. Finding the appropriate components to solve a particular problem is not very straightforward and new techniques must be developed to effectively reuse components. One of the great challenges in reusing components is concerned with how to actually classify components \"properly\" in order to further retrieve them. Classifying components for effective retrieval depends on acquiring the appropriate information in classification to improve the precision and recall rates in retrieval; finding only the potentially reusable components and not missing potential solutions. At the same time, the classification and retrieval mechanisms must be easy enough to persuade developers to reuse components. This work studies the classification techniques of software components, repository and retrieval methods. Hereafter is presented a proposal of components classification model that considers not just its function, but business and quality attributes. It is proposed a semi-automatic classification mechanism of software information, allowing a cheaper classification. REUSE+ prototype was built to exemplify the use of model and method of semi-automatic classification, allowing the described proposal validation, highlighting at the end the mainly contributions of the work.

The simplest form of a snow particle is a hexagonal prism which can grow into a stellar crystal by growing branches from the six corners of the prism. The snow particle is affected by the temperature and supersaturation in the air, giving its unique form. Manual classification of snow particles based on shape is tedious work. Convolutional Neural Network (CNN) can therefor be of great assistance and are common in automatic image processing. From a data set consisting of 3165 images sorted into 15 shape classes, a sub set of 2193 images and 7 classes was used. The selected classes had the highest number of snow particle images and were used to train, validate and test on. Four data sets were constructed and eight models were used to classify the snow particles into seven classes. To reduce the amount of training data needed pretrained versions of neural networks AlexNet and ResNet50 were used with a technique called transfer learning. The 2193 images make up the first data set, Data set 1. To handle unbalanced classes in the first data set Synthetic Minority Oversampling Technique (SMOTE) was used to increase the number of snow particles in classes with few examples, creating Data set 2. A third data set was constructed to mimic a real world application. The data for training and validation was increased with SMOTE, while the test data only consisted of real snow particles. The performance of both ResNet50 and AlexNet on the data met the requirements for a practical application. However, ResNet50 had a higher overall accuracy, 72%, compared to AlexNet 69% on the evaluated data set. A t-test was conducted with a significance of p < 1·10−8. To enhance the shape of the snow particles a Euclidean Distance Transform (EDT) was used, creating Data set 4. However, this did not increase the accuracy of the trained model. To increase the accuracy of the models more training data of snow particles is needed, especially for classes with few examples. A larger data set would also allow more classes to be included in the classification.

A huge effort has been made in the development of image classification systemswith the objective of creating high-quality thematic maps and to establishprecise inventories about land cover use. The peculiarities of Remote SensingImages (RSIs) combined with the traditional image classification challengesmake RSI classification a hard task. Many of the problems are related to therepresentation scale of the data, and to both the size and therepresentativeness of used training set.In this work, we addressed four research issues in order to develop effectivesolutions for interactive classification of remote sensing images.The first research issue concerns the fact that image descriptorsproposed in the literature achieve good results in various applications, butmany of them have never been used in remote sensing classification tasks.We have tested twelve descriptors that encodespectral/color properties and seven texture descriptors. We have also proposeda methodology based on the K-Nearest Neighbor (KNN) classifier for evaluationof descriptors in classification context. Experiments demonstrate that JointAuto-Correlogram (JAC), Color Bitmap, Invariant Steerable Pyramid Decomposition(SID), and Quantized Compound Change Histogram (QCCH) yield the best results incoffee and pasture recognition tasks.The second research issue refers to the problem of selecting the scaleof segmentation for object-based remote sensing classification. Recentlyproposed methods exploit features extracted from segmented objects to improvehigh-resolution image classification. However, the definition of the scale ofsegmentation is a challenging task. We have proposedtwo multiscale classification approaches based on boosting of weak classifiers.The first approach, Multiscale Classifier (MSC), builds a strongclassifier that combines features extracted from multiple scales ofsegmentation. The other, Hierarchical Multiscale Classifier (HMSC), exploits thehierarchical topology of segmented regions to improve training efficiencywithout accuracy loss when compared to the MSC. Experiments show that it isbetter to use multiple scales than use only one segmentation scale result. Wehave also analyzed and discussed about the correlation among the useddescriptors and the scales of segmentation.The third research issue concerns the selection of training examples and therefinement of classification results through multiscale segmentation. We have proposed an approach forinteractive multiscale classification of remote sensing images.It is an active learning strategy that allows the classification resultrefinement by the user along iterations. Experimentalresults show that the combination of scales produces better results thanisolated scales in a relevance feedback process. Furthermore, the interactivemethod achieves good results with few user interactions. The proposed methodneeds only a small portion of the training set to build classifiers that are asstrong as the ones generated by a supervised method that uses the whole availabletraining set.The fourth research issue refers to the problem of extracting features of ahierarchy of regions for multiscale classification. We have proposed a strategythat exploits the existing relationships among regions in a hierarchy. Thisapproach, called BoW-Propagation, exploits the bag-of-visual-word model topropagate features along multiple scales. We also extend this idea topropagate histogram-based global descriptors, the H-Propagation method. The proposedmethods speed up the feature extraction process and yield good results when compared with globallow-level extraction approaches.

