A detecção de gestos é uma etapa importante em aplicações de interação humanocomputador. Se a mão do usuário é detectada com precisão, tanto a análise quanto o reconhecimento do gesto de mão se tornam mais simples e confiáveis. Neste trabalho, descrevemos um novo método para detecção de pele humana, destinada a ser empregada como uma etapa de pré-processamento para segmentação de gestos de mão em sistemas que visam o seu reconhecimento. Primeiramente, treinamos os modelos de cor e textura de pele (material a ser identificado) a partir de um conjunto de treinamento formado por imagens de pele. Nessa etapa, construímos um modelo de mistura de Gaussianas (GMM), para determinar os tons de cor da pele e um dicionário de textons, para textura de pele. Em seguida, introduzimos um estratégia de fusão estocástica de regiões de texturas, para determinar todos os segmentos de diferentes materiais presentes na imagem (cada um associado a uma textura). Tendo obtido todas as regiões, cada segmento encontrado é classificado com base nos modelos de cor de pele (GMM) e textura de pele (dicionário de textons). Para testar o desempenho do algoritmo desenvolvido realizamos experimentos com o conjunto de imagens SDC, projetado especialmente para esse tipo de avaliação (detecção de pele humana). Comparado com outras técnicas do estado-daarte em segmentação de pele humana disponíveis na literatura, os resultados obtidos em nossos experimentos mostram que a abordagem aqui proposta é resistente às variações de cor e iluminação decorrentes de diferentes tons de pele (etnia do usuário), assim como de mudanças de pose da mão, mantendo sua capacidade de discriminar pele humana de outros materiais altamente texturizados presentes na imagem. / Gesture detection is an important task in human-computer interaction applications. If the hand of the user is precisely detected, both analysis and recognition of hand gesture become more simple and reliable. This work describes a new method for human skin detection, used as a pre-processing stage for hand gesture segmentation in recognition systems. First, we obtain the models of color and texture of human skin (material to be identified) from a training set consisting of skin images. At this stage, we build a Gaussian mixture model (GMM) for identifying skin color tones and a dictionary of textons for skin texture. Then, we introduce a stochastic region merging strategy, to determine all segments of different materials present in the image (each associated with a texture). Once the texture regions are obtained, each segment is classified based on skin color (GMM) and skin texture (dictionary of textons) model. To verify the performance of the developed algorithm, we perform experiments on the SDC database, specially designed for this kind of evaluation (human skin detection). Also, compared with other state-ofthe- art skin segmentation techniques, the results obtained in our experiments show that the proposed approach is robust to color and illumination variations arising from different skin tones (ethnicity of the user) as well as changes of pose, while keeping its ability for discriminating human skin from other highly textured background materials.

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2017-02-24T13:58:39Z No. of bitstreams: 2 Dissertação - Daniela de Oliveira Albanez - 2017.pdf: 10127114 bytes, checksum: 4c037243629d84539257a8febc621fa8 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-02-24T13:59:39Z (GMT) No. of bitstreams: 2 Dissertação - Daniela de Oliveira Albanez - 2017.pdf: 10127114 bytes, checksum: 4c037243629d84539257a8febc621fa8 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-02-24T13:59:39Z (GMT). No. of bitstreams: 2 Dissertação - Daniela de Oliveira Albanez - 2017.pdf: 10127114 bytes, checksum: 4c037243629d84539257a8febc621fa8 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-02-15 / Image segmentation is one of image processing that problems that deserve special interest of the scientific community, given its real utility and application in various areas as medicine, geography, engineering, mathematics and computing, just to name a few. Much of the recent interest in segmentation has been motivated by the availability of satellite images on the Earth’s surface, which can be transformed into concrete knowledge, aiming at land use monitoring and data mining. This work proposes a new segmentation method, using Arficial Intelligence techniques, more specifically Artificial Neural Networks (ANNs), and compare its results of segmentation of satellite images with the original method. The binarized results are compared with the ground truth for the validation of the proposed segmentation method. Experimental results, quantative analysis of segmentation results, indicating that the proposed segmentation method generates better results and a decaying of 36.60% in the total average computacional time when compared with the original method. / Segmentação de Imagens é um dos problemas de processamento de imagens que mercê especial interesse da comunidade científica, tendo em vista sua real utilidade e aplicação em várias áreas do conhecimento como a medicina, geografia, engenharia, matemática e computação, só para citar algumas. Grande parte do interesse recente sobre segmentação foi motivado pela disponibilidade de imagens de satélite sobre a superfície da Terra, que podem ser transformadas em conhecimento concreto, visando o monitoramento e a mineração do uso da terra. Este trabalho propõe um novo método de segmentação, através de técnicas de Inteligência Artificial, mais especificamente pelas Redes Neurais Artificiais (RNA’s), e compara seus resultados de segmentação de imagens de satélite com o método original descrito na literatura. Os resultados binarizados são comparados com o ground truth para a validação do método de segmentação proposto. Resultados experimentais, realizados através da analise quantitativa dos resultados de segmentação, indicam que o método de segmentação proposto produz melhores resultados e uma redução média total do desempenho computacional de 36.60% em relação ao método original.

