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.

Imaginários da morte: poética das imagens em cemitérios brasileiros

The thesis presented is committed to a poetic reading that results in the creation of meaning and images of the death from the various cultural practices and symbolic representations exposed in urban cemeteries in some Brazilian cities, aiming to give visibility to new understandings about the imaginary of the in the contemporary scene. Death, therefore, will be seen as a imagining condition of anthroposwhen starts itself from the prerogative of the human consciousness of death (MORIN, 1970), in other words, this awareness that man has he will die and that triggers reflections about their existence allows the emergence of a number of practices such as: mourning, funeral rituals and the creation of several impregnated representations of human emotions emerged from the death facing the man and present, in a more evident form in cemeterial spaces. For this, it focuses on the conflictuous dimension that man establishes with death, because the cultural practices and symbolic representations observed in the research field are the result of this conflict and allow the expansion of the senses about this issue, to the extent that these are coated with a fantastic aura, mystical, secret, spooky, fearful, religious, building a complex imagination. The general plan of this study is to discuss and create, from a phenomenology of imagination and materials / dynamics imagination, as well as along the lines treated by Gaston Bachelard, images of death, from a field experience in cemeteries in Brazil. For this, it is assumed, to observe the cultural practices and symbolic representations in these spaces, a posture able to make the experience into the search field a moment of symbolic exchanges and creation. Thus, it was used observation, conversations with visitors and employees of the cemeteries and the capture of photographic records. The data produced as a fragment of a conversation, a tearful outburst about the loss of a relative, a melancholic epitaph, a flower on the grave or a cry captured by photography were seen as detonators of meanings and a poetic of the imagination.

Imaginários da morte: poética das imagens em cemitérios brasileiros

The thesis presented is committed to a poetic reading that results in the creation of meaning and images of the death from the various cultural practices and symbolic representations exposed in urban cemeteries in some Brazilian cities, aiming to give visibility to new understandings about the imaginary of the in the contemporary scene. Death, therefore, will be seen as a imagining condition of anthroposwhen starts itself from the prerogative of the human consciousness of death (MORIN, 1970), in other words, this awareness that man has he will die and that triggers reflections about their existence allows the emergence of a number of practices such as: mourning, funeral rituals and the creation of several impregnated representations of human emotions emerged from the death facing the man and present, in a more evident form in cemeterial spaces. For this, it focuses on the conflictuous dimension that man establishes with death, because the cultural practices and symbolic representations observed in the research field are the result of this conflict and allow the expansion of the senses about this issue, to the extent that these are coated with a fantastic aura, mystical, secret, spooky, fearful, religious, building a complex imagination. The general plan of this study is to discuss and create, from a phenomenology of imagination and materials / dynamics imagination, as well as along the lines treated by Gaston Bachelard, images of death, from a field experience in cemeteries in Brazil. For this, it is assumed, to observe the cultural practices and symbolic representations in these spaces, a posture able to make the experience into the search field a moment of symbolic exchanges and creation. Thus, it was used observation, conversations with visitors and employees of the cemeteries and the capture of photographic records. The data produced as a fragment of a conversation, a tearful outburst about the loss of a relative, a melancholic epitaph, a flower on the grave or a cry captured by photography were seen as detonators of meanings and a poetic of the imagination.

O político nas imagens de A missão de Heiner Müller e O homem que era uma fábrica de Augusto Boal

