Caracterização de microorganismos aquáticos por processamento digital de imagens e redes neurais artificiais

A identificação e o monitoramento de microorganismos aquáticos, como bactérias e microalgas, tem sido uma tarefa árdua e morosa. Técnicas convencionais, com uso de microscópios e corantes, são complexas, exigindo um grande esforço por parte dos técnicos e pesquisadores. Uma das maiores dificuldades nos processos convencionais de identificação via microscopia é o elevado número de diferentes espécies e variantes existentes nos ambientes aquáticos, muitas com semelhança de forma e textura. O presente trabalho tem por objetivo o desenvolvimento de uma metodologia para a caracterização e classificação de microorganismos aquáticos (bactérias e microalgas), bem como a determinação de características cinemáticas, através do estudo da mobilidade de microalgas que possuem estruturas que permitem a natação (flagelos). Para caracterização e reconhecimento de padrões as metodologias empregadas foram: o processamento digital de imagens e redes neurais artificiais (RNA). Para a determinação da mobilidade dos microorganismos foram empregadas técnicas de velocimetria por processamento de imagens de partículas em movimento (Particle Tracking Velocimetry - PTV). O trabalho está dividido em duas partes: 1) caracterização e contagem de microalgas e bactérias aquáticas em amostras e 2) medição da velocidade de movimentação das microalgas em lâminas de microscópio. A primeira parte envolve a aquisição e processamento digital de imagens de microalgas, a partir de um microscópio ótico, sua caracterização e determinação da densidade de cada espécie contida em amostras. Por meio de um microscópio epifluorescente, foi possível, ainda, acompanhar o crescimento de bactérias aquáticas e efetuar a sua medição por operadores morfológicos. A segunda parte constitui-se na medição da velocidade de movimentação de microalgas, cujo parâmetro pode ser utilizado como um indicador para se avaliar o efeito de substâncias tóxicas ou fatores de estresse sobre as microalgas. O trabalho em desenvolvimento contribuirá para o projeto "Produção do Camarão Marinho Penaeus Paulensis no Sul do Brasil: Cultivo em estruturas Alternativas" em andamento na Estação Marinha de Aquacultura - EMA e para pesquisas no Laboratório de Ecologia do Fitoplâncton e de Microorganismos Marinhos do Departamento de Oceanografia da FURG. O trabalho propõe a utilização dos níveis de intensidade da imagem em padrão RGB e oito grandezas geométricas como características para reconhecimento de padrões das microalgas O conjunto proposto de características das microalgas, do ponto de vista de grandezas geométricas e da cor (nível de intensidade da imagem e transformadas Fourier e Radon), levou à geração de indicadores que permitiram o reconhecimento de padrões. As redes neurais artificiais desenvolvidas com topologia de rede multinível totalmente conectada, supervisionada, e com algoritmo de retropropagação, atingiram as metas de erro máximo estipuladas entre os neurônios de saída desejados e os obtidos, permitindo a caracterização das microalgas.

Uma Fundamentação Intervalar Aplicada à Morfologia Matemática

This work present a interval approach to deal with images with that contain uncertainties, as well, as treating these uncertainties through morphologic operations. Had been presented two intervals models. For the first, is introduced an algebraic space with three values, that was constructed based in the tri-valorada logic of Lukasiewiecz. With this algebraic structure, the theory of the interval binary images, that extends the classic binary model with the inclusion of the uncertainty information, was introduced. The same one can be applied to represent certain binary images with uncertainty in pixels, that it was originated, for example, during the process of the acquisition of the image. The lattice structure of these images, allow the definition of the morphologic operators, where the uncertainties are treated locally. The second model, extend the classic model to the images in gray levels, where the functions that represent these images are mapping in a finite set of interval values. The algebraic structure belong the complete lattices class, what also it allow the definition of the elementary operators of the mathematical morphology, dilation and erosion for this images. Thus, it is established a interval theory applied to the mathematical morphology to deal with problems of uncertainties in images

Detecção de rodovias em imagens digitais de alta resolução com o uso da teoria de morfologia matemática

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Quantificação de fibrose e enfisema em pacientes com paracoccidioidomicose (PCM) pulmonar, através de imagens de tomografia computadorizada de alta resolução (TCAR)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Segmentação morfológica aplicada à cartografia

Pós-graduação em Ciências Cartográficas - FCT

Detecção e restauração de áreas sombreadas em imagens digitais de alta resolução espacial

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Detecção automática e análise temporal de slope streaks na superfície de Marte

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Higher-order regularization and morphological techniques for image segmentation

