Orientador: Ricardo da Silva Torres, Hélio Pedrini / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-22T03:54:24Z (GMT). No. of bitstreams: 1 Andrade_FelipedosSantosPintode_M.pdf: 3172421 bytes, checksum: cf06d3683b1828f22508de3f77ed1c00 (MD5) Previous issue date: 2012 / Resumo: Recentemente, a fusão de descritores tem sido usada para melhorar o desempenho de sistemas de busca em tarefas de recuperação de imagens e vídeos. Descritores podem ser globais ou locais, dependendo de como analisam o conteúdo visual. A maioria dos trabalhos existentes tem se concentrado na fusão de um tipo de descritor. Este trabalho objetiva analisar o impacto da combinação de descritores locais e globais. Realiza-se um estudo comparativo de diferentes tipos de descritores e todas suas possíveis combinações. Além disso, investigam-se modelos para extração e a comparação das características globais e locais para recuperação de imagens e vídeos e estuda-se a utilização da técnica de programação genética para combinar esses descritores. Experimentos extensivos baseados em um projeto experimental rigoroso mostram que descritores locais e globais complementam-se quando combinados. Além disso, esta combinação produz resultados superiores aos observados para outras combinações e ao uso dos descritores individualmente / Abstract: Recently, fusion of descriptors has become a trend for improving the performance in image and video retrieval tasks. Descriptors can be global or local, depending on how they analyze visual content. Most of existing works have focused on the fusion of a single type of descriptor. Different from all of them, this work aims at analyzing the impact of combining global and local descriptors. Here, we perform a comparative study of different types of descriptors and all of their possible combinations. Furthermore, we investigate different models for extracting and comparing local and global features of images and videos, and evaluate the use of genetic programming as a suitable alternative for combining local and global descriptors. Extensive experiments following a rigorous experimental design show that global and local descriptors complement each other, such that, when combined, they outperform other combinations or single descriptors / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

The purpose of this thesis is to present a modified version of the algorithm used in the open source differencing tool zdelta, entitled "iDelta". This algorithm will manage file data and will be built specifically to difference images in the Photoshop file format.

Document representation is a fundamental concept in information retrieval (IR), and has been relied upon in textual IR systems since the advent of library catalogs. The reliance upon text-based representations of stored information has been perpetuated in conventional systems for the retrieval of moving images as well. Although newer systems have added image-based representations of moving image documents as aids to retrieval, there has been little research examining how humans interpret these different types of representations. Such basic research has the potential to inform IR system designers about how best to aid users of their systems in retrieving moving images. One key requirement for the effective use of document representations in either textual or image form is thedegree to which these representations are congruent with the original documents. A measure of congruence is the degree to which human responses to representations are similar to responses produced by the document being represented. The aim of this study was to develop a model for the representation of moving images based upon human judgements of representativeness. The study measured the degree of congruence between moving image documents and their representations, both text and image based, in a non-retrieval environment with and without task constraints. Multidimensional scaling (MDS) was used to examine the dimensional dispersions of human judgements for the full moving images and their representations.

This paper proposes an end-to-end, scale invariant, visual object recognition system, composed of computational components that mimic the cortex in the brain. The system uses a two stage process. The first stage is a filter that extracts scale invariant features from the visual field. The second stage uses inference based spacio-temporal analysis of these features to identify objects in the visual field. The proposed model combines Numenta's Hierarchical Temporal Memory (HTM), with HMAX developed by MIT's Brain and Cognitive Science Department. While these two biologically inspired paradigms are based on what is known about the visual cortex, HTM and HMAX tackle the overall object recognition problem from different directions. Image pyramid based methods like HMAX make explicit use of scale, but have no sense of time. HTM, on the other hand, only indirectly tackles scale, but makes explicit use of time. By combining HTM and HMAX, both scale and time are addressed. In this paper, I show that HTM and HMAX can be combined to make a com- plete cortex inspired object recognition model that explicitly uses both scale and time to recognize objects in temporal sequences of images. Additionally, through experimentation, I examine several variations of HMAX and its

Indiana University-Purdue University Indianapolis (IUPUI) / In this thesis, we describe a different implementation for in loop filtering method for 3D-HEVC. First we propose the use of adaptive loop filtering (ALF) technique for 3D-HEVC standard in-loop filtering. This filter uses Wiener–based method to minimize the Mean Squared Error between filtered pixel and original pixels. The performance of adaptive loop filter in picture based level is evaluated. Results show up to of 0.2 dB PSNR improvement in Luminance component for the texture and 2.1 dB for the depth. In addition, we obtain up to 0.1 dB improvement in Chrominance component for the texture view after applying this filter in picture based filtering. Moreover, a design of an in-loop filtering with Fast Bilateral Filter for 3D-HEVC standard is proposed. Bilateral filter is a filter that smoothes an image while preserving strong edges and it can remove the artifacts in an image. Performance of the bilateral filter in picture based level for 3D-HEVC is evaluated. Test model HTM- 6.2 is used to demonstrate the results. Results show up to of 20 percent of reduction in processing time of 3D-HEVC with less than affecting PSNR of the encoded 3D video using Fast Bilateral Filter.