Augusto Boal (Brasil) y Heiner Müller (Alemania) son dramaturgos del siglo XX que vivieron en países y contextos evidentemente distintos. Sin embargo, con la crisis del teatro burgués y de las condiciones de legitimidad del régimen de producción de este teatro, ambos presentan puntos de contacto en sus líneas y vectores teatrales que, frente a la universalidad cuestionable de la dramatización, llevan a la concepción de un teatro múltiple y perturbador del orden de lo sensible. Los procesos de escenificación contemporánea exige un adelantamiento del sentido político, desviando del juego de representaciones sociales, para dar lugar al trabajo deconstructor de imágenes como cisión entre la palabra y lo representado, entre lo legible y lo visible. Frente al expuesto, las escritas escénicas y, por eso, literarias de estos autores, sitios de singularización – no con ausencia de paradojas – capaces de movilizar manifestaciones e impases cuanto a las imágenes que ordenan o desordenan los textos dramáticos, traen para la contemporaneidad tensiones que llevan al teatro mismo, tanto a interpelarse como, en su fuerza plural, a encontrar pasajes para el nuevo. Llevar a la superficie aspectos políticos en las imágenes de los textos dramáticos, considerándolos en su inscripción literaria: “La misión: recuerdos de una revolución”, de Heiner Müller, y de “El hombre que era una fábrica”, de Augusto Boal, se hace un desafío, una vez que las imágenes pretendidas son aquellas con formas o materialidades todavía no visibles en la escena, podríamos decir, en estado virtual. Como imágenes pensantes, ellas suceden en el plan de inmanencia del lenguaje (Deleuze y Guattari). Siendo lo “político” una perturbación en lo sensible, contrario a la política (Rancière), la dramaturgia se abala en multiplicidades, desplazando y desnaturalizando las funciones de autor/dramaturgo y lector/actor, teatro/literatura. Dramaturgia simultánea, imagen, fragmento y colaje se muestran como procedimientos artísticos y literarios creativos que se encuentran apropiados sea en la teoría del teatro del oprimido (Boal), sea en el teatro pos-dramático (Hans-ThiesLehmann), a pesar de que, al confrontarlas, sobresalían en desentendimientos: la primera coincide con la lógica de la identidad y la segunda, esta se desarticula, movida por la diáfora, contestación, o desacuerdo. Tales relaciones – no apriorísticas – se suceden en cuanto acontecimiento de la lectura o de la literatura como acontecimiento en que lo político en las imágenes se da, antes, en las lagunas y obscuridades, aludiendo a lo que está más allá de lo sentido, de la escena del gesto y de la palabra. El lector no se para para atribuir sentido, se interroga frente a las metamorfosis y formas oblicuas de acontecimientos insospechables que componen lo político estableciendo la gestión colectiva de la enunciación. En este caso, el texto de Boal y el texto de Müller se inscriben en la producción de una literatura menor, o de un teatro menor, o que los califica como agentes de devenires revolucionarios, agitando, a través de la política en las imágenes, e irrumpiendo contra el problema del poder en las artes.

Reconstrução e reconhecimento de imagens binárias utilizando o algoritmo Máquina de Boltzmann

The objective of this work is to use algorithms known as Boltzmann Machine to rebuild and classify patterns as images. This algorithm has a similar structure to that of an Artificial Neural Network but network nodes have stochastic and probabilistic decisions. This work presents the theoretical framework of the main Artificial Neural Networks, General Boltzmann Machine algorithm and a variation of this algorithm known as Restricted Boltzmann Machine. Computer simulations are performed comparing algorithms Artificial Neural Network Backpropagation with these algorithms Boltzmann General Machine and Machine Restricted Boltzmann. Through computer simulations are analyzed executions times of the different described algorithms and bit hit percentage of trained patterns that are later reconstructed. Finally, they used binary images with and without noise in training Restricted Boltzmann Machine algorithm, these images are reconstructed and classified according to the bit hit percentage in the reconstruction of the images. The Boltzmann machine algorithms were able to classify patterns trained and showed excellent results in the reconstruction of the standards code faster runtime and thus can be used in applications such as image recognition.