A segmentação de imagens e, em visão computacional, uma tarefa de grande importância, para a qual existem várias abordagem. A complexidade de tais abordagens está relacionada à natureza da imagem e também ao grau de precisão da segmentação, que e um conceito bastante subjetivo, normalmente associado a semelhança que apresenta a segmentaçã produzida pela visão humana. Na segmentação de imagens baseada em algoritmos de agrupamento em grafos, geralmente os pixels da imagem compôem os nós do grafo e as arestas representam a similaridade entre estes nós. Assim, a segmentação pode ser obtida por meio do agrupamento dos nós do grafo. É importante salientar, no entanto, que as técnicas de agrupamento em grafos surgiram no contexto de reconhecimento de padrões, cujo objetivo primario era o tratamento de dados diversos que não envolviam imagens. O uso de tais tecnicas para a segmentação de imagens e relativamente recente e revela alguns problemas desaadores. O primeiro deles é a deficiente escalabilidade de alguns métodos, o que impede o seu uso efetivo em imagens de altas dimensões. Outra questão é a falta de estudos que avaliam as medidas de similaridade na montagem do grafo e critérios que aferem a qualidade do agrupamento para a área específica de segmentação de imagens. Em outras palavras, faltam na literatura análises mais específicas que indiquem quais algoritmos de agrupamento em grafos são mais efetivos para a segmentação de imagens e que procurem associar (ou correlacionar) as várias medidas de similaridade e métricas de qualidade de agrupamento que produzam segmentações mais precisas. Neste trabalho é apresentada a avaliação de 6 algoritmos de agrupamento em grafos formulados em base a 3 categorias identificadas (agrupamento espectral, algoritmos de particionamento multinível e algoritmos para detectar comunidades) e aplicadas na segmentação automática de imagens de cenas naturais com grandes dimensões. Esta avaliação objetiva aferir, sobretudo, a qualidade da segmentação, a escalabilidade, o desempenho de 7 funções de similaridade formuladas, e também visa corroborar a existência da correlação entre a qualidade do agrupamento e a qualidade da segmentação. Para reduzir o esforço computacional e contribuir com a escalabilidade dos algoritmos formulados é utilizado um algoritmo de pré-processamento (SLIC) que agrupa váarios pixels da imagem em uma unica região (superpixels), o que contribui para reduzir o tamanho do grafo e, consequentemente, reduzindo o custo computacional do agrupamento. Os resultados demostram que os algoritmos formulados LP (Label Propagation) e FG (Fast Greedy) apresentam boa escalabilidade e boa qualidade de segmentação. Seis das sete funções de similaridade avaliadas apresentam um bom desempenho, independentemente do algoritmo de agrupamento empregado. É mostrado também que exites correlação entre a medida de qualidade de agrupamento conhecido como índice de silhueta e a qualidade de segmentação, ou seja, quanto maior o valor de silhueta, melhor a segmentação. A qualidade de segmentação foi avaliada quantitativamente, utilizando-se um conjunto de imagens segmentadas manualmente / Image segmentation is an important task within computer vision for which many approaches are available. The complexity of such approaches are intrinsically related with the nature of the image and also the desired accuracy aimed at. Image segmentation accuracy, however, is a subjective concept and is normally associated with how much it resembles segmentation produced by the human vision system. In graphbased clustering image segmentation algorithms, pixels are normally represented as nodes and edges convey the similarity between such nodes. Hence, segmentation may be attained by means of grouping node of a graph. It is important, though, to point out that graph-based clustering techniques rst appeared in the context of pattern recognition and its primary data source were not images. The usage of such techniques for image segmentation is a recent trend and poses some challenge issues. The first is the poor scalability that many methods exhibit, impairing its application in images of larger dimensions. Another issues is that lack of studies that assess the goodness of similarity measures employed in graph computation and also clustering quality criteria assessments for the specic area of image processing. In other words, there is no evidences in the literature on how effective graph-based clustering algorithms are for image segmentation and no studies that associate similarity functions and clustering quality metrics with image processing quality. This work presents an evaluation of six graph-based clustering algorithms according to three major categories found in the literature (spectral clustering, multi layer partitioning algorithms and community detectors) applied to automatic segmentation of image of larger dimensions. This evaluation takes into account segmentation quality, scalability, the