L'objectif de cette thèse est de développer des solutions efficaces pour laclassification interactive des images de télédétection. Cet objectif a étéréalisé en répondant à quatre questions de recherche.La première question porte sur le fait que les descripteursd'images proposées dans la littérature obtiennent de bons résultats dansdiverses applications, mais beaucoup d'entre eux n'ont jamais été utilisés pour la classification des images de télédétection. Nous avons testé douzedescripteurs qui codent les propriétés spectrales et la couleur, ainsi que septdescripteurs de texture. Nous avons également proposé une méthodologie baséesur le classificateur KNN (K plus proches voisins) pour l'évaluation desdescripteurs dans le contexte de la classification. Les descripteurs Joint Auto-Correlogram (JAC),Color Bitmap, Invariant Steerable Pyramid Decomposition (SID) etQuantized Compound Change Histogram (QCCH), ont obtenu les meilleursrésultats dans les expériences de reconnaissance des plantations de café et depâturages.La deuxième question se rapporte au choix del'échelle de segmentation pour la classification d'images baséesur objets.Certaines méthodes récemment proposées exploitent des caractéristiques extraitesdes objets segmentés pour améliorer classification des images hauterésolution. Toutefois, le choix d'une bonne échelle de segmentation est unetâche difficile.Ainsi, nous avons proposé deux approches pour la classification multi-échelles fondées sur le les principes du Boosting, qui permet de combiner desclassifieurs faibles pour former un classifieur fort.La première approche, Multiscale Classifier (MSC), construit unclassifieur fort qui combine des caractéristiques extraites de plusieurséchelles de segmentation. L'autre, Hierarchical Multiscale Classifier(HMSC), exploite la topologie hiérarchique de régions segmentées afind'améliorer l'efficacité des classifications sans perte de précision parrapport au MSC. Les expériences montrent qu'il est préférable d'utiliser des plusieurs échelles plutôt qu'une seul échelle de segmentation. Nous avons également analysé et discuté la corrélation entre lesdescripteurs et des échelles de segmentation.La troisième question concerne la sélection des exemplesd'apprentissage et l'amélioration des résultats de classification basés sur lasegmentation multiéchelle. Nous avons proposé une approche pour laclassification interactive multi-échelles des images de télédétection. Ils'agit d'une stratégie d'apprentissage actif qui permet le raffinement desrésultats de classification par l'utilisateur. Les résultats des expériencesmontrent que la combinaison des échelles produit de meilleurs résultats que leschaque échelle isolément dans un processus de retour de pertinence. Par ailleurs,la méthode interactive permet d'obtenir de bons résultats avec peud'interactions de l'utilisateur. Il n'a besoin que d'une faible partie del'ensemble d'apprentissage pour construire des classificateurs qui sont aussiforts que ceux générés par une méthode supervisée qui utilise l'ensembled'apprentissage complet.La quatrième question se réfère au problème de l'extraction descaractéristiques d'un hiérarchie des régions pour la classificationmulti-échelles. Nous avons proposé une stratégie qui exploite les relationsexistantes entre les régions dans une hiérarchie. Cette approche, appelée BoW-Propagation, exploite le modèle de bag-of-visual-word pour propagerles caractéristiques entre les échelles de la hiérarchie. Nous avons égalementétendu cette idée pour propager des descripteurs globaux basés sur leshistogrammes, l'approche H-Propagation. Ces approches accélèrent leprocessus d'extraction et donnent de bons résultats par rapport à l'extractionde descripteurs globaux. / A huge effort has been made in the development of image classification systemswith the objective of creating high-quality thematic maps and to establishprecise inventories about land cover use. The peculiarities of Remote SensingImages (RSIs) combined with the traditional image classification challengesmake RSI classification a hard task. Many of the problems are related to therepresentation scale of the data, and to both the size and therepresentativeness of used training set.In this work, we addressed four research issues in order to develop effectivesolutions for interactive classification of remote sensing images.The first research issue concerns the fact that image descriptorsproposed in the literature achieve good results in various applications, butmany of them have never been used in remote sensing classification tasks.We have tested twelve descriptors that encodespectral/color properties and seven texture descriptors. We have also proposeda methodology based on the K-Nearest Neighbor (KNN) classifier for evaluationof descriptors in classification context. Experiments demonstrate that JointAuto-Correlogram (JAC), Color Bitmap, Invariant Steerable Pyramid Decomposition(SID), and Quantized Compound Change Histogram (QCCH) yield the best results incoffee and pasture recognition tasks.The second research issue refers to the problem of selecting the scaleof segmentation for object-based remote sensing classification. Recentlyproposed methods exploit features extracted from segmented objects to improvehigh-resolution image classification. However, the definition of the scale ofsegmentation is a challenging task. We have proposedtwo multiscale classification approaches based on boosting of weak classifiers.The first approach, Multiscale Classifier (MSC), builds a strongclassifier that combines features extracted from multiple scales ofsegmentation. The other, Hierarchical Multiscale Classifier (HMSC), exploits thehierarchical topology of segmented regions to improve training efficiencywithout accuracy loss when compared to the MSC. Experiments