No description available.

Submitted by Diogo Barreiros (diogo.barreiros@ufba.br) on 2017-02-06T16:59:36Z No. of bitstreams: 1 dissertacao_mestrado_jose-grimaldo.pdf: 19406681 bytes, checksum: d108855fa0fb0d44ee5d1cb59579a04c (MD5) / Approved for entry into archive by Vanessa Reis (vanessa.jamile@ufba.br) on 2017-02-07T11:51:58Z (GMT) No. of bitstreams: 1 dissertacao_mestrado_jose-grimaldo.pdf: 19406681 bytes, checksum: d108855fa0fb0d44ee5d1cb59579a04c (MD5) / Made available in DSpace on 2017-02-07T11:51:58Z (GMT). No. of bitstreams: 1 dissertacao_mestrado_jose-grimaldo.pdf: 19406681 bytes, checksum: d108855fa0fb0d44ee5d1cb59579a04c (MD5) / Accuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-o between detection performance and fast execution commonly represents the ultimate goal of an object detector in real life applications. Most images are composed of non-trivial amounts of background information, such as sky, ground and water. In this sense, using an object detector against a recurring background pattern can require a signi cant amount of the total processing time. To alleviate this problem, search space reduction methods can help focusing the detection procedure on more distinctive image regions. / Among the several approaches for search space reduction, we explored saliency information to organize regions based on their probability of containing objects. Saliency detectors are capable of pinpointing regions which generate stronger visual stimuli based solely on information extracted from the image. The fact that saliency methods do not require prior training is an important benefit, which allows application of these techniques in a broad range of machine vision domains. We propose a novel method toward the goal of faster object detectors. The proposed method was grounded on a multi-scale spectral residue (MSR) analysis using saliency detection. For better search space reduction, our method enables fine control of search scale, more robustness to variations on saliency intensity along an object length and also a direct way to control the balance between search space reduction and false negatives caused by region selection. Compared to a regular sliding window search over the images, in our experiments, MSR was able to reduce by 75% (in average) the number of windows to be evaluated by an object detector while improving or at least maintaining detector ROC performance. The proposed method was thoroughly evaluated over a subset of LabelMe dataset (person images), improving detection performance in most cases. This evaluation was done comparing object detection performance against different object detectors, with and without MSR. Additionally, we also provide evaluation of how different object classes interact with MSR, which was done using Pascal VOC 2007 dataset. Finally, tests made showed that window selection performance of MSR has a good scalability with regard to image size. From the obtained data, our conclusion is that MSR can provide substantial benefits to existing sliding window detectors

Made available in DSpace on 2014-06-11T19:25:39Z (GMT). No. of bitstreams: 0 Previous issue date: 2009-09-25Bitstream added on 2014-06-13T19:33:05Z : No. of bitstreams: 1 rodrigues_rvr_me_prud.pdf: 1982108 bytes, checksum: 5cd99583a59b533223f322970e160062 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Esta pesquisa, referente à linha de pesquisa Tecnologias de Informação e Comunicação e Educação, consiste na construção de um Objeto de Aprendizagem (OA) fundamentado sob a perspectiva lógico-histórica e, em decorrência de sua utilização em sala de aula, na análise das potencialidades formadoras do conceito números inteiros. Proporcionar o conhecimento da constituição e extensão de um conceito matemático deve ser um desafio à implementação de qualquer recurso de natureza tecnológica no ensino da Matemática, do contrário esta ferramenta corre o risco de reproduzir técnicas esvaziadas de sentido. Para enfrentar esse desafio, o aporte teórico oferecido por Kopnin (1978), Caraça (1984), Lanner de Moura (et al 2003), Sousa (2004) e Dias (2007) mostrou o movimento histórico e intelectual de criação de conceitos como forma de pensamento e perspectiva didática na produção do conhecimento. O percurso desta investigação, concebido como um estudo de caso qualitativo dividiu-se em duas etapas. A partir dos trabalhos de Lizcano (1993/2006), Schubring (2000/2001), Lima & Moisés (1998), Prado & Moura (2007a/2007b) e Prado (2008), na primeira etapa denominada por caráter bibliográfico/laboratorial, os aspectos substanciais e simbólicos, apreendidos do desenvolvimento lógico-histórico do conceito números inteiros, aliados aos efeitos comunicacionais das novas tecnologias (BELLONI, 2000/2001)... / This research is connected to the research line Information and Communication Technologies and Education. The present paper is about the development of a Learning Object (LO) that is based on logical-historical approach and, due to it is applied to the classroom, on forming potentiality of whole numbers concepts. Providing knowledge about a mathematical concept constitution and extension might be a challenge for implementing any technological resource to Mathematics instruction. On the contrary, this toll may reproduce techniques with no meaning. In order to face such challenge, this paper is based on theoretical approaches offered by Kopnin (1978), Caraça (1984), Lanner de Moura (et al 2003), Sousa (2004) e Dias (2007) who point out the historical and intellectual movement of creating concepts as a way to think and a didactic perspective to produce knowledge. This investigation is a qualitative case study that was divided in two steps. The first one was based on Lizcano (1993/2006), Schubring (2000/2001), Lima & Moisés (1998), Prado & Moura (2007a/2007b) e Prado (2008) works. It had a bibliographical/laboratorial character. At this stage, theoretical and methodological processes of the LO “The Universe and its Opposites” production were outlined by substantial and symbolic aspects, apprehend from logical-historical development of whole numbers concept, joined to communicative effects of new technologies (BELLONI, 2000/2001)... (Complete abstract click electronic access below)