La segmentación de imágenes es un campo importante de la visión computacional y una de las áreas de investigación más activas, con aplicaciones en comprensión de imágenes, detección de objetos, reconocimiento facial, vigilancia de vídeo o procesamiento de imagen médica. La segmentación de imágenes es un problema difícil en general, pero especialmente en entornos científicos y biomédicos, donde las técnicas de adquisición imagen proporcionan imágenes ruidosas. Además, en muchos de estos casos se necesita una precisión casi perfecta. En esta tesis, revisamos y comparamos primero algunas de las técnicas ampliamente usadas para la segmentación de imágenes médicas. Estas técnicas usan clasificadores a nivel de pixel e introducen regularización sobre pares de píxeles que es normalmente insuficiente. Estudiamos las dificultades que presentan para capturar la información de alto nivel sobre los objetos a segmentar. Esta deficiencia da lugar a detecciones erróneas, bordes irregulares, configuraciones con topología errónea y formas inválidas. Para solucionar estos problemas, proponemos un nuevo método de regularización de alto nivel que aprende información topológica y de forma a partir de los datos de entrenamiento de una forma no paramétrica usando potenciales de orden superior. Los potenciales de orden superior se están popularizando en visión por computador, pero la representación exacta de un potencial de orden superior definido sobre muchas variables es computacionalmente inviable. Usamos una representación compacta de los potenciales basada en un conjunto finito de patrones aprendidos de los datos de entrenamiento que, a su vez, depende de las observaciones. Gracias a esta representación, los potenciales de orden superior pueden ser convertidos a potenciales de orden 2 con algunas variables auxiliares añadidas. Experimentos con imágenes reales y sintéticas confirman que nuestro modelo soluciona los errores de aproximaciones más débiles. Incluso con una regularización de alto nivel, una precisión exacta es inalcanzable, y se requeire de edición manual de los resultados de la segmentación automática. La edición manual es tediosa y pesada, y cualquier herramienta de ayuda es muy apreciada. Estas herramientas necesitan ser precisas, pero también lo suficientemente rápidas para ser usadas de forma interactiva. Los contornos activos son una buena solución: son buenos para detecciones precisas de fronteras y, en lugar de buscar una solución global, proporcionan un ajuste fino a resultados que ya existían previamente. Sin embargo, requieren una representación implícita que les permita trabajar con cambios topológicos del contorno, y esto da lugar a ecuaciones en derivadas parciales (EDP) que son costosas de resolver computacionalmente y pueden presentar problemas de estabilidad numérica. Presentamos una aproximación morfológica a la evolución de contornos basada en un nuevo operador morfológico de curvatura que es válido para superficies de cualquier dimensión. Aproximamos la solución numérica de la EDP de la evolución de contorno mediante la aplicación sucesiva de un conjunto de operadores morfológicos aplicados sobre una función de conjuntos de nivel. Estos operadores son muy rápidos, no sufren de problemas de estabilidad numérica y no degradan la función de los conjuntos de nivel, de modo que no hay necesidad de reinicializarlo. Además, su implementación es mucho más sencilla que la de las EDP, ya que no requieren usar sofisticados algoritmos numéricos. Desde un punto de vista teórico, profundizamos en las conexiones entre operadores morfológicos y diferenciales, e introducimos nuevos resultados en este área. Validamos nuestra aproximación proporcionando una implementación morfológica de los contornos geodésicos activos, los contornos activos sin bordes, y los turbopíxeles. En los experimentos realizados, las implementaciones morfológicas convergen a soluciones equivalentes a aquéllas logradas mediante soluciones numéricas tradicionales, pero con ganancias significativas en simplicidad, velocidad y estabilidad. ABSTRACT Image segmentation is an important field in computer vision and one of its most active research areas, with applications in image understanding, object detection, face recognition, video surveillance or medical image processing. Image segmentation is a challenging problem in general, but especially in the biological and medical image fields, where the imaging techniques usually produce cluttered and noisy images and near-perfect accuracy is required in many cases. In this thesis we first review and compare some standard techniques widely used for medical image segmentation. These techniques use pixel-wise classifiers and introduce weak pairwise regularization which is insufficient in many cases. We study their difficulties to capture high-level structural information about the objects to segment. This deficiency leads to many erroneous detections, ragged boundaries, incorrect topological configurations and wrong shapes. To deal with these problems, we propose a new regularization method that learns shape and topological information from training data in a nonparametric way using high-order potentials. High-order potentials are becoming increasingly popular in computer vision. However, the exact representation of a general higher order potential defined over many variables is computationally infeasible. We use a compact representation of the potentials based on a finite set of patterns learned fromtraining data that, in turn, depends on the observations. Thanks to this representation, high-order potentials can be converted into pairwise potentials with some added auxiliary variables and minimized with tree-reweighted message passing (TRW) and belief propagation (BP) techniques. Both synthetic and real experiments confirm that our model fixes the errors of weaker approaches. Even with high-level regularization, perfect accuracy is still unattainable, and human editing of the segmentation results is necessary. The manual edition is tedious and cumbersome, and tools that assist the user are greatly appreciated. These tools need to be precise, but also fast enough to be used in real-time. Active contours are a good solution: they are good for precise boundary detection and, instead of finding a global solution, they provide a fine tuning to previously existing results. However, they require an implicit representation to deal with topological changes of the contour, and this leads to PDEs that are computationally costly to solve and may present numerical stability issues. We present a morphological approach to contour evolution based on a new curvature morphological operator valid for surfaces of any dimension. We approximate the numerical solution of the contour evolution PDE by the successive application of a set of morphological operators defined on a binary level-set. These operators are very fast, do not suffer numerical stability issues, and do not degrade the level set function, so there is no need to reinitialize it. Moreover, their implementation is much easier than their PDE counterpart, since they do not require the use of sophisticated numerical algorithms. From a theoretical point of view, we delve into the connections between differential andmorphological operators, and introduce novel results in this area. We validate the approach providing amorphological implementation of the geodesic active contours, the active contours without borders, and turbopixels. In the experiments conducted, the morphological implementations converge to solutions equivalent to those achieved by traditional numerical solutions, but with significant gains in simplicity, speed, and stability.