This dissertation develops several new algorithms to solve existing problems in practical application of the previously developed PCA+JPEG2000, which has shown superior rate-distortion performance in hyperspectral image compression. In addition, a new scheme is proposed to facilitate multi-temporal hyperspectral image compression. Specifically, the uniqueness in each algorithm is described as follows. 1. An empirical piecewise linear equation is proposed to estimate the optimal number of major principal components (PCs) used in SubPCA+JPEG2000 for AVIRIS data. Sensor-specific equations are presented with excellent fitting performance for AVIRIS, HYDICE, and HyMap data. As a conclusion, a general guideline is provided for finding sensor-specific piecewise linear equations. 2. An anomaly-removal-based hyperspectral image compression algorithm is proposed. It preserves anomalous pixels in a lossless manner, and yields the same or even improved rate-distortion performance. It is particularly useful to SubPCA+JPEG2000 when compressing data with anomalies that may reside in minor PCs. 3. A segmented PCA-based PCA+JPEG2000 compression algorithm is developed, which spectrally partitions an image based on its spectral correlation coefficients. This compression scheme greatly improves the rate-distortion performance of PCA+JPEG2000 when the spatial size of the data is relatively smaller than its spectral size, especially at low bitrates. A sensor-specific partition method is also developed for fast processing with suboptimal performance. 4. A joint multi-temporal image compression scheme is proposed. The algorithm preserves change information in a lossless fashion during the compression. It can yield perfect change detection with slightly degraded rate-distortion performance.

Indiana University-Purdue University Indianapolis (IUPUI) / A novel algorithm was developed to convert raw 2-dimensional endoscope videos into 3-dimensional view. Minimally invasive surgeries aided with 3D view of the invivo site have shown to reduce errors and improve training time compared to those with 2D view. The novelty of this algorithm is that two cues in the images have been used to develop the 3D. Illumination is the rst cue used to nd the darkest regions in the endoscopy images in order to locate the vanishing point(s). The second cue is the presence of ridge-like structures in the in-vivo images of the endoscopy image sequence. Edge detection is used to map these ridge-like structures into concentric ellipses with their common center at the darkest spot. Then, these two observations are used to infer the depth of the endoscopy videos; which then serves to convert them from 2D to 3D. The processing time is between 21 seconds to 20 minutes for each frame, on a 2.27GHz CPU. The time depends on the number of edge pixels present in the edge-detection image. The accuracy of ellipse detection was measured to be 98.98% to 99.99%. The algorithm was tested on 3 truth images with known ellipse parameters and also on real bronchoscopy image sequences from two surgical procedures. Out of 1020 frames tested in total, 688 frames had single vanishing point while 332 frames had two vanishing points. Our algorithm detected the single vanishing point in 653 of the 688 frames and two vanishing points in 322 of the 332 frames.

[Truncated abstract] Rocks, as the host to natural chains of coupled thermal, hydraulic and mechanical processes, are heterogeneous at a variety of length scales, and in their mechanical properties, as well as in the hydraulic and thermal transport properties. Rock heterogeneity affects the ultimate hydro-carbon recovery or geothermal energy production. This heterogeneity has been considered one important and difficult problem that needs to be taken into account for its effect on the coupled processes. The aim of this thesis is to investigate the effect of rock heterogeneity on multi-physical processes. A fully coupled finite element model, hereinafter referred to as a porosity-based model (PBM) was developed to characterise the thermal-hydraulic-mechanical (THM) coupling processes. The development of the PBM consists of a two-staged workflow. First, based on poromechanics, porosity, one of the inherent rock properties, was derived as a variant function of the thermal, hydraulic and mechanical effects. Then, empirical relations or experimental results, correlating porosity with the mechanical, hydraulic and thermal properties, were incorporated as the coupling effects. In the PBM, the bulk volume of the model is assumed to be changeable. The rate of the volumetric strain was derived as the difference of two parts: the first part is the change in volume per unit of volume and per unit of time (this part was traditionally considered the rate of volumetric strain); and the second is the product of the first part and the volumetric strain. The second part makes the PBM a significant advancement of the models reported in the literature. ... impact of the rock heterogeneity on the hydro-mechanical responses because of the requirement of large memory and long central processing unit (CPU) time for the 3D applications. In the 2D PBM applications, as the thermal boundary condition applied to the rock samples containing some fractures, the pore pressure is generated by the thermal gradient. Some pore pressure islands can be generated as the statistical model and the digital image model are applied to characterise the initial porosity distribution. However, by using the homogeneous model, this phenomenon cannot be produced. In the 3D PBM applications, the existing fractures become the preferential paths for the fluid flowing inside the numerical model. The numerical results show that the PBM is sufficiently reliable to account for the rock mineral distribution in the hydro-mechanical coupling processes. The applications of the statistical method and the digital image processing technique make it possible to visualise the rock heterogeneity effect on the pore pressure distribution and the heat dissipation inside the rock model. Monitoring the fluid flux demonstrates the impact of the rock heterogeneity on the fluid product, which concerns petroleum engineering. The overall fluid flux (OFF) is mostly overestimated when the rock and fluid properties are assumed to be homogeneous. The 3D PBM application is an example. As the rock is heterogeneous, the OFF by the digital core is almost the same as that by the homogeneous model (this is due to that some fractures running through the digital core become the preferential path for the fluid flow), and around 1.5 times of that by the statistical model.

