Es wurde eine neue Färbemethode zur simultanen Darstellung von Estrogenrezeptoren (ER) und argyrophilen Nukleolus-organisierenden Regionen (AgNORs) entwickelt, um die Proliferationscharakteristika ER-positiver und ER-negativer Tumorzellen unabhängig voneinander zu bestimmen. Um eine mögliche gegenseitige Beeinflussung beider Färbemethoden auszuschließen wurden Serienschnitte 10 invasiv duktaler Mammakarzinome entweder mit einer der einzelnen Methoden oder mit der Simultanfärbemethode ER/AgNORs gefärbt und nachfolgend vergleichend untersucht. Durch Vermessung der histologischen Schnitte mit Hilfe der digitalen Bildanalyse konnten reziproke Effekte ausgeschlossen werden. Es konnte nachgewiesen werden, daß die simultane Färbung beider Marker zu einem reproduzierbaren und spezifischen Färberesultat führt. Es ist somit gerechtfertigt, AgNORs in immunhistochemisch gefärbten Zellen zu messen. Histologische Schnitte von 49 invasiven Mammakarzinomen wurden simultan für ER und AgNORs gefärbt. In jeweils 100 ER-positiven und ER-negativen Tumorzellkernen wurden die AgNORs mit Hilfe des Bildverarbeitungssystems AMBA vermessen. Zur Quantifizierung der AgNORs in immunhistochemisch gefärbten Zellkernen wurde das Programm AMBA\ orcolor angewendet. Die AgNOR-Konfiguration wird beschrieben durch Anzahl, Fläche und räumliche Verteilung innerhalb des Zellkerns. Zwischen ER-positiven und ER-negativen Zellen bestehen hochsignifikante Unterschiede. ER-negative Zellen des Mammakarzinoms besitzen eine größere Anzahl AgNORs (3,06 *0,67) verglichen mit den ER-positiven Zellen (1,65 *0,34). Nur die AgNOR-Parameter der ER-negativen Zellfraktion korrelierten mit anderen Malignitätsmarkern (Bloom-Richardson-Grading; Wachstumsfraktion (Ki-67)). Die ER-negativen Zellen lassen sich als Zellfraktion mit höherer Proliferationsaktivität charakterisieren. Die Ergebnisse zeigen, daß die ER-negativen Zellen des Mammakarzinoms einen entscheidenden Beitrag zur Tumorproliferation leisten und sehr wahrscheinlich die Progression der Tumorerkrankung bestimmen. / A new staining method for simultaneous demonstration of Estrogen receptors (ER) and argyrophilc Nucleolus-Organizer Regions (AgNORs) was developed to measure the proliferation characteristics of ER-positive and ER-negative tumour cell independently. To rule out possible reciprocal effects of the two staining procedures serial slides of 10 invasive ductale breast cancers were stained with either the single staining methods or the simultaneous ER/AgNOR-staining method and investigated comparatively. Measuring the slides by means of image analysis reciprocal effects could be excluded. It could be proved that a simultaneous staining of both markers leads to a reproducible and specific staining result. It is concluded that it is justified to measure AgNORs in immunohistochemically stained cells. Specimens of 49 invasive breast cancers were stained simultaneously for Estrogen receptors (ER) and argyrophilc Nucleolus-Organizer Regions (AgNORs). AgNORs in 100 ER-positive and 100 ER-negative tumour cell nuclei were measured by means of the image analysis system AMBA. For the quantification of AgNORs within immunohistochemically stained nuclei the measuring program AMBA\ orcolor was used. AgNOR number, area and distribution within the nucleus describe the AgNOR-configuration. Highly significant differences between ER-positive and ER-negative tumour cells were found. ER-negative breast cancer cells have a larger amount of AgNORs within their nuclei (3,06 *0,67) compared to ER-positive cells (1,65 *0,34). A special clustering phenomenon in ER-positive cells was found. Only the AgNOR-parameters of the ER-negative cell fraction were found to be associated with other indicators of malignancy (Bloom-Richardson-Grading; Growth-Fraction (Ki-67)). The ER-negative cells of breast cancer are characterised as the cell fraction with a higher proliferation activity. The results indicate that the ER-negative cells of breast cancer mainly contribute to the tumour proliferation characteristics and most likely to the progression of the tumour disease.