Classificação de nódulos pulmonares em imagens tomográficas utilizando redes neurais artificiais em cascata

Lung cancer is the most common of malignant tumors, with 1.59 million new cases worldwide in 2012. Early detection is the main factor to determine the survival of patients affected by this disease. Furthermore, the correct classification is important to define the most appropriate therapeutic approach as well as suggest the prognosis and the clinical disease evolution. Among the exams used to detect lung cancer, computed tomography have been the most indicated. However, CT images are naturally complex and even experts medical are subject to fault detection or classification. In order to assist the detection of malignant tumors, computer-aided diagnosis systems have been developed to aid reduce the amount of false positives biopsies. In this work it was developed an automatic classification system of pulmonary nodules on CT images by using Artificial Neural Networks. Morphological, texture and intensity attributes were extracted from lung nodules cut tomographic images using elliptical regions of interest that they were subsequently segmented by Otsu method. These features were selected through statistical tests that compare populations (T test of Student and U test of Mann-Whitney); from which it originated a ranking. The features after selected, were inserted in Artificial Neural Networks (backpropagation) to compose two types of classification; one to classify nodules in malignant and benign (network 1); and another to classify two types of malignancies (network 2); featuring a cascade classifier. The best networks were associated and its performance was measured by the area under the ROC curve, where the network 1 and network 2 achieved performance equal to 0.901 and 0.892 respectively.

Uma abordagem baseada em filtragem colaborativa integrada a mapas de saliência para a recomendação de imagens

Nowadays, the amount of customers using sites for shopping is greatly increasing, mainly due to the easiness and rapidity of this way of consumption. The sites, differently from physical stores, can make anything available to customers. In this context, Recommender Systems (RS) have become indispensable to help consumers to find products that may possibly pleasant or be useful to them. These systems often use techniques of Collaborating Filtering (CF), whose main underlying idea is that products are recommended to a given user based on purchase information and evaluations of past, by a group of users similar to the user who is requesting recommendation. One of the main challenges faced by such a technique is the need of the user to provide some information about her preferences on products in order to get further recommendations from the system. When there are items that do not have ratings or that possess quite few ratings available, the recommender system performs poorly. This problem is known as new item cold-start. In this paper, we propose to investigate in what extent information on visual attention can help to produce more accurate recommendation models. We present a new CF strategy, called IKB-MS, that uses visual attention to characterize images and alleviate the new item cold-start problem. In order to validate this strategy, we created a clothing image database and we use three algorithms well known for the extraction of visual attention these images. An extensive set of experiments shows that our approach is efficient and outperforms state-of-the-art CF RS.

História, literatura e cinema: um debate sobre a historicidade das imagens dos piratas e da pirataria

We seek, through this work, to understand the construction of the pirates’ images from the Golden Age of Piracy (late seventeenth through early eighteenth century) through the observation of the circulation of these images, which are not limited to one field of knowledge. We take into account the importance of the book “A General History of the robberies and murders of the most notorious pirates...” written by Charles Johnson for these constructions, not only literary, but also historiographical provided that the stories of pirates and piracy gained ground in historiography from the twentieth century on. We also seek to show that this historiographical space arises opposed to an apparent historiographical silence about these stories that lasts for about two centuries, related to a new way of writing history in the aesthetic regime, where it arises as a science through a poetics of knowledge, of which the philosopher Jacques Rancière helps us reflect. Lastly, reflecting upon how these images of pirates circulate nowadays, we seek to understand the historicity of the pirates’ images within that aesthetic regime based on some scenes of the film series Pirates of the Caribbean by Disney™.