This study is an attempt to simulate aspects of human visual perception by automating the detection of specific types of objects in digital images. The success of the methods attempted here was measured by how well results of experiments corresponded to what a typical human’s assessment of the data might be. The subject of the study was images of live fish taken underwater by digital video or digital still cameras. It is desirable to be able to automate the processing of such data for efficient stock assessment for fisheries management. In this study some well known statistical pattern classification techniques were tested and new syntactical/ structural pattern recognition techniques were developed. For testing of statistical pattern classification, the pixels belonging to fish were separated from the background pixels and the EM algorithm for Gaussian mixture models was used to locate clusters of pixels. The means and the covariance matrices for the components of the model were used to indicate the location, size and shape of the clusters. Because the number of components in the mixture is unknown, the EM algorithm has to be run a number of times with different numbers of components and then the best model chosen using a model selection criterion. The AIC (Akaike Information Criterion) and the MDL (Minimum Description Length) were tested.The MDL was found to estimate the numbers of clusters of pixels more accurately than the AIC, which tended to overestimate cluster numbers. In order to reduce problems caused by initialisation of the EM algorithm (i.e. starting positions of mixtures and number of mixtures), the Dynamic Cluster Finding algorithm (DCF) was developed (based on the Dog-Rabbit strategy). This algorithm can produce an estimate of the locations and numbers of clusters of pixels. The Dog-Rabbit strategy is based on early studies of learning behaviour in neurons. The main difference between Dog-Rabbit and DCF is that DCF is based on a toroidal topology which removes the tendency of cluster locators to migrate to the centre of mass of the data set and miss clusters near the edges of the image. In the second approach to the problem, data was extracted from the image using an edge detector. The edges from a reference object were compared with the edges from a new image to determine if the object occurred in the new image. In order to compare edges, the edge pixels were first assembled into curves using an UpWrite procedure; then the curves were smoothed by fitting parametric cubic polynomials. Finally the curves were converted to arrays of numbers which represented the signed curvature of the curves at regular intervals. Sets of curves from different images can be compared by comparing the arrays of signed curvature values, as well as the relative orientations and locations of the curves. Discrepancy values were calculated to indicate how well curves and sets of curves matched the reference object. The total length of all matched curves was used to indicate what fraction of the reference object was found in the new image. The curve matching procedure gave results which corresponded well with what a human being being might observe.

CAPES; CNPq / In the activated sludge process, problems of foaming and filamentous bulking can occur due to overgrowth of certain filamentous bacteria. Nowadays, these microorganisms are typically monitored by means of light microscopy combined with staining techniques. As drawbacks, these methods are susceptible to human errors, subjectivity and limited by the use of discontinuous microscopy. The present project aims the application of an in situ microscope (ISM) for continuous monitoring of filamentous bacteria, providing real-time examination, automated analysis and elimination of sampling, preparation and transport of samples. The ISM previously developed at the Hochschule Mannheim required adaptations for use within wastewater environment, specially in terms of impermeability and development of a cleaning mechanism. With a new objective lens design, the system was simplified to a single tubus and an externally activated cleaning system based on magnetism was created. A proper image processing algorithm was designed for automated recognition and measurement of filamentous objects, allowing real-time evaluation of images without any staining, phase-contrast or dilution techniques. Three main operations are performed: preprocessing and binarization; recognition of filaments using distance-maps and shape descriptors; measurement and display of total extended filament length. A 3D-printed prototype was used for experiments with respect to the new ISM’s design, providing images with resolution very close to the ones acquired with the previous microscope. The designed cleaning system has shown to be effective, removing dirt settled above the lens during tests. For evaluation of the image processing algorithm, samples from an industrial activated sludge plant were collected weekly for a period of twelve months and imaged without any prior conditioning, replicating real environment conditions. Experiments have shown that the developed algorithm correctly identifies trends of filament growth rate, which is the most important parameter for decision making. For reference images whose filaments were marked by specialists, the algorithm correctly recognized 72% of the filaments pixels, with a false positive rate of at most 14%. An average execution time of 0.7 second per image was achieved, demonstrating the algorithm suitability for real-time monitoring. / Em processos de lodo ativado, problemas de foaming e filamentous bulking podem ocorrer devido ao crescimento exagerado de bactérias filamentosas. Atualmente, o monitoramento de tais micro-organismos é feito por meio de métodos baseados em microscopia ótica combinada com técnicas de marcadores, os quais apresentam limitações intrínsecas da microscopia descontínua, são subjetivos e suscetíveis a erro humano. O presente projeto visa a aplicação de um microscópio in situ (ISM) para monitoramento contínuo de bactérