Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.

Cette thèse a pour objectif d'améliorer la classification d'objets sous-marins dans des images sonar haute résolution. En particulier, il s'agit de distinguer les mines des objets inoffensifs parmi une collection d'objets ressemblant à des mines. Nos recherches ont été dirigées par deux contraintes classiques en guerre de la mine : d'une part, le manque de données et d'autre part, le besoin de lisibilité des décisions. Nous avons donc constitué une base de données la plus représentative possible et simulé des objets dans le but de la compléter. Le manque d'exemples nous a mené à utiliser une représentation compacte, issue de la reconnaissance de visages : les Structural Binary Gradient Patterns (SBGP). Dans la même optique, nous avons dérivé une méthode d'adaptation de domaine semi-supervisée, basée sur le transport optimal, qui peut être facilement interprétable. Enfin, nous avons développé un nouvel algorithme de classification : les Ensemble of Exemplar-Maximum Excluding Ball (EE-MEB) qui sont à la fois adaptés à des petits jeux de données mais dont la décision est également aisément analysable / This thesis aims to improve the classification of underwater objects in high resolution sonar images. Especially, we seek to make the distinction between mines and harmless objects from a collection of mine-like objects. Our research was led by two classical constraints of the mine warfare : firstly, the lack of data and secondly, the need for readability of the classification. In this context, we built a database as much representative as possible and simulated objects in order to complete it. The lack of examples led us to use a compact representation, originally used by the face recognition community : the Structural Binary Gradient Patterns (SBGP). To the same end, we derived a method of semi-supervised domain adaptation, based on optimal transport, that can be easily interpreted. Finally, we developed a new classification algorithm : the Ensemble of Exemplar-Maximum Excluding Ball (EE-MEB) which is suitable for small datasets and with an easily interpretable decision function

Digital image archiving urgently requires advanced techniques for more efficient storage and retrieval methods because of the increasing amount of digital. Although JPEG supply systems to compress image data efficiently, the problems of how to organize the image database structure for efficient indexing and retrieval, how to index and retrieve image data from DCT compressed domain and how to interpret image data semantically are major obstacles for further development of digital image database system. In content-based image, image analysis is the primary step to extract useful information from image databases. The difficulty in content-based image retrieval is how to summarize the low-level features into high-level or semantic descriptors to facilitate the retrieval procedure. Such a shift toward a semantic visual data learning or detection of semantic objects generates an urgent need to link the low level features with semantic understanding of the observed visual information. To solve such a 'semantic gap' problem, an efficient way is to develop a number of classifiers to identify the presence of semantic image components that can be connected to semantic descriptors. Among various semantic objects, the human face is a very important example, which is usually also the most significant element in many images and photos. The presence of faces can usually be correlated to specific scenes with semantic inference according to a given ontology. Therefore, face detection can be an efficient tool to annotate images for semantic descriptors. In this thesis, a paradigm to process, analyze and interpret digital images is proposed. In order to speed up access to desired images, after accessing image data, image features are presented for analysis. This analysis gives not only a structure for content-based image retrieval but also the basic units ii for high-level semantic image interpretation. Finally, images are interpreted and classified into some semantic categories by semantic object detection categorization algorithm.

Submitted by Angela Maria de Oliveira (amolivei@uepg.br) on 2019-02-28T17:58:29Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Renan Rosa.pdf: 4067327 bytes, checksum: eb0bd9e84fbd89a24b4a397c9655fa62 (MD5) / Made available in DSpace on 2019-02-28T17:58:29Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Renan Rosa.pdf: 4067327 bytes, checksum: eb0bd9e84fbd89a24b4a397c9655fa62 (MD5) Previous issue date: 2018-11-19 / As pragas em lavouras causam prejuízos econômicos na agricultura, reduzindo a produção e consequentemente os lucros. O manejo de pragas é essencial, para reduzir estes prejuízos, e consiste na identificação e posterior controle desse tipo de ameaça. O controle é fundamentalmente dependente da identificação, pois é a partir dela que o manejo é feito. A identificação é feita visualmente, baseando-se nas características da praga. Essas características são inerentes e diferem de espécie para espécie. Devido à dificuldade da identificação, esse processo é realizado principalmente por profissionais especializados na área, o que acarreta na concentração do conhecimento. Esta dissertação apresenta uma metodologia para classificação de pragas por meio de técnicas de computação, onde um sistema computacional do tipo clienteservidor foi criado a fim de prover a classificação de pragas por meio de serviço, que é realizado pelo uso de rede neural convolucional baseada na arquitetura Inception V3. As pragas Anticarsia Gemmatalis, Helicoverpa armigera e Spodoptera Cosmioides, foram escolhidas para classificação por serem bastante comuns no estado do Paraná. A rede neural convolucional obteve índice de acerto de 92,5%. / Pests on crops cause economic damage to agriculture, reducing production and consequently profits. Pest management is essential to reduce these losses, and consists in the identification and subsequent control of this type of threat. Control is fundamentally dependent on identification, because management is done from it. The identification is made visually, based on the characteristics of the pest. These characteristics are inherent and differ from species to species. Due to the difficulty of identification, this process is carried out mainly by professionals specialized in the area, which entails the concentration of knowledge. This dissertation presents a methodology for pest classification by means of computational techniques, in which a client-server computational system was created in order to provide pest classification by means of a service, which is performed by the use of convolutional neural network based in the Inception V3 architecture. The pests Anticarsia Gemmatalis, Helicoverpa armigera and Spodoptera Cosmioides, were chosen for classification because they are quite common in the state of Paraná. The convolutional neural network obtained a success rate of 92.5%.

Thesis (MSc)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: Supervised classifiers are commonly used in remote sensing to extract land cover information. They are, however, limited in their ability to cost-effectively produce sufficiently accurate land cover maps. Various factors affect the accuracy of supervised classifiers. Notably, the number of available training samples is known to significantly influence classifier performance and to obtain a sufficient number of samples is not always practical. The support vector machine (SVM) does perform well with a limited number of training samples. But little research has been done to evaluate SVM’s performance for geographical object-based image analysis (GEOBIA). GEOBIA also allows the easy integration of additional features into the classification process, a factor which may significantly influence classification accuracies. As such, two experiments were developed and implemented in this research. The first compared the performances of object-based SVM, maximum likelihood (ML) and nearest neighbour (NN) classifiers using varying training set sizes. The effect of feature dimensionality on classifier accuracy was investigated in the second experiment. A SPOT 5 subscene and a four-class classification scheme were used. For the first experiment, training set sizes ranging from 4-20 per land cover class were tested. The performance of all the classifiers improved significantly as the training set size was increased. The ML classifier performed poorly when few (<10 per class) training samples were used and the NN classifier performed poorly compared to SVM throughout the experiment. SVM was the superior classifier for all training set sizes although ML achieved competitive results for sets of 12 or more training samples per class. Training sets were kept constant (20 and 10 samples per class) for the second experiment while an increasing number of features (1 to 22) were included. SVM consistently produced superior classification results. SVM and NN were not significantly (negatively) affected by an increase in feature dimensionality, but ML’s ability to perform under conditions of large feature dimensionalities and few training areas was limited. Further investigations using a variety of imagery types, classification schemes and additional features; finding optimal combinations of training set size and number of features; and determining the effect of specific features should prove valuable in developing more costeffective ways to process large volumes of satellite imagery. KEYWORDS Supervised classification, land cover, support vector machine, nearest neighbour classification maximum likelihood classification, geographic object-based image analysis / AFRIKAANSE OPSOMMING: Gerigte klassifiseerders word gereeld aangewend in afstandswaarneming om inligting oor landdekking te onttrek. Sulke klassifiseerders het egter beperkte vermoëns om akkurate landdekkingskaarte koste-effektief te produseer. Verskeie faktore het ʼn uitwerking op die akkuraatheid van gerigte klassifiseerders. Dit is veral bekend dat die getal beskikbare opleidingseenhede ʼn beduidende invloed op klassifiseerderakkuraatheid het en dit is nie altyd prakties om voldoende getalle te bekom nie. Die steunvektormasjien (SVM) werk goed met beperkte getalle opleidingseenhede. Min navorsing is egter gedoen om SVM se verrigting vir geografiese objek-gebaseerde beeldanalise (GEOBIA) te evalueer. GEOBIA vergemaklik die integrasie van addisionele kenmerke in die klassifikasie proses, ʼn faktor wat klassifikasie akkuraathede aansienlik kan beïnvloed. Twee eksperimente is gevolglik ontwikkel en geïmplementeer in hierdie navorsing. Die eerste eksperiment het objekgebaseerde SVM, maksimum waarskynlikheids- (ML) en naaste naburige (NN) klassifiseerders se verrigtings met verskillende groottes van opleidingstelle vergelyk. Die effek van kenmerkdimensionaliteit is in die tweede eksperiment ondersoek. ʼn SPOT 5 subbeeld en ʼn vier-klas klassifikasieskema is aangewend. Opleidingstelgroottes van 4-20 per landdekkingsklas is in die eerste eksperiment getoets. Die verrigting van die klassifiseerders het beduidend met ʼn toename in die grootte van die opleidingstelle verbeter. ML het swak presteer wanneer min (<10 per klas) opleidingseenhede gebruik is en NN het, in vergelyking met SVM, deurgaans swak presteer. SVM het die beste presteer vir alle groottes van opleidingstelle alhoewel ML kompeterend was vir stelle van 12 of meer opleidingseenhede per klas. Die grootte van die opleidingstelle is konstant gehou (20 en 10 eenhede per klas) in die tweede eksperiment waarin ʼn toenemende getal kenmerke (1 tot 22) toegevoeg is. SVM het deurgaans beter klassifikasieresultate gelewer. SVM en NN was nie beduidend (negatief) beïnvloed deur ʼn toename in kenmerkdimensionaliteit nie, maar ML se vermoë om te presteer onder toestande van groot kenmerkdimensionaliteite en min opleidingsareas was beperk. Verdere ondersoeke met ʼn verskeidenheid beelde, klassifikasie skemas en addisionele kenmerke; die vind van optimale kombinasies van opleidingstelgrootte en getal kenmerke; en die bepaling van die effek van spesifieke kenmerke sal waardevol wees in die ontwikkelling van meer koste effektiewe metodes om groot volumes satellietbeelde te prosesseer. TREFWOORDE Gerigte klassifikasie, landdekking, steunvektormasjien, naaste naburige klassifikasie, maksimum waarskynlikheidsklassifikasie, geografiese objekgebaseerde beeldanalise