Le projet ARCADIA vise à développer une méthode automatique d’analyse des décors sur des tessons de céramique réalisés à la molette pour faciliter l’interprétation de ce patrimoine archéologique. Cette automatisation doit remplacer la procédure manuelle effectuée par l’archéologue, devenue trop fastidieuse avec l’augmentation du corpus (38000 tessons). L’objectif in fine est de réussir à associer automatiquement les décors à la molette du potier qui les a créés. Dans ce contexte, nous avons développé une chaine complète depuis la numérisation des tessons jusqu’à la classification automatique des décors selon leur style de motifs(carré, losange, chevrons, oves, etc). Les travaux présentés proposent plusieurs contributions mettant en oeuvre des méthodes d’analyse d’images et d’apprentissage automatique. A partir du nuage de points 3D, une carte des profondeurs est obtenue. Une méthode originale de détection automatique de la région saillante focalisée sur le décor est proposée. Ensuite les décors sont caractérisés pour effectuer leur classification. Un nouveau descripteur, appelé Blob-SIFT, est proposé pour collecter les signatures seulement dans les zones pertinentes du décor. Cette approche adaptée à chaque décor, permet à la fois de réduire considérablement la masse de données et d’améliorer les performances de classification. Nous proposons également une approche apprentissage profond, puis, une approche hybride combinant les vecteurs de caractéristiques locales extraites par Blob-SIFT et la caractérisation globale du décor fournie par l’apprentissage profond qui améliore encore les performances de classification. / The ARCADIA project aims to develop an automatic method for analyzing engraved decorations on ceramic sherds to facilitate the interpretation of this archaeological heritage. It is to replace the manual and tedious procedure carried out by the archaeologist since the corpus increased to more 38000 sherds. The ultimate goal is to grouping all the decorations created with the same wheel by a poter. We developped a complete chain from the 3Dscanning of the sherd to the automatic classification of the decorations according to their style (diamonds, square, chevrons, oves, etc). In this context, several contributions are proposed implementing methods of image analysis and machine learning. From the 3Dpoint cloud, a depth map is extracted and an original method is applied to automatically detect the salient region centered onto the decoration. Then, a new descriptor, called Blob-SIFT, is proposed to collect signatures only in the relevant areas and characterize the decoration to perform the classification. This approach adapted to each sherd, allows both to reduce significantly the mass of data and improve classification rates. We also use deep learning, and propose an hybrid approach combining local features extracted by Blob-SIFT with global features provided by deep learning to increase the classification performance.