abstract: Vision is the ability to see and interpret any visual stimulus. It is one of the most fundamental and complex tasks the brain performs. Its complexity can be understood from the fact that close to 50% of the human brain is dedicated to vision. The brain receives an overwhelming amount of sensory information from the retina – estimated at up to 100 Mbps per optic nerve. Parallel processing of the entire visual field in real time is likely impossible for even the most sophisticated brains due to the high computational complexity of the task [1]. Yet, organisms can efficiently process this information to parse complex scenes in real time. This amazing feat of nature relies on selective attention which allows the brain to filter sensory information to select only a small subset of it for further processing. Today, Computer Vision has become ubiquitous in our society with several in image understanding, medicine, drones, self-driving cars and many more. With the advent of GPUs and the availability of huge datasets like ImageNet, Convolutional Neural Networks (CNNs) have come to play a very important role in solving computer vision tasks, e.g object detection. However, the size of the networks become prohibitive when higher accuracies are needed, which in turn demands more hardware. This hinders the application of CNNs to mobile platforms and stops them from hitting the real-time mark. The computational efficiency of a computer vision task, like object detection, can be enhanced by adopting a selective attention mechanism into the algorithm. In this work, this idea is explored by using Visual Proto Object Saliency algorithm [1] to crop out the areas of an image without relevant objects before a computationally intensive network like the Faster R-CNN [2] processes it. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2017

No description available.

Made available in DSpace on 2014-06-12T15:54:28Z (GMT). No. of bitstreams: 2 arquivo7152_1.pdf: 1057833 bytes, checksum: 67e3dddb2bcfb41fafccbd6d0086f285 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2005 / Neste trabalho discutimos o projeto de compiladores corretos por construção para linguagens orientadas a objeto. Um compilador correto é aquele que garante que a semântica é preservada quando o programa fonte _e traduzido para a linguagem destino. O projeto de compiladores corretos para linguagens imperativas se encontra bem fundamentado; atualmente, o maior desafio é o desenvolvimento de uma abordagem para lidar com características de orientação a objetos. Nesta tese, descrevemos uma abordagem algébrica para construção de compiladores corretos para uma linguagem orientada a objetos chamada ROOL (acrônimo para Refenement Objecy-oriented Language), que é similar a Java e C++. Esta linguagem inclue classes, herança, ligação dinâmica, recursão, cast e teste de tipos, e visibilidade baseada em classes. Na nossa abordagem, lidamos com o problema de corretude do compilador transformando a tarefa de compilação em uma tarefa de refinamento de programa. O processo de compilação passa ser identificado como sendo a redução de um programa fonte, escrito em um subconjunto executável da linguagem, para uma forma normal. A forma normal é gerada por uma série de transformações que preservam a corretude, e s ao provadas corretas a partir das leis básicas da linguagem; portanto o processo é correto por construção. A maior vantagem da nossa abordagem reside na caracterização do processo de compilação dentro de um sistema uniforme onde as comparações e traduções entre semânticas são evitadas. A redução a forma normal é formalizada como uma álgebra onde a noção central é a de refinamento de programas. Portanto, o produto da compilação é um programa na própria linguagem fonte. Nossa forma normal é um programa na forma de um interpretador, escrito na mesma linguagem fonte, emulando o comportamento da máquina destino. A partir desse interpretador, é que a seqüência das instruções geradas são capturadas. Definimos a Máquina Virtual de ROOL (RVM) como sendo nossa máquina destino; ela _e baseada na Máquina Virtual de Java (JVM) Tal uniformidade implica que todo o cálculo necessário para assegurar a corretude do processo de compilação é realizado em um único sistema de uma linguagem orientada a objetos cuja semântica é dada por leis algébricas. Nenhuma teoria relativa a linguagem fonte ou destino é desenvolvida ou usada no processo. O processo de compilação é justificado por teoremas de redução da forma normal. Existem cinco fases: pré-compilação de classes, redirecionamento de chamada de métodos, simplificação, eliminação de controle e refinamento de dados. Para cada fase, um teorema assegura o resultado esperado. O teorema principal conecta os passos intermediários e estabelece o resultado para todo o processo. Uma vez que os teoremas de redu¢c~ ao pra cada fase são provados corretos a partir das leis básicas de ROOL, eles corroboram para a corretude de todo o processo

No description available.

M.Sc. (Information Science) / In this study we have looked at object-oriented programming in the field of manufacturing. Scheduling was the main topic of research in this study. Object-oriented programming was used, because It was found easier to develop a general scheduling system by using objects. The use of mathematical algorithms (for example) would have been much more cumbersome and further developments would not have been as simple. At first, Expert Systems (ES), Artificial Intelligence (AI), Flexible Manufacturing Systems (FMS), Process Planning, Computer Integrated Manufacturing (elM), etc. are discussed. This forms the basis for the different scheduling techniques studied. . To make the study more useful, a system was developed in Turbo Pascal 5.5. The Idea behind the system is to explain different dynamic scheduling techniques, for example due date scheduling, backward scheduling and priority scheduling. The objects used in the system are explained with the help of a pseudo-object-oriented language, "NOT". The conclusions made from this paper can be used for further studies.

Object experts quickly and accurately discriminate objects within their domain of expertise. Although expert recognition has been extensively studied both at the behavioral- and neural-levels in both real-world and laboratory trained experts, we know little about the visual features and perceptual strategies that the expert learns to use in order to make fast and accurate recognition judgments. Thus, the aim of this work was to identify the visual features (e.g., color, form, motion) and perceptual strategies (e.g., fixation pattern) that real-world experts employ to recognize objects from their domain of expertise. Experiments 1 to 3 used psychophysical methods to test the role of color, form (spatial frequencies), and motion, respectively, in expert object recognition. Experiment 1 showed that although both experts and novices relied on color to recognize birds at the family level, analysis of the response time distribution revealed that color facilitated expert performance in the fastest and slowest trials whereas color only helped the novices in the slower trials. Experiment 2 showed that both experts and novices were more accurate when bird images contained the internal information represented by a middle range of SFs, described by a quadratic function. However, the experts, but not the novices, showed a similar quadratic relationship between response times and SF range. Experiment 3 showed that, contrary to our prediction, both groups were equally sensitivity to global bird motion. Experiment 4, which tested the perceptual stategies of expert recognition in a gaze-contingent eye-tracking paradigm, showed that only in the fastest trials did experts use a wider range of vision. Experiment 5, which examined the neural representations of categories within the expert domain, suggested that the mechanisms that represents within-categories of faces also represented within-categories from the domain of expertise, but not the novice domain. Collectively, these studies suggest that expertise influence visual discrimination mechanisms such that they become more sensitive to the visual dimensions upon which the expert domains are discriminated. / Graduate / 2018-12-12

Includes bibliographical references / Active object recognition provides a mechanism for selecting informative viewpoints to complete recognition tasks as quickly and accurately as possible. One can manipulate the position of the camera or the object of interest to obtain more useful information. This approach can improve the computational efficiency of the recognition task by only processing viewpoints selected based on the amount of relevant information they contain. Active object recognition methods are based around how to select the next best viewpoint and the integration of the extracted information. Most active recognition methods do not use local interest points which have been shown to work well in other recognition tasks and are tested on images containing a single object with no occlusions or clutter. In this thesis we investigate using local interest points (SIFT) in probabilistic and non-probabilistic settings for active single and multiple object and viewpoint/pose recognition. Test images used contain objects that are occluded and occur in significant clutter. Visually similar objects are also included in our dataset. Initially we introduce a non-probabilistic 3D active object recognition system which consists of a mechanism for selecting the next best viewpoint and an integration strategy to provide feedback to the system. A novel approach to weighting the uniqueness of features extracted is presented, using a vocabulary tree data structure. This process is then used to determine the next best viewpoint by selecting the one with the highest number of unique features. A Bayesian framework uses the modified statistics from the vocabulary structure to update the system's confidence in the identity of the object. New test images are only captured when the belief hypothesis is below a predefined threshold. This vocabulary tree method is tested against randomly selecting the next viewpoint and a state-of-the-art active object recognition method by Kootstra et al.. Our approach outperforms both methods by correctly recognizing more objects with less computational expense. This vocabulary tree method is extended for use in a probabilistic setting to improve the object recognition accuracy. We introduce Bayesian approaches for object recognition and object and pose recognition. Three likelihood models are introduced which incorporate various parameters and levels of complexity. The occlusion model, which includes geometric information and variables that cater for the background distribution and occlusion, correctly recognizes all objects on our challenging database. This probabilistic approach is further extended for recognizing multiple objects and poses in a test images. We show through experiments that this model can recognize multiple objects which occur in close proximity to distractor objects. Our viewpoint selection strategy is also extended to the multiple object application and performs well when compared to randomly selecting the next viewpoint, the activation model and mutual information. We also study the impact of using active vision for shape recognition. Fourier descriptors are used as input to our shape recognition system with mutual information as the active vision component. We build multinomial and Gaussian distributions using this information, which correctly recognizes a sequence of objects. We demonstrate the effectiveness of active vision in object recognition systems. We show that even in different recognition applications using different low level inputs, incorporating active vision improves the overall accuracy and decreases the computational expense of object recognition systems.