La classification d'images s'articule généralement autour des deux étapes que sont l'étape d'extraction de signatures suivie de l'étape d'analyse des données extraites, ces dernières étant généralement quantitatives. De nombreux modèles de classification ont été proposés dans la littérature, le choix du modèle le plus adapté est souvent guidé par les performances en classification ainsi que la lisibilité du modèle. L'arbre de classification et le treillis de Galois sont deux modèles symboliques connus pour leur lisibilité. Dans sa thèse [Guillas 2007], Guillas a utilisé efficacement les treillis de Galois pour la classification d'images, et des liens structurels forts avec les arbres de classification ont été mis en évidence. Les travaux présentés dans ce manuscrit font suite à ces résultats, et ont pour but de définir un modèle hybride entre ces deux modèles, qui réunissent leurs avantages (leur lisibilité respective, la robustesse du treillis et le faible espace mémoire de l'arbre). A ces fins, l'étude des liens existants entre les deux modèles a permis de mettre en avant leurs différences. Tout d'abord, le type de discrétisation, les arbres utilisent généralement une discrétisation locale tandis que les treillis, initialement définis pour des données binaires, utilisent une discrétisation globale. A partir d'une étude des propriétés des treillis dichotomiques (treillis définis après une discrétisation), nous proposons une discrétisation locale pour les treillis permettant d'améliorer ses performances en classification et de diminuer sa complexité structurelle. Puis, le processus de post-élagage mis en œuvre dans la plupart des arbres a pour objectif de diminuer la complexité de ces derniers, mais aussi d'augmenter leurs performances en généralisation. Les simplifications de la structure de treillis (exponentielle en la taille de données dans les pires cas), quant à elles, sont motivées uniquement par une diminution de la complexité structurelle. En combinant ces deux simplifications, nous proposons une simplification de la structure du treillis obtenue après notre discrétisation locale et aboutissant à un modèle de classification hybride qui profite de la lisibilité des deux modèles tout en étant moins complexe que le treillis mais aussi performant que celui-ci. / Image classification is generally based on two steps namely the extraction of the image signature, followed by the extracted data analysis. Image signature is generally numerical. Many classification models have been proposed in the literature, among which most suitable choice is often guided by the classification performance and the model readability. Decision trees and Galois lattices are two symbolic models known for their readability. In her thesis {Guillas 2007}, Guillas efficiently used Galois lattices for image classification. Strong structural links between decision trees and Galois lattices have been highlighted. Accordingly, we are interested in comparing models in order to design a hybrid model between those two. The hybrid model will combine the advantages (robustness of the lattice, low memory space of the tree and readability of both). For this purpose, we study the links between the two models to highlight their differences. Firstly, the discretization type where decision trees generally use a local discretization while Galois lattices, originally defined for binary data, use a global discretization. From the study of the properties of dichotomic lattice (specific lattice defined after discretization), we propose a local discretization for lattice that allows us to improve its classification performances and reduces its structural complexity. Then, the process of post-pruning implemented in most of the decision trees aims to reduce the complexity of the latter, but also to improve their classification performances. Lattice filtering is solely motivated by a decrease in the structural complexity of the structures (exponential in the size of data in the worst case). By combining these two processes, we propose a simplification of the lattice structure constructed after our local discretization. This simplification leads to a hybrid classification model that takes advantage of both decision trees and Galois lattice. It is as readable as the last two, while being less complex than the lattice but also efficient.