L'objectif de cette thèse est d'étudier le comportement de différentes représentations d'images, notamment apprentissage profond, dans le contexte d'application en imagerie médicale. Le but est de développer une méthode unifiée efficace pour les applications visées que sont la super résolution, la segmentation et la synthèse. La super-résolution est un procès d'estimation d'une image haute-résolution à partir d'une ou plusieurs images basses résolutions. Dans cette thèse, nous nous concentrons sur la super résolutionunique, c'est-à-dire que l'image haute résolution (HR) est estimée par une image basse-résolution (LR) correspondante. Augmenter la résolution de l'image grâce à la super-résolution est la clé d'une compréhension plus précise de l'anatomie. L'application de la super résolution permet d'obtenir des cartes de segmentation plus précises. Étant donné que deux bases de données qui contiennent les images différentes (par exemple, les images d'IRM et les images de CT), la synthèse est un procès d'estimation d'une image qui est approximative aux images dans la base de données de cible à partir d'une image de la base de données de source. Parfois, certains contrastes tissulaires ne peuvent pas être acquis pendant la séance d'imagerie en raison du temps et des coûts élevés ou de l'absence d'appareils. Une solution possible est à utiliser des méthodes de synthèse d'images médicales pour générer les images avec le contraste différent qui est manquée dans le domaine à cible à partir de l'image du domaine donnée. L'objectif des images synthétiques est d'améliorer d'autres étapes du traitement automatique des images médicales telles que la segmentation, la super-résolution ou l'enregistrement. Dans cette thèse, nous proposons les réseaux neurones pour la super résolutionet la synthèse d'image médicale. Les résultats démontrent le potentiel de la méthode que nous proposons en ce qui concerne les applications médicales pratiques. / In this thesis, our motivation is dedicated to studying the behaviors of different image representations and developing a method for super-resolution, cross-modal synthesis and segmentation of medical imaging. Super-Resolution aims to enhance the image resolution using single or multiple data acquisitions. In this work, we focus on single image super-resolution (SR) that estimates the high-resolution (HR) image from one corresponding low-resolution (LR) image. Increasing image resolution through SR is a key to more accurate understanding of the anatomy. The applications of super-resolution have been shown that applying super-resolution techniques leads to more accurate segmentation maps. Sometimes, certain tissue contrasts may not be acquired during the imaging session because of time-consuming, expensive costor lacking of devices. One possible solution is to use medical image cross-modal synthesis methods to generate the missing subject-specific scans in the desired target domain from the given source image domain. The objective of synthetic images is to improve other automatic medical image processing steps such as segmentation, super-resolution or registration. In this thesis, convolutional neural networks are applied to super-resolution and cross-modal synthesis in the context of supervised learning. In addition, an attempt to apply generative adversarial networks for unpaired cross-modal synthesis brain MRI is described. Results demonstrate the potential of deep learning methods with respect to practical medical applications.

Obtaining an accurate estimate of a land-cover classifier's performance over a wide geographic area is a challenging problem due to the need to generate the ground truth that covers the entire area that may be thousands of square kilometers in size. The current best approach constructs a testing dataset by drawing samples randomly from the entire area --- with a human supplying the true label for each such sample --- with the hope that the selections thus made statistically capture all of the data diversity in the area. A major shortcoming of this approach is that it is difficult for a human to ensure that the information provided by the next data element chosen by the random sampler is non-redundant with respect to the data already collected. In order to reduce the annotation burden, it makes sense to remove any redundancies from the entire dataset before presenting its samples to a human for annotation. This dissertation presents a framework that uses a combination of clustering and compression to create a concise-set representation of the land-cover data for a large geographic area. Whereas clustering is achieved by applying Locality Sensitive Hashing (LSH) to the data elements, compression is achieved through choosing a single data element to represent a given cluster. This framework reduces the annotation burden on the human and makes it more likely that the human would persevere during the annotation stage. We validate our framework experimentally by comparing it with the traditional random sampling approach using WorldView2 satellite imagery.