performance of seven similarity functions and, nally, bring some insights on the correlation between clustering and segmentation quality. To reduce computational costs and enhance scalability of the methods we employ a pre processing algorithm (SLIC) which combines many pixels into one single region (superpixel). This contributes to reduce the graph size and, consequently, the cost of clustering. Results have shown that the LP (Label Propagation) and FG (Fast Greedy) algorithms exhibit good scalability and good segmentation. Six out of the seven similarity functions presented good performance, regardless the clustering algorithm. We also have shown that there is correlation between clustering quality and image segmentation quality, when the Silhouette measure is employed. That is, the higher the Silhouette values, the better the segmentation. Image segmentation quality has been quantitatively assessed by means of ground-truth data or user segmented images

Orientador: Yuzo Iano / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-25T04:20:13Z (GMT). No. of bitstreams: 1 Freitas_ClaudioCesarSilvade_M.pdf: 6956740 bytes, checksum: a8ec8ed0154572009885ad4f604698e0 (MD5) Previous issue date: 2014 / Resumo: Está cada vez mais claro como a tecnologia biométrica tem se tornado mais presente no cotidiano das pessoas e tema de interesse de grupos de pesquisa ao redor do mundo. Isso é refletido pela grande quantidade de trabalhos existentes na área e muitos investimentos comerciais. Tecnologias biométricas são basicamente sistemas com capacidade de identificar e verificar a identidade de um indivíduo por meio de uma característica física ou comportamental. Esse trabalho propõe um estudo sobre o reconhecimento das linhas palmares que utiliza a análise de componentes principais como método de reconhecimento. A motivação para esse estudo está na importância de melhorar os métodos existentes de biometria, visto que ainda não existe uma técnica livre de erros ou falsificações. Este estudo é importante pois irá apresentar a aplicação do PCA para a detecção das linhas palmares utilizando uma técnica simples de limiarização adaptativa para extrair as informações biométricas da imagem palmar. Os resultados dessa pesquisa mostraram que o PCA apresentou um desempenho superior quando utilizamos a limiarização adaptativa para a extração das linhas principais da palma da mão. Conclui-se que essa modalidade biométrica apresenta um bom potencial para ser utilizada como medida de identificação e verificação de um usuário. Contudo, é necessário que sejam utilizados os algoritmos de processamento adequados, assim como, deve-se levar em consideração a qualidade e resolução da imagem, o tipo de processamento e o custo computacional necessário / Abstract: It is easy to identify how biometric technology has become more present in daily life as it has become the subject of interest from research groups around the world. This reality is a result of a large amount of existing work in the area and many commercial investments. Biometric technologies are basically systems developed in order to identify and verify the identity of an individual through a physical or behavioral characteristic. This work proposes a study on palmprint recognition using PCA and local adaptive thresholding. The motivation for this study is the importance of improving existing methods of biometric systems, since there is no technique completely safe against fails or steals. This is a simple technique used in order to facilitate the development of a palmprint recognition system using simple methods to be applied in different systems, such as embedded systems. The results of this research showed that the PCA reached superior performance when using adaptive thresholding to extract the lines from the palmprint. We conclude that the biometric modality proposed in this study has a good potential to be used in identification and verification of a user. However, it is necessary to use the appropriate algorithm in image processing in order to extract as much information as possible. Additionally, it is necessary to consider the image resolution, and the hardware and computational cost involved in the method proposed / Mestrado / Telecomunicações e Telemática / Mestre em Engenharia Elétrica

Medical imaging is an important tool for diagnosis and treatment planning today. However as the demand for efficiency increases at the same time as the data volumes grow immensely, the need for computer assisted analysis, such as image segmentation, to help and guide the practitioner increases. Medical image segmentation could be used for various different tasks, the localization and delineation of pathologies such as cancer tumors is just one example. Numerous problems with noise and image artifacts in the generated images make the segmentation a difficult task, and the developer is forced to choose between speed and performance. In clinical practise, however, this is impossible as both speed and performance are crucial. One solution to this problem might be to involve the user more in the segmentation, using interactivite algorithms where the user might influence the segmentation for an improved result. This thesis has concentrated on finding a fast and interactive segmentation method for liver tumor segmentation. Various different methods were explored, and a few were chosen for implementation and further development. Two methods appeared to be the most promising, Bayesian Region Growing (BRG) and Level Set. An interactive Level Set algorithm emerged as the best alternative for the interactivity of the algorithm, and could be used in combination with both BRG and Level Set. A new data term based on a probability model instead of image edges was also explored for the Level Set-method, and proved to be more promising than the original one. The probability based Level Set and the BRG method both provided good quality results, but the fastest of the two was the BRG-method, which could segment a tumor present in 25 CT image slices in less than 10 seconds when implemented in Matlab and mex-C++ code on an ACPI x64-based PC with two 2.4 GHz Intel(R) Core(TM) 2CPU and 8 GB RAM memory. The interactive Level Set could be succesfully used as an interactive addition to the automatic method, but its usefulness was somewhat reduced by its slow processing time ( 1.5 s/slice) and the relative complexity of the needed user interactions.

The human vision system is generally recognized as being superior to all known artificial vision systems. Visual attention, among many processes that are related to human vision, is responsible for identifying relevant regions in a scene for further processing. In most cases, analyzing an entire scene is unnecessary and inevitably time consuming. Hence considering visual attention might be advantageous. A subfield of computer vision where this particular functionality is computationally emulated has been shown to retain high potential in solving real world vision problems effectively. In this monograph, elements of visual attention are explored and algorithms are proposed that exploit such elements in order to enhance image understanding capabilities. Satellite images are given special attention due to their practical relevance, inherent complexity in terms of image contents, and their resolution. Processing such large-size images using visual attention can be very helpful since one can first identify relevant regions and deploy further detailed analysis in those regions only. Bottom-up features, which are directly derived from the scene contents, are at the core of visual attention and help identify salient image regions. In the literature, the use of intensity, orientation and color as dominant features to compute bottom-up attention is ubiquitous. The effects of incorporating an entropy feature on top of the above mentioned ones are also studied. This investigation demonstrates that such integration makes visual attention more sensitive to fine details and hence retains the potential to be exploited in a suitable context. One interesting application of bottom-up attention, which is also examined in this work, is that of image segmentation. Since low salient regions generally correspond to homogenously textured regions in the input image; a model can therefore be learned from a homogenous region and used to group similar textures existing in other image regions. Experimentation demonstrates that the proposed method produces realistic segmentation on satellite images. Top-down attention, on the other hand, is influenced by the observer’s current states such as knowledge, goal, and expectation. It can be exploited to locate target objects depending on various features, and increases search or recognition efficiency by concentrating on the relevant image regions only. This technique is very helpful in processing large images such as satellite images. A novel algorithm for computing top-down attention is proposed which is able to learn and quantify important bottom-up features from a set of training images and enhances such features in a test image in order to localize objects having similar features. An object recognition technique is then deployed that extracts potential target objects from the computed top-down attention map and attempts to recognize them. An object descriptor is formed based on physical appearance and uses both texture and shape information. This combination is shown to be especially useful in the object recognition phase. The proposed texture descriptor is based on Legendre moments computed on local binary patterns, while shape is described using Hu moment invariants. Several tools and techniques such as different types of moments of functions, and combinations of different measures have been applied for the purpose of experimentations. The developed algorithms are generalized, efficient and effective, and have the potential to be deployed for real world problems. A dedicated software testing platform has been designed to facilitate the manipulation of satellite images and support a modular and flexible implementation of computational methods, including various components of visual attention models.