show that it isbetter to use multiple scales than use only one segmentation scale result. Wehave also analyzed and discussed about the correlation among the useddescriptors and the scales of segmentation.The third research issue concerns the selection of training examples and therefinement of classification results through multiscale segmentation. We have proposed an approach forinteractive multiscale classification of remote sensing images.It is an active learning strategy that allows the classification resultrefinement by the user along iterations. Experimentalresults show that the combination of scales produces better results thanisolated scales in a relevance feedback process. Furthermore, the interactivemethod achieves good results with few user interactions. The proposed methodneeds only a small portion of the training set to build classifiers that are asstrong as the ones generated by a supervised method that uses the whole availabletraining set.The fourth research issue refers to the problem of extracting features of ahierarchy of regions for multiscale classification. We have proposed a strategythat exploits the existing relationships among regions in a hierarchy. Thisapproach, called BoW-Propagation, exploits the bag-of-visual-word model topropagate features along multiple scales. We also extend this idea topropagate histogram-based global descriptors, the H-Propagation method. The proposedmethods speed up the feature extraction process and yield good results when compared with globallow-level extraction approaches.

Neste trabalho foi desenvolvida uma instrumentação óptica in-line para filmagem de partículas in situ, utilizando a técnica de sombreamento, acompanhada de softwares para processamento das imagens. As novas ferramentas foram implementadas e foi conduzido um estudo de caso para a avaliação da dinâmica de partículas e suas forçantes ambientais em uma região costeira de Ubatuba. O sistema com 4 sensores acoplados, adquiriu dados oceanográficos e de imagens a cada 40 minutos, no período entre 20 de fevereiro e 7 de junho de 2017. Dados metereológicos adicionais foram obtidos para análises correlativas. Testes com os softwares de visão computacional estabeleceram o uso dos filtros de tamanho entre 500 e 16300 pixels e contraste maior que 50% para segmentação das Regiões de Interesse (ROIs). Os testes também indicaram a melhor performance do algoritmo de segmentação ModeValue e de uma base de treinamento composta por 9 classes com 300 organismos cada para a classificação automática. Devido à baixa acurácia obtida na etapa de classificação automática de imagens desconhecidas de organismos (27%), os objetos foram analisados nesse estudo como partículas, divididos de acordo com o tamanho de seu eixo maior em três ranges (<385 μm; 385-620 μm; >620μm). A análise das partículas, por questões estatísticas, considerou o maior intervalo de amostragens contínuas da série, de 5 de abril a 7 de maio de 2017. Primeiramente a série de cada variável foi decomposta em componentes harmônicas, com base na análise de Fourier, visando detectar padrões recorrentes e, em seguida, as variáveis com picos de densidade espectral mais expressivos em frequências da ordem de uma semana e de um dia foram comparadas por meio da coerência quadrada. As partículas menores, do range 1, foram as que melhor representaram a abundância total e os maiores valores de coerência foram entre as variáveis com período característico de um dia. A instrumentação implementada e testada ao longo de cerca de 3 meses possibilitou a aquisição de imagens de qualidade e de resultados iniciais úteis para o aprimoramento do sistema, visando instalações futuras de longo prazo em ambientes costeiros. / In this work, in-line optical optical instrumentation was developed for in situ particle filming, using the shadowgraphic technique, accompanied by image processing software. The new tools were implemented and a case study was carried out to evaluate the dynamics of particles and their environmental forcing in a coastal region of Ubatuba. The system, with 4 coupled environmental sensors, acquired oceanographic and image data every 40 minutes, between February 20 and June 7, 2017. Aditional meteorological data were obtained for correlative analyzes. Tests with the implemented computer vision software have stablished the use of size filters between 500 and 16300 pixels and contrast level greater than 50% for the segmentation of Regions of Interest (ROIs). The test also indicated the best performance of the Mode Value segmentation algorithm and of a training set composed by 9 classes with 300 organisms each for automatic classification. Due to the low global accuracy obtained in the automatic classification stage of unknown images of organisms (27%), the objects were analyzed in this study as particle, divided according to the size of their major axis in three ranges (<385 μm; 385 - 620 μm; >620μm). Particle analysis, for statistical reasons, considered the largest continuous sampling range of the series, from April 5 to May 7, 2017. First, the series of each variables decomposed into harmonic components, based on Fourier analysis, aiming to detect recurrent patterns, and then the variables with more expressive spectral density peaks at frequencies of the order of one week and one day were compared by means of square coherence. The smaller particles of range 1 were the ones that best represented the total abundance, and the highest values of coherence were among the variables with characteristic period of one day. The instrumentation implemented and tested over about 3 months allowed the acquisition og high-quality images and the initial results were useful for improving the system, aiming at future long-term deployments in coastal environments.