As atividades agrícolas no Estado de São Paulo, foram responsáveis pela supressão da cobertura vegetal original do solo e, sua conseqüente degradação. A vegetação nativa foi gradativamente substituída por culturas como café, pastagem, citros e cana-de-açúcar, durante séculos de ocupação e uso da terra. A recomposição da cobertura florestal auxilia na prevenção da erosão do solo e na redução dos impactos causados. A floresta ripária retém os sedimentos resultantes do desprendimento do solo à montante e transportados pela enxurrada. A deposição de sedimentos na zona ripária está relacionada à pluviosidade, às feições geomorfológicas, ao material de origem e manejo da área à montante. O padrão de distribuição de sedimentos na zona ripária reflete a dinâmica da deposição e os prováveis processos ocorridos. Para inferir sobre os processos de deposição ocorridos, foram realizadas análises macro e micromorfológicas e, também análises granulométricas apoiadas na interpretação estatística dos parâmetros de Folk & Ward (1957). As amostras de solo foram dispersas em Hexametafosfato de Sódio e também em água, para simular as condições de campo, seguindo a metodologia de Camargo (1986). Os resultados obtidos através da análise granulométrica, foram reforçados pelas análises de imagens e porosidade em amostras indeformadas. Os atributos do solo enterrado e dos sedimentos depositados, evidenciam um padrão de deposição irregular e desuniforme, que sugere a ocorrência de eventos erosivos de grande intensidade (fluxo turbulento). Essa irregularidade e desuniformidade da deposição está relacionada à alteração do uso da terra. A implantação do reflorestamento na zona ripária de Iracema B deslocou a deposição de sedimentos, 25m à montante na encosta. / Agricultural pratices in the state of São Paulo - Brazil, are directly responsible for the suppression of the natural vegetation cover and soil degradation. The natural vegetation was substituted by coffee, pastures, citrus and sugar-cane crops, over centuries of occupation and land use. The native forest recuperation prevents soil erosion and reduces environmental impacts. Riparian forest traps sediments transported by \"splash\" and runoff. Sediments deposition in riparian zone depends on rainfall, geomorphology, original soil characteristics and management. Sediment distribution paths in riparian zones reflect the deposition dynamics and the type of deposition event. In order to study the deposition processes in a riparian forest located in the county of Iracemapolis-state of São Paulo, macro and micromorphological analyses, as well as particle size distribution using Folk & Ward (1957) parameters, were done. Soil samples were dispersed with sodium hexametaphosphate and water. This last technique was done to simulate field transport conditions. The particle size distribution results together with the field and laboratory morphological analyses showed an irregular and non-uniform sediment deposition. This deposition process suggests the occurrence of high intensity erosive events that produce high amount of sediments and runoff characterized by a turbulent flow. Land use changes significantly affect this type of deposition. The recuperation of the natural forest dislocated sediment deposition inside the riparian forest 25 m upslope.

The purpose of this study was to investigate the image selection in the swedish newspaper Aftonbladet during three days. We wanted to know what kind of images Aftonbladet choosed to publish in the printed newspaper and in the corresponding articles on the web. Through a semiotic image analysis we were able to analyze what images Aftonbladet choosed to publish and what the images signaled. We were also looking for differences and similarities in the image selection so we compared what kind of different images the newspaper where using on the web and in the printed newspaper. We analyzed three  pages from two newspapers in June, and the associated web articles, which gave us a total of 50 photos to analyze. Through the analysis we found that most of the images could speak to the observer's pathos, that is, emotions. The result also showed that Aftonbladet used more sensational journalism on images of people in the printed newspaper compared to the web. The similarities we found mainly concerned that there were many of the images that were the same on the web and the printed newspaper. The differences we found mainly concerned that there were many more images on the web than in the printed newspaper and the pictures were also much bigger at the website. We hope that our study will provide an in-depth understanding of the importance of the image in the news context and contribute to the journalistic research field.

A diversidade de espécies presentes no riquíssimo reino vegetal torna o processo de identificação de órgãos foliares uma tarefa muito complexa. A biodiversidade das espécies, associada aos modelos tradicionais de taxonomia, transforma essa tarefa em um verdadeiro desafio para os pesquisadores. Neste trabalho é apresentada uma nova abordagem para identificação de espécies vegetais baseada em características internas dos órgãos foliares. A coleta de informações é realizada através de técnicas de visão computacional e análise de imagens, através das quais são extraídas características relativas à complexidade (dimensão fractal) e biometria dos órgãos foliares. A eficiência da metodologia desenvolvida foi avaliada em casos reais de identificação de espécies, em que foram utilizados dois conjuntos de imagens: espécies da Mata Atlântica e do Cerrado brasileiro, e espécies de maracujás silvestres do gênero Passiflora. Para classificação das espécies foram utilizadas as técnicas de reconhecimento padrões de análise de agrupamentos e redes neurais artificiais. / The plant species diversity makes their correct identification a very complex task. The traditional taxonomy models, associated with species biodiversity, has been transformed this task in a challenger for the researches. This work presents a new approach to plant species identification, based on internal characteristics of leaf form. The data are collected by computer vision and shape analysis techniques, which extracts features from complexity (fractal dimension) and biometry of plant species. The methodology efficiency was evaluated with real cases of species identification: digital images of Mata Atlântica and brazilian Cerrado species; and passion fruit species of genus Passiflora. The species classifications are performed using pattern recognition techniques as clustering and artificial neural networks.