L'objectif de cette thèse concerne l'analyse automatique d'images de façades de bâtiments à partir de descriptions formelles à priori de formes géométriques. Ces informations suggérées par un utilisateur permettent de modéliser, de manière formelle, des contraintes spatiales plus ou moins dures quant à la segmentation sémantique produite par le système. Ceci permet de se défaire de deux principaux écueils inhérents aux méthodes d'analyse de façades existantes qui concernent d'une part la coûteuse fidélité de la segmentation résultante aux données visuelles de départ, d'autre part, la spécificité architecturale des règles imposées lors du processus de traitement. Nous proposons d'explorer au travers de cette thèse, différentes méthodes alternatives à celles proposées dans la littérature en exploitant un formalisme de représentation d'à priori de haut niveau d'abstraction, les propriétés engendrées par ces nouvelles méthodes ainsi que les outils de résolution mis en œuvres par celles-ci. Le système résultant est évalué tant quantitativement que qualitativement sur de multiples bases de données standards et par le biais d'études comparatives à des approches à l'état de l'art en la matière. Parmi nos contributions, nous pouvons citer la combinaison du formalisme des grammaires de graphes exprimant les variations architecturales de façades de bâtiments et les modèles graphiques probabilistes modélisant l'énergie attribuée à une configuration paramétrique donnée, dans un schéma d'optimisation par minimisation d'énergie; ainsi qu'une nouvelle approche par programmation linéaire d'analyse avec à priori de formes. Enfin, nous proposons un formalisme flexible de ces à priori devançant de par ses performances les méthodes à l'état de l'art tout en combinant les avantages de la généricité de contraintes simples manuellement imposées par un utilisateur, à celles de la précision de la segmentation finale qui se faisait jusqu'alors au prix d'un encodage préliminaire restrictif de règles grammaticales complexes propres à une famille architecturale donnée. Le système décrit permet également de traiter avec robustesse des scènes comprenant des objets occultants et pourrait encore être étendu notamment afin de traiter l'extension tri-dimensionnelle de la sémantisation d'environnements urbains sous forme de nuages de points 3D ou d'une analyse multi-image de bâtiments / The aim of this work is to propose a framework for facade segmentation with user-defined shape priors. In such a framework, the user specifies a shape prior using a rigorously defined shape prior formalism. The prior expresses a number of hard constraints and soft preference on spatial configuration of segments, constituting the final segmentation. Existing approaches to the problem are affected by a compromise between the type of constraints, the satisfaction of which can be guaranteed by the segmentation algorithm, and the capability to approximate optimal segmentations consistent with a prior. In this thesis we explore a number of approaches to facade parsing that combine prior formalism featuring high expressive power, guarantees of conformance of the resulting segmentations to the prior, and effective inference. We evaluate the proposed algorithms on a number of datasets. Since one of our focus points is the accuracy gain resulting from more effective inference algorithms, we perform a fair comparison to existing methods, using the same data term. Our contributions include a combination of graph grammars for expressing variation of facade structure with graphical models encoding the energy of models of given structures for different positions of facade elements. We also present the first linear formulation of facade parsing with shape priors. Finally, we propose a shape prior formalism that enables formulating the problem of optimal segmentation as the inference in a Markov random field over the standard four-connected grid of pixels. The last method advances the state of the art by combining the flexibility of a user-defined grammar with segmentation accuracy that was reserved for frameworks with pre-defined priors before. It also enables handling occlusions by simultaneously recovering the structure of the occluded facade and segmenting the occluding objects. We believe that it can be extended in many directions, including semantizing three-dimensional point clouds and parsing images of general urban scenes