<p>У оквиру докторске дисертације извршен је преглед стања постојећих начина<br />идентификације геопросторних објеката на основу података насталих на принципима<br />даљинске детекције. Извршена је анализа постојећих проблема и корака које је<br />неопходно провести како би се добили што бољи резултати идентификације<br />геопросторних објеката. Анализирани су поступци мапирања, начини сегментације<br />слике, критеријуми за идентификацију, селекцију и класификацију геопросторних<br />објеката као и методе класификације. На основу анализе креиран је модел<br />идентификовања геопросторних објеката базираних на објектно оријентисаној анализи<br />слике. На основу предложеног модела извршена је верификација модела у поступку<br />идентификовања зграда, пољопривредних површина, шумских површина и водених<br />површина које представљају студије случаја.</p> / <p>U okviru doktorske disertacije izvršen je pregled stanja postojećih načina<br />identifikacije geoprostornih objekata na osnovu podataka nastalih na principima<br />daljinske detekcije. Izvršena je analiza postojećih problema i koraka koje je<br />neophodno provesti kako bi se dobili što bolji rezultati identifikacije<br />geoprostornih objekata. Analizirani su postupci mapiranja, načini segmentacije<br />slike, kriterijumi za identifikaciju, selekciju i klasifikaciju geoprostornih<br />objekata kao i metode klasifikacije. Na osnovu analize kreiran je model<br />identifikovanja geoprostornih objekata baziranih na objektno orijentisanoj analizi<br />slike. Na osnovu predloženog modela izvršena je verifikacija modela u postupku<br />identifikovanja zgrada, poljoprivrednih površina, šumskih površina i vodenih<br />površina koje predstavljaju studije slučaja.</p> / <p>This PhD thesis includes an overview of the existing methods of identifying geospatial<br />objects from a remote sensing data, basically satellite or airplane images. The analysis<br />of existing problems and necessary steps in identification of remotely sensed data is<br />obtained in way to get the best results of identification of geospatial objects. The<br />mapping procedures, methods of image segmentation, the criteria for identification,<br />selection and classification of geospatial objects and methods of classification are also<br />analyzed. The result of analysis is a model of identifying geospatial objects based on<br />object-oriented image analysis. Based on the proposed model, verification of the<br />model was carried out. Afterwards case study of the proposed model is carried out in<br />process of identifying buildings, farmland, forest and water areas.</p>

Made available in DSpace on 2017-07-10T19:24:19Z (GMT). No. of bitstreams: 1 Clovis_Cechim_MC.pdf: 6987482 bytes, checksum: c33db297dd7ec8aaf8bfde9e1e56c2cc (MD5) Previous issue date: 2016-02-04 / Sugarcane has been cropped and produced in Brazil for a long time, so, it deserves mention because it makes the country as the largest producer, with also representativeness in sugar and ethanol production. The knowledge of reliable estimates concerning their cropped areas is essential for Brazilian agribusiness, as they help in determining prices to producers by power plants as well as allow establishing logistics flow of production. The cropped areas estimates are made by official agencies. Therefore, in order to reduce this subjectivity, geotechnology use comes as an alternative since it has been widely used in mappings agricultural crops. Thus, this study aimed at developing a methodology for mapping sugarcane crop in Paraná State with satellite images as LANDSAT, IRS and spectrum-temporal series of vegetation indexes from MODIS sensor, for 2010/2011 to 2014/2015 harvesting season. The carried out mappings indicated a strong positive correlation concerning Canasat and official IBGE. The developed method was based on Fuzzy ARTMAP classification and was efficient to map and estimate the sugarcane cropped area using vegetation index in Paraná State. / A cana-de-açúcar como cultura cultivada e produzida no Brasil merece destaque, pois torna o País o maior produtor mundial, com representatividade também na produção de açúcar e etanol. O conhecimento de estimativas confiáveis de suas áreas cultivadas é imprescindível para o agronegócio brasileiro, por auxiliar na determinação dos preços aos produtores pelas usinas e permitir estabelecer a logística de escoamento da produção. As estimativas de área cultivada são realizadas de forma subjetiva pelos órgãos oficiais. Com a finalidade de diminuir tal subjetividade, surge como alternativa o uso de geotecnologias, as quais têm sido muito utilizadas em mapeamentos de culturas agrícolas. Diante disto, o objetivo deste trabalho foi o desenvolvimento de uma metodologia para o mapeamento da cultura de cana-de-açúcar para o Estado do Paraná usando imagens dos satélites LANDSAT, IRS e de séries espectro-temporais de índices de vegetação, provenientes do sensor MODIS, para as safras de 2010/2011 a 2014/2015. O mapeamento da cultura foi realizado a partir do modelo de classificação supervisionada Fuzzy ARTMAP, tendo como variáveis de entrada, termos harmônicos de amplitude e fase e as métricas fenológicas da cultura. Os mapeamentos realizados indicaram forte correlação positiva com relação aos dados do Canasat e oficiais IBGE. O método desenvolvido com base na classificação Fuzzy ARTMAP demonstrou ser eficiente para mapear e estimar a área cultivada da cultura de cana-de-açúcar utilizando índices de vegetação no Estado do Paraná.