O crescimento acelerado das cidades e os reflexos desse aumento das populações urbanas é preocupação constante na atualidade. Nesse processo, o surgimento de ocupações precárias, especialmente nas regiões metropolitanas, torna-se uma das características mais explicitas, caracterizando a própria lógica de ocupação, uso e direito desigual ao território. O monitoramento dessas áreas, sua formação e expansão, são uma necessidade crescente, em diversos locais no mundo, visto que a inclusão dessas áreas à cidade formal é tido como gatilho para a melhoria das condições de vida de mais de 100 milhões de pessoas que vivem em favelas no mundo todo, como colocam as Metas de Desenvolvimento do Milênio propostas pela Organização das Nações Unidas. Contudo, para que os habitantes das favelas sejam atendidos em seu direito a uma vida digna, faz-se necessário seu conhecimento e principalmente quantas são e onde estão. Um importante instrumento, com relação benéfica entre tempo de aquisição, custo de aplicação e possibilidade de replicabilidade e transferência de conhecimento é o uso de dados de Sensoriamento Remoto. Estes possibilitam o estabelecimento de metodologias através de procedimentos de detecção de feições e classificação do uso do solo, para identificação dessas áreas. Não obstante, os métodos de classificação clássicos quando aplicados a imagens de altíssima resolução espacial não conseguem extrair de forma satisfatória, em determinados casos, informações para uso intraurbano. Nesse ínterim surgem novos paradigmas de classificação de imagens como a Análise Orientada a Objeto, onde o processo de classificação parte do objeto geográfico definido a partir da segmentação da imagem, aproximando o objeto de feições do mundo real. Sobre estes objetos é possível a aplicação de regras de pertinência e de contexto através de linguagens e softwares específicos que permitem a transposição do conhecimento humano de fotointerpretação relação contextual para o meio computacional. Este trabalho objetivou avaliar o uso desta técnica de classificação para a detecção e mapeamento de favelas no município de Taboão da Serra/SP, utilizando dados auxiliares para a caracterização destas áreas e seus graus e tipos de precariedade. Os resultados demonstram a validade da aplicação da técnica. / The accelerated growth of the cities and the reflections of the increase of the urban population has been a constant concern nowadays. In this process, the occurrence of precarious occupancies, mainly in the metropolitan regions, has become one of the most explicit characteristics, describing the logic of occupancy itself, unequal use and right to the territory. The monitoring of these areas, their lineup and expansion, are an increasing need in several places in the world, as the inclusion of these areas in the formal city is considered a trigger for the living conditions improvement of over 100 million people who live in slums all over the world, as the Developments Goals of the Millennium proposed by the United Nations Organization. However, in order to meet the rights to a dignified life of the slums inhabitants, it is necessary to know about them mainly their number and where they are. An important tool related to the beneficial relation among the acquisition time, application cost and possibility of applying again, and transference of knowledge is the use of data from Remote Sensing. These data make it possible to establish the methodologies through the detection of features procedures and classification of the land use for these areas identification. Nevertheless the classical methods of classification cannot obtain, in certain cases, information on the interurban use, in a satisfactory way. In the interim, new paradigms of images classification appear like the Object Based Image Analysis (OBIA) which goes from the defined geographic object to the image segmentation, approaching the object to features of the real world. The application of pertinent rules and context over these objects is possible through specific languages and softwares that allow the transference of human knowledge of photo interpretation and contextual relation to the computing environment. This work aimed at evaluating the use of this classification technique for detection and zoning of slums in Taboão da Serra/SP town using supporting data for the areas characterization, its grades and kinds of precarious conditions. The results show the validity of the technique application.