CUDA-MMP - Codificação de imagens com sistemas com múltiplos núcleos

Hoje em dia, a área de codificação de dados é transversal a diversos tipos de engenharias devido à sua grande importância. Com o aumento exponencial na criação de dados digitais, o campo da compressão de dados ganhou uma grande visibilidade nesta área. São constantemente desenvolvidos e melhorados algoritmos de compressão por forma a obter a maior compressão de dados possível seja com ou sem perda de dados, permitindo sustentar o rápido e constante crescimento dos mesmos. Um dos grandes problemas deste tipo de algoritmos deve-se ao grande poder computacional que por vezes é necessário para obter uma boa taxa de compressão mantendo a qualidade dos dados quando descompactados. Este documento descreve uma estratégia para tentar reduzir o impacto do poder computacional necessário à codificação de imagens utilizando uma implementação heterogénea. O objetivo é tentar efetuar a paralelização das secções que requerem elevado poder computacional reduzindo assim o tempo necessário à compressão de dados. Este documento baseia-se na implementação desta estratégia para o algoritmo de codificação de imagens MMP-Intra. Utilizando inicialmente uma análise teórica, demonstramos que é viável efetuar a paralelização do algoritmo, sendo possível obter elevados ganhos de desempenho. Por forma a provar que o algoritmo MMP-Intra era paralelizavel e identificar os ganhos reais foi desenvolvido um protótipo inicial, o qual obteve um desempenho muito inferiore ao do algoritmo original, necessitando de muito mais tempo para obter os mesmo resultados. Utilizando um processo de otimização iterativo o protótipo passou por várias etapas de refinação. O protótipo refinado final obteve resultados muito superiores ao algoritmo sequencial no qual o mesmo foi baseado chegando a obter desempenhos quatro vezes superior ao original.

Imagens do terceiro setor: um estudo com pais e responsáveis financeiros das organizações educacionais

The present report is the result of an applied research in the educational entities of the third sector, aiming to demonstrate whether the financial influences the perception of users on the image of those entities. For both used the prospect of integrative marketing relationship adapting to and developing a set of indicators which bore the measurement of images from the model of Machado et al (2005) and Kotler and Fox (1994). The sample included a total of 187 parents and financial responsibility in 03 (three) institutions of education in Natal / RN. These data were processed by multivariate statistical analysis, factor analysis, linear regression, analysis of cluster and discriminant analysis. The factor analysis also identified 6 images perceived by users of services. Next were the relationships of cause and effect between the financial and images formed. In discriminant analysis, was identified two distinct groups of parents and guardians with financial perceptions similar and well defined. The result of the work shows that the differential level of financial participation of parents and guardians not influence the formation of the images formed from educational institutions of the third sector

Modelo de estimativa de valores nutricionais, calóricos e glicêmicos por meio de reconhecimento de alimentos em imagens digitais

Atualmente, a disponibilização de informações alimentares e nutricionais em estabelecimentos da área de alimentação não é obrigatória. Porém, os consumidores podem, fácil e rapidamente, obter informações precisas em sites confiáveis ou por meio de aplicativos sobre a composição nutricional e calórica de alimentos. Estudos recentes mostram a importância não só do controle da ingestão diária de calorias, mas também do consumo de carboidratos, que são os nutrientes mais responsáveis por elevar o nível de glicose no sangue. O objetivo deste trabalho é propor um modelo para reconhecimento de alimentos em imagens de refeições por meio de técnicas de Processamento Digital de Imagens, possibilitando assim, a estimativa dos valores nutricionais, calóricos e glicêmicos dos alimentos identificados. Serão analisadas imagens de refeições e mediante reconhecimento, serão estimados os valores calóricos, nutricionais e glicêmicos de cada alimento identificado e da refeição. O procedimento de construção do artefato será conduzido pelo método Design Science Research. O resultado esperado com a finalização do trabalho é o modelo de reconhecimento de alimentos em imagens de refeições e de disponibilização de informações nutricionais, calóricas e glicêmicas validado. 

Imagens do oriente em contos e lendas de Macau

A chegada a Macau dos navegadores portugueses, em meados do séc. XVI, lançou as bases de quase cinco séculos de contacto ininterrupto entre o Ocidente e o Oriente. Macau é, muitas vezes, caracterizado como um ponto de encontro, de coexistência harmoniosa e de intercâmbio multicultural (principalmente entre a cultura oriental e portuguesa). Existe variada literatura que tem Macau como objeto de reflexão, nomeadamente no subsistema infantojuvenil. Este trabalho pretende, por meio de uma análise sistemática de uma coletânea de contos infantojuvenis de temática oriental, da autoria de Alice Vieira e com ilustrações de Alain Corbel, caracterizar as representações do Oriente que surgem no contexto da literatura portuguesa contemporânea para a infância, refletindo sobre as imagens mais recorrentes e as simbologias mais significativas.