A segmentação é um passo importante em praticamente todas as tarefas que envolvem processamento de imagens digitais. Devido à variedade de imagens e diferentes necessidades da segmentação, a automação da segmentação não é uma tarefa trivial. Em muitas situações, abordagens interativas, nas quais o usuário pode intervir para guiar o processo de segmentação, são bastante úteis. Abordagens baseadas na transformação watershed mostram-se adequadas para a segmentação interativa de imagens: o watershed a partir de marcadores possibilita que o usuário marque as regiões de interesse na imagem; o watershed hierárquico gera uma hierarquia de partições da imagem sendo analisada, hierarquia na qual o usuário pode navegar facilmente e selecionar uma particular partição (segmentação). Em um trabalho prévio, propomos um método que integra as duas abordagens de forma que o usuário possa combinar os pontos fortes dessas duas formas de interação intercaladamente. Apesar da versatilidade obtida ao se integrar as duas abordagens, as hierarquias construídas dificilmente contêm partições interessantes e o esforço de interação necessário para se obter um resultado desejado pode ser muito elevado. Nesta tese propomos um método, baseado em aprendizagem computacional, que utiliza imagens previamente segmentadas para tentar adaptar uma dada hierarquia de forma que esta contenha partições mais próximas de uma partição de interesse. Na formulação de aprendizagem computacional, diferentes características da imagem são associadas a possíveis contornos de regiões, e esses são classificados como contornos que devem ou não estar presentes na partição final por uma máquina de suporte vetorial previamente treinada. A hierarquia dada é adaptada de forma a conter uma partição que seja consistente com a classificação obtida. Essa abordagem é particularmente interessante em cenários nos quais lotes de imagens similares ou sequências de imagens, como frames em sequências de vídeo ou cortes produzidas por exames de diagnóstico por imagem, precisam ser segmentadas. Nesses casos, é esperado que, a cada nova imagem a ser segmentada, o esforço de interação necessário para se obter a segmentação desejada seja reduzido em relação ao esforço que seria necessário com o uso da hierarquia original. Para não dependermos de experimentos com usuários na avaliação da redução no esforço de interação, propomos e utilizamos um modelo de interação que simula usuários humanos no contexto de segmentação hierárquica. Simulações deste modelo foram comparadas com sequências de interação observadas em experimentos com usuários humanos. Experimentos com diferentes lotes e sequências de imagens mostram que o método é capaz de reduzir o esforço de interação. / Segmentation is an important step in nearly all tasks involving digital image processing. Due to the variety of images and segmentation needs, automation of segmentation is not a trivial task. In many situations, interactive approaches in which the user can intervene to guide the segmentation process, are quite useful. Watershed transformation based approaches are suitable for interactive image segmentation: the watershed from markers allows the user to mark the regions of interest in the image; the hierarchical watershed generates a hierarchy of partitions of the image being analyzed, hierarchy in which the user can easily navigate and select a particular partition (segmentation). In a previous work, we have proposed a method that integrates the two approaches so that the user can combine the strong points of these two forms of interaction interchangeably. Despite the versatility obtained by integrating the two approaches, the built hierarchies hardly contain interesting partitions and the interaction effort needed to obtain a desired outcome can be very high. In this thesis we propose a method, based on machine learning, that uses images previously segmented to try to adapt a given hierarchy so that it contains partitions closer to the partition of interest. In the machine learning formulation, different image features are associated to the possible region contours, and these are classified as ones that must or must not be present in the final partition by a previously trained support vector machine. The given hierarchy is adapted to contain a partition that is consistent with the obtained classification. This approach is particularly interesting in scenarios where batches of similar images or sequences of images, such as frames in video sequences or cuts produced by imaging diagnosis procedures, need to be segmented. In such cases, it is expected that for each new image to be segmented, the interaction effort required to achieve the desired segmentation is reduced relative to the effort that would be required when using the original hierarchy. In order to do not depend on experiments with users in assessing the reduction in interaction effort, we propose and use an interaction model that simulates human users in the context of hierarchical segmentation. Simulations of this model were compared with interaction sequences observed in experiments with humans users. Experiments with different bacthes and image sequences show that the method is able to reduce the interaction effort.