Neste trabalho foi desenvolvida uma instrumentação óptica in-line para filmagem de partículas in situ, utilizando a técnica de sombreamento, acompanhada de softwares para processamento das imagens. As novas ferramentas foram implementadas e foi conduzido um estudo de caso para a avaliação da dinâmica de partículas e suas forçantes ambientais em uma região costeira de Ubatuba. O sistema com 4 sensores acoplados, adquiriu dados oceanográficos e de imagens a cada 40 minutos, no período entre 20 de fevereiro e 7 de junho de 2017. Dados metereológicos adicionais foram obtidos para análises correlativas. Testes com os softwares de visão computacional estabeleceram o uso dos filtros de tamanho entre 500 e 16300 pixels e contraste maior que 50% para segmentação das Regiões de Interesse (ROIs). Os testes também indicaram a melhor performance do algoritmo de segmentação ModeValue e de uma base de treinamento composta por 9 classes com 300 organismos cada para a classificação automática. Devido à baixa acurácia obtida na etapa de classificação automática de imagens desconhecidas de organismos (27%), os objetos foram analisados nesse estudo como partículas, divididos de acordo com o tamanho de seu eixo maior em três ranges (<385 μm; 385-620 μm; >620μm). A análise das partículas, por questões estatísticas, considerou o maior intervalo de amostragens contínuas da série, de 5 de abril a 7 de maio de 2017. Primeiramente a série de cada variável foi decomposta em componentes harmônicas, com base na análise de Fourier, visando detectar padrões recorrentes e, em seguida, as variáveis com picos de densidade espectral mais expressivos em frequências da ordem de uma semana e de um dia foram comparadas por meio da coerência quadrada. As partículas menores, do range 1, foram as que melhor representaram a abundância total e os maiores valores de coerência foram entre as variáveis com período característico de um dia. A instrumentação implementada e testada ao longo de cerca de 3 meses possibilitou a aquisição de imagens de qualidade e de resultados iniciais úteis para o aprimoramento do sistema, visando instalações futuras de longo prazo em ambientes costeiros. / In this work, in-line optical optical instrumentation was developed for in situ particle filming, using the shadowgraphic technique, accompanied by image processing software. The new tools were implemented and a case study was carried out to evaluate the dynamics of particles and their environmental forcing in a coastal region of Ubatuba. The system, with 4 coupled environmental sensors, acquired oceanographic and image data every 40 minutes, between February 20 and June 7, 2017. Aditional meteorological data were obtained for correlative analyzes. Tests with the implemented computer vision software have stablished the use of size filters between 500 and 16300 pixels and contrast level greater than 50% for the segmentation of Regions of Interest (ROIs). The test also indicated the best performance of the Mode Value segmentation algorithm and of a training set composed by 9 classes with 300 organisms each for automatic classification. Due to the low global accuracy obtained in the automatic classification stage of unknown images of organisms (27%), the objects were analyzed in this study as particle, divided according to the size of their major axis in three ranges (<385 μm; 385 - 620 μm; >620μm). Particle analysis, for statistical reasons, considered the largest continuous sampling range of the series, from April 5 to May 7, 2017. First, the series of each variables decomposed into harmonic components, based on Fourier analysis, aiming to detect recurrent patterns, and then the variables with more expressive spectral density peaks at frequencies of the order of one week and one day were compared by means of square coherence. The smaller particles of range 1 were the ones that best represented the total abundance, and the highest values of coherence were among the variables with characteristic period of one day. The instrumentation implemented and tested over about 3 months allowed the acquisition og high-quality images and the initial results were useful for improving the system, aiming at future long-term deployments in coastal environments.