Imagens das línguas de alunos do 6º ano : um estudo em Aveiro

O presente estudo é o resultado de um projeto investigativo que, embora se relacione com a Sensibilização à Diversidade Linguística, tem como tema principal as Imagens das Línguas. Este estudo, cujo título é “Imagens das línguas de alunos do 6.º ano: um estudo em Aveiro”, tem como objetivos perceber quais as imagens das línguas dos alunos do 6.º ano, verificar qual a língua em que estes alunos se matriculam no ano seguinte e se essa escolha foi baseada em imagens estereotipadas das línguas (e em quais) e averiguar se a imagem que os alunos do 6.º ano têm sobre línguas influencia a sua escolha para aprendizagem posterior. Os dados foram recolhidos através de instrumentos distintos (o desenho e o inquérito por questionário). Primeiramente, os discentes elaboraram quatro desenhos seguindo as instruções “desenha-te a falar a tua língua materna”, “desenha-te a falar uma língua que já aprendeste”, “desenha-te a falar uma língua que gostavas de aprender” e “desenha-te a falar uma língua que não gostavas de aprender”. Seguindo-se o preenchimento do inquérito por questionário, composto por cinco questões, relacionadas com as quatro línguas em estudo (português, francês, espanhol e inglês) e que faziam parte da recolha de dados através do desenho. Relativamente ao tratamento de dados optamos pela utilização de categorias de análise (línguas como objetos afetivos, objetos de ensino-aprendizagem, instrumentos de construção e afirmação de identidades individuais e coletivas, objetos de poder e como instrumentos de construção de relações interpessoais e intergrupais), que permitiram perceber quais as imagens das línguas dos alunos inquiridos. Os resultados permitiram-nos perceber que as imagens que os alunos do 6.º ano têm das línguas portuguesa, francesa, espanhola e inglesa são, de alguma forma, estereotipadas. A maioria dos alunos tem uma imagem das línguas como instrumentos de construção e afirmação de identidades individuais e coletivas, isto é, imagens associadas à relação língua/história de um povo/cultura. Contudo, concluímos que esta imagem cultural das línguas também está associada a uma imagem afetiva, salientando a relação aluno/língua/cultura. Partindo das nossas conclusões, poder-se-ão, no futuro desenvolver sessões de Sensibilização à Diversidade Linguística, com o objetivo de (re)construir as Imagens das Línguas que os alunos têm.

Sobre projetos, palavras e imagens: relacionando textos e desenhos nos trabalhos finais de graduação em arquitetura e urbanismo

This research continues the current debate about the role of the images and the words in the architectural design persuasion, where we emphasize the increasing valuation of written documents (FORTY, 2004; MARKUS; CAMERON, 2002), the seduction for the graphical representation (DURAND, 2003) and the rhetorical effects of the graphical and textual resources (TOSTRUP, 1999). Based on these quarrels, we look for verify in the graduate final projects the relation between the design texts and images. From the PROJEDATA, database of the PROJETAR research group (UFRN), we selected the final projects of two brazilians universities, UFRN and USP, that in a first analysis, they had shown as ideal types of two distinct design presentation models, respectively: texts and drawings in separated documents, or combined in an only support. Based on Markus explanation about the function and the content of the texts, on the Durand perspective with regard to graphical representation uses and on Tostrup point of view concerning the rhetorical potential of texts and drawings, we analyze, in a set of 25 projects, how the students relate the textual and imagetical speeches. For this, we related the focus of each speech, in order to verify the possible coherence between both. We conclude that in the model of USP final project the coherence between the texts and the drawings is clearer than in the model adopted in UFRN