Segmentation, recognition and 3D reconstruction of objects have been cutting-edge research topics, which have many applications ranging from environmental and medical to geographical applications as well as intelligent transportation. In this dissertation, I focus on the study of segmentation, recognition and 3D reconstruction of objects using LiDAR data/MRI. Three main works are that (I). Feature extraction algorithm based on sparse LiDAR data. A novel method has been proposed for feature extraction from sparse LiDAR data. The algorithm and the related principles have been described. Also, I have tested and discussed the choices and roles of parameters. By using correlation of neighboring points directly, statistic distribution of normal vectors at each point has been effectively used to determine the category of the selected point. (II). Segmentation and 3D reconstruction of objects based on LiDAR/MRI. The proposed method includes that the 3D LiDAR data are layered, that different categories are segmented, and that 3D canopy surfaces of individual tree crowns and clusters of trees are reconstructed from LiDAR point data based on a region active contour model. The proposed method allows for delineations of 3D forest canopy naturally from the contours of raw LiDAR point clouds. The proposed model is suitable not only for a series of ideal cone shapes, but also for other kinds of 3D shapes as well as other kinds dataset such as MRI. (III). Novel algorithms for recognition of objects based on LiDAR/MRI. Aimed to the sparse LiDAR data, the feature extraction algorithm has been proposed and applied to classify the building and trees. More importantly, the novel algorithms based on level set methods have been provided and employed to recognize not only the buildings and trees, the different trees (e.g. Oak trees and Douglas firs), but also the subthalamus nuclei (STNs). By using the novel algorithms based on level set method, a 3D model of the subthalamus nuclei (STNs) in the brain has been successfully reconstructed based on the statistical data of previous investigations of an anatomy atlas as reference. The 3D rendering of the subthalamic nuclei and the skull directly from MR imaging is also utilized to determine the 3D coordinates of the STNs in the brain. In summary, the novel methods and algorithms of segmentation, recognition and 3D reconstruction of objects have been proposed. The related experiments have been done to test and confirm the validation of the proposed methods. The experimental results also demonstrate the accuracy, efficiency and effectiveness of the proposed methods. A framework for segmentation, recognition and 3D reconstruction of objects has been established, which has been applied to many research areas.

The aim of the first part of this thesis is to explain the theoretical basis of transmission electron microscopy and to mention fundamental parts of transmission electron microscopes. The next part of this work is focused on possible methods of image segmentation, the use of neural networks in the detection of objects in an image and the subsequent clustering of results. The theoretical part of the thesis is concluded with an explanation of some already published methods of automatic detection of biological structures in microscopic images and theoretical design of the algorithm, which will be subsequently developed. The process of training neural networks in order to automatically detect biological structures in an image is described at the beginning of the practical part. This is followed by an evaluation of the results achieved by these networks. Subsequently, cluster analysis methods are applied to these results, the products of which are compared with each other and also with the results obtained by already published methods.