Made available in DSpace on 2017-05-12T14:47:35Z (GMT). No. of bitstreams: 1 Clovis_Cechim_MC.pdf: 6987482 bytes, checksum: c33db297dd7ec8aaf8bfde9e1e56c2cc (MD5) Previous issue date: 2016-02-04 / Sugarcane has been cropped and produced in Brazil for a long time, so, it deserves mention because it makes the country as the largest producer, with also representativeness in sugar and ethanol production. The knowledge of reliable estimates concerning their cropped areas is essential for Brazilian agribusiness, as they help in determining prices to producers by power plants as well as allow establishing logistics flow of production. The cropped areas estimates are made by official agencies. Therefore, in order to reduce this subjectivity, geotechnology use comes as an alternative since it has been widely used in mappings agricultural crops. Thus, this study aimed at developing a methodology for mapping sugarcane crop in Paraná State with satellite images as LANDSAT, IRS and spectrum-temporal series of vegetation indexes from MODIS sensor, for 2010/2011 to 2014/2015 harvesting season. The carried out mappings indicated a strong positive correlation concerning Canasat and official IBGE. The developed method was based on Fuzzy ARTMAP classification and was efficient to map and estimate the sugarcane cropped area using vegetation index in Paraná State. / A cana-de-açúcar como cultura cultivada e produzida no Brasil merece destaque, pois torna o País o maior produtor mundial, com representatividade também na produção de açúcar e etanol. O conhecimento de estimativas confiáveis de suas áreas cultivadas é imprescindível para o agronegócio brasileiro, por auxiliar na determinação dos preços aos produtores pelas usinas e permitir estabelecer a logística de escoamento da produção. As estimativas de área cultivada são realizadas de forma subjetiva pelos órgãos oficiais. Com a finalidade de diminuir tal subjetividade, surge como alternativa o uso de geotecnologias, as quais têm sido muito utilizadas em mapeamentos de culturas agrícolas. Diante disto, o objetivo deste trabalho foi o desenvolvimento de uma metodologia para o mapeamento da cultura de cana-de-açúcar para o Estado do Paraná usando imagens dos satélites LANDSAT, IRS e de séries espectro-temporais de índices de vegetação, provenientes do sensor MODIS, para as safras de 2010/2011 a 2014/2015. O mapeamento da cultura foi realizado a partir do modelo de classificação supervisionada Fuzzy ARTMAP, tendo como variáveis de entrada, termos harmônicos de amplitude e fase e as métricas fenológicas da cultura. Os mapeamentos realizados indicaram forte correlação positiva com relação aos dados do Canasat e oficiais IBGE. O método desenvolvido com base na classificação Fuzzy ARTMAP demonstrou ser eficiente para mapear e estimar a área cultivada da cultura de cana-de-açúcar utilizando índices de vegetação no Estado do Paraná.

This work describes completely new approach to detection of retinal nerve fibre layer (RNFL) loss in colour fundus images. Such RNFL losses indicate eye glaucoma illness and an early diagnosis of RNFL changes is very important for successful treatment. Method is presented with the purpose of supporting glaucoma diagnosis in ophthalmology. The proposed textural analysis method utilizes local binary patterns (LBP). This approach is characterized especially by computational simplicity and insensitivity to monotonic changes of illumination. Image histograms of LBP distributions are used to gain several textural features aimed to classify healthy or glaucomatous tissue of the retina. The method was experimentally tested using fundus images of glaucomatous patients with focal RNFL loss. The results show that the proposed method can be used in order to supporting diagnosis of glaucoma with satisfactory efficiency.