A presente pesquisa teve por objetivo a investigação da influência do tamanho de partículas floculadas na eficiência da clarificação de águas para abastecimento por flotação por ar dissolvido (FAD) com o emprego de método e equipamento para a aquisição e análise de imagens especialmente desenvolvidos, tendo em vista à caracterização da distribuição de tamanho de flocos e microbolhas de ar, bem como, o estudo dos aglomerados bolhas-floco (em termos de número de microbolhas de ar aderidas e velocidade ascensional) presentes no processo de flotação e comparação dos dados experimentais àqueles obtidos em simulação com o emprego do modelo matemático proposto por Reali (1991). Os ensaios foram realizados com água sintética (turbidez de 7,5±0,2 NTU; cor aparente de 38±1 uC; alcalinidade de 29,8±0,6 mg\'CA\'CO IND.3\'/L; condutividade de 59,3±0,8 \'mü\'S/cm; UV254nm de 0,128±0,004 \'CM POT.-1\'), a qual foi coagulada com a aplicação de 1,9 mg/L de \'AL POT. 3+\' (pH de 6,6±0,05) e divididos em duas Fases: Fase 1 - ensaios preliminares realizados em escala de laboratório, com o emprego do flotateste; Fase 2 - ensaios realizados em unidade piloto de flotação. Os resultados alcançados demonstraram que: i) a distribuição de tamanho de partículas floculadas influenciou diretamente a clarificação por flotação da água em estudo, sendo que as melhores condições de floculação foram aquelas que conduziram à formação, em sua maioria, de partículas floculadas com diâmetro médio de Feret acima de 300 \'mü\'m; ii) os menores valores residuais dos parâmetros analisados na água em estudo foram alcançados com o emprego do tempo de floculação de 17 min, entretanto a FAD foi capaz de operar também com boa eficiência com a utilização de tempo de floculação de 10 min; iii) o método e equipamento desenvolvidos nesta pesquisa para a aquisição e análise de imagens demonstraram constituir importantes ferramentas para a obtenção das distribuições de tamanho de flocos e microbolhas de ar, bem como, para a determinação do número de microbolhas de ar aderidas às superfícies dos flocos e da velocidade ascensional dos aglomerados bolhas-floco gerados no processo de flotação; iv) mesmo com as diversas simplificações adotadas no desenvolvimento do modelo matemático analisado e considerando as condições experimentais utilizadas nesta pesquisa, foi possível verificar para a água em estudo e para as condições operacionais empregadas nesta pesquisa, que a modelação matemática proposta por Reali (1991) foi capaz de fornecer subsídios para uma adequada estimativa do número de microbolhas de ar aderidas aos flocos, bem como, das velocidades ascensionais dos aglomerados bolhas-floco. / The goal of this research was to investigate the flocculated particles size distribution influence on the dissolved air flotation (DAF) efficiency. Special image acquisition method and equipment were used to characterize the flocculated particles and air microbubbles size distribution, as well as, the clusters (in terms of microbubbles number adhered and rise velocity) in the contact zone outlet of the DAF unit. Besides that, the experimental results were compared with those obtained from the DAF modeling proposed by Reali (1991). The trials were carried out with synthetic water (temperature of 26.0 ± 0.5oC; turbidity of 7.5±0.2 NTU; apparent color of 38±1 CU; alkalinity of 29.8±0.6 mg\'CA\'\'CO IND.3\'/L; conductivity of 59.3±0.8 \'mü\'S/cm; UV254nm of 0.128±0.004 \'CM POT.-1\'), that it was coagulated by applying 1.9 mg/L of \'AL POT.3+\' (22.5 mg/L alum). The trials were divided into two phases: Phase 1 - preliminary tests carried out in laboratory facilities (flotatest); Phase 2 - tests carried out in pilot facilities (DAF pilot unit). The results showed that: i) the flocculation conditions interfered directly on the efficiency of DAF process, and the best flocculation conditions were those that conducted to formation of flocculated particles size with Feret mean diameter above 300 \'mü\'m; ii) the best results were obtained applying flocculation time of 17 min, however, DAF was also capable of operating with a satisfactory efficiency when applying flocculation time of 10 min; iii) the special image acquisition method and equipment developed in this research proved to be a important tool to characterize the flocculated particles and air microbubbles size distribution, as well as, the number of air microbubbles adhered to the flocs surface and the clusters rise velocity; iv) the DAF modeling developed by Reali (1991) provided a reliable prediction of the microbubbles number adhered to the flocs surface, as well as, the clusters rise velocity.