Sistemas de ayuda al diagnóstico y reconocimiento de microcalcificaciones en mamografía mediante descriptores de escala y redes jerárquicas

La presente Tesis investiga el campo del reconocimiento automático de imágenes mediante ordenador aplicado al análisis de imágenes médicas en mamografía digital. Hay un interés por desarrollar sistemas de aprendizaje que asistan a los radiólogos en el reconocimiento de las microcalcificaciones para apoyarles en los programas de cribado y prevención del cáncer de mama. Para ello el análisis de las microcalcificaciones se ha revelado como técnica clave de diagnóstico precoz, pero sin embargo el diseño de sistemas automáticos para reconocerlas es complejo por la variabilidad y condiciones de las imágenes mamográficas. En este trabajo se analizan los planteamientos teóricos de diseño de sistemas de reconocimiento de imágenes, con énfasis en los problemas específicos de detección y clasificación de microcalcificaciones. Se ha realizado un estudio que incluye desde las técnicas de operadores morfológicos, redes neuronales, máquinas de vectores soporte, hasta las más recientes de aprendizaje profundo mediante redes neuronales convolucionales, contemplando la importancia de los conceptos de escala y jerarquía a la hora del diseño y sus implicaciones en la búsqueda de la arquitectura de conexiones y capas de la red. Con estos fundamentos teóricos y elementos de diseño procedentes de otros trabajos en este área realizados por el autor, se implementan tres sistemas de reconocimiento de mamografías que reflejan una evolución tecnológica, culminando en un sistema basado en Redes Neuronales Convolucionales (CNN) cuya arquitectura se diseña gracias al análisis teórico anterior y a los resultados prácticos de análisis de escalas llevados a cabo en nuestra base de datos de imágenes. Los tres sistemas se entrenan y validan con la base de datos de mamografías DDSM, con un total de 100 muestras de entrenamiento y 100 de prueba escogidas para evitar sesgos y reflejar fielmente un programa de cribado. La validez de las CNN para el problema que nos ocupa queda demostrada y se propone un camino de investigación para el diseño de su arquitectura. ABSTRACT This Dissertation investigates the field of computer image recognition applied to medical imaging in mammography. There is an interest in developing learning systems to assist radiologists in recognition of microcalcifications to help them in screening programs for prevention of breast cancer. Analysis of microcalcifications has emerged as a key technique for early diagnosis of breast cancer, but the design of automatic systems to recognize them is complicated by the variability and conditions of mammographic images. In this Thesis the theoretical approaches to design image recognition systems are discussed, with emphasis on the specific problems of detection and classification of microcalcifications. Our study includes techniques ranging from morphological operators, neural networks and support vector machines, to the most recent deep convolutional neural networks. We deal with learning theory by analyzing the importance of the concepts of scale and hierarchy at the design stage and its implications in the search for the architecture of connections and network layers. With these theoretical facts and design elements coming from other works in this area done by the author, three mammogram recognition systems which reflect technological developments are implemented, culminating in a system based on Convolutional Neural Networks (CNN), whose architecture is designed thanks to the previously mentioned theoretical study and practical results of analysis conducted on scales in our image database. All three systems are trained and validated against the DDSM mammographic database, with a total of 100 training samples and 100 test samples chosen to avoid bias and stand for a real screening program. The validity of the CNN approach to the problem is demonstrated and a research way to help in designing the architecture of these networks is proposed.

Sistema de contagem com morfologia matemática fuzzy

Mathematical Morphology presents a systematic approach to extract geometric features of binary images, using morphological operators that transform the original image into another by means of a third image called structuring element and came out in 1960 by researchers Jean Serra and George Matheron. Fuzzy mathematical morphology extends the operators towards grayscale and color images and was initially proposed by Goetherian using fuzzy logic. Using this approach it is possible to make a study of fuzzy connectives, which allows some scope for analysis for the construction of morphological operators and their applicability in image processing. In this paper, we propose the development of morphological operators fuzzy using the R-implications for aid and improve image processing, and then to build a system with these operators to count the spores mycorrhizal fungi and red blood cells. It was used as the hypothetical-deductive methodologies for the part formal and incremental-iterative for the experimental part. These operators were applied in digital and microscopic images. The conjunctions and implications of fuzzy morphology mathematical reasoning will be used in order to choose the best adjunction to be applied depending on the problem being approached, i.e., we will use automorphisms on the implications and observe their influence on segmenting images and then on their processing. In order to validate the developed system, it was applied to counting problems in microscopic images, extending to pathological images. It was noted that for the computation of spores the best operator was the erosion of Gödel. It developed three groups of morphological operators fuzzy, Lukasiewicz, And Godel Goguen that can have a variety applications

Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.

Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.

Relación genética de seis especies de teocintles (Zea spp) mesoamericanos empleando descriptores morfológicos en el CEO, Posoltega, Chinandega, 2009

El presente trabajo se realizó para comparar teocintles seis especies de teocintle de Mesoamérica. Se estableció un experimento en el Centro Experimental de Occidente, Posoltega, Chinandega en el año 2008 , para ello se utilizó el esquema de diseño de Bloque Completo al Azar, se efectuó un análisis de varianza, separación de media Tukey (∞=0.05). Los resultados obtenidos indican que las variables número de ramas laterales en el tallo, longitud de la panoja, número de granos en la mazorca, ancho del grano no mostraron diferencias significativas. En cuanto a carácter de espiguilla todos difieren estadísticamente . Se encontró correlación entre las variables, y los tres primeros componentes principales aislaron el 83% de la variación total. El análisis de conglomerado mediante el método UPGMA y distancia euclidea agrupó las seis especies estudiadas en cuatro grupos las especies Zea perennis(a) y Zea huehuetenangensis se separan de los demás teocintle. Al comparar característica morfológicas las especies de México se diferencian de las especie de Guatemala y Nicaragua, las cuales revelaron característica similares en común.

Efecto de la aplicación in vitrio de colchicina sobre caracteres morfológicos y ciclógicos en plantas de quequisque (Xanthosoma violaceum Schott) Cv. Nueva Guinea

La poliploidía es un mecanismo evolutivo en algunos grupos de animales y vegetales que les confiere ventajas adaptativas al medio donde se desarrollan; mayor vigor, tamaño y características deseables para el hombre. La manipulación de la ploidía es utilizada en el fitomejoramiento para producir cultivares mejorados. La colchicina es ampliamente aplicada en la inducción de poliploides. Indicadores morfológicos y citológicos son utilizados como métodos indirectos para proyectar poliploidías en plantas. El quequisque (Xanthosoma violaceum Schott) mundialmente es atacado por el Mal seco (Pythium myriotylum), que reduce hasta en 100% los rendimientos. No existen cultivares diploides resistentes a la enfermedad. A plantas del cultivar Nueva Guinea se aplicó in vitro 0.0, 6.25, 12.5, 18.75 y 25 mg l-1 de colchicina (tratamientos testigo, 1, 2, 3 y 4 respectivamente) por 40 días. En invernadero se evaluó la altura de planta, número, largo y ancho de hojas. Se cortó 1 cm2 del ápice, parte media y base de las hojas para evaluar con micrómetro la densidad y tamaño de estomas en la hoja y el número de cloroplastos. 23 días después del trasplante (ddt) los tratamientos registraron plantas estadísticamente diferentes en altura, largo y ancho de hojas. A los 53 ddt las plantas no registraron diferencias estadísticas entre los tratamientos en las variables morfológicas pero si en las variables citológicas. Las concentraciones de colchicina 18.75 y 25 mgl-1 indujeron disminuciones en la altura de planta, largo y ancho de hojas. Las concentraciones 6.25 y 12.5 mgl-1 resultaron en menor número de estomas por cm2, mayor tamaño de estomas y concentración de cloroplastos en estos.

Las estrategias competitivas de los operadores de transporte marítimo de contenedores en línea regular

459 p.