As atividades agrícolas no Estado de São Paulo, foram responsáveis pela supressão da cobertura vegetal original do solo e, sua conseqüente degradação. A vegetação nativa foi gradativamente substituída por culturas como café, pastagem, citros e cana-de-açúcar, durante séculos de ocupação e uso da terra. A recomposição da cobertura florestal auxilia na prevenção da erosão do solo e na redução dos impactos causados. A floresta ripária retém os sedimentos resultantes do desprendimento do solo à montante e transportados pela enxurrada. A deposição de sedimentos na zona ripária está relacionada à pluviosidade, às feições geomorfológicas, ao material de origem e manejo da área à montante. O padrão de distribuição de sedimentos na zona ripária reflete a dinâmica da deposição e os prováveis processos ocorridos. Para inferir sobre os processos de deposição ocorridos, foram realizadas análises macro e micromorfológicas e, também análises granulométricas apoiadas na interpretação estatística dos parâmetros de Folk & Ward (1957). As amostras de solo foram dispersas em Hexametafosfato de Sódio e também em água, para simular as condições de campo, seguindo a metodologia de Camargo (1986). Os resultados obtidos através da análise granulométrica, foram reforçados pelas análises de imagens e porosidade em amostras indeformadas. Os atributos do solo enterrado e dos sedimentos depositados, evidenciam um padrão de deposição irregular e desuniforme, que sugere a ocorrência de eventos erosivos de grande intensidade (fluxo turbulento). Essa irregularidade e desuniformidade da deposição está relacionada à alteração do uso da terra. A implantação do reflorestamento na zona ripária de Iracema B deslocou a deposição de sedimentos, 25m à montante na encosta. / Agricultural pratices in the state of São Paulo - Brazil, are directly responsible for the suppression of the natural vegetation cover and soil degradation. The natural vegetation was substituted by coffee, pastures, citrus and sugar-cane crops, over centuries of occupation and land use. The native forest recuperation prevents soil erosion and reduces environmental impacts. Riparian forest traps sediments transported by \"splash\" and runoff. Sediments deposition in riparian zone depends on rainfall, geomorphology, original soil characteristics and management. Sediment distribution paths in riparian zones reflect the deposition dynamics and the type of deposition event. In order to study the deposition processes in a riparian forest located in the county of Iracemapolis-state of São Paulo, macro and micromorphological analyses, as well as particle size distribution using Folk & Ward (1957) parameters, were done. Soil samples were dispersed with sodium hexametaphosphate and water. This last technique was done to simulate field transport conditions. The particle size distribution results together with the field and laboratory morphological analyses showed an irregular and non-uniform sediment deposition. This deposition process suggests the occurrence of high intensity erosive events that produce high amount of sediments and runoff characterized by a turbulent flow. Land use changes significantly affect this type of deposition. The recuperation of the natural forest dislocated sediment deposition inside the riparian forest 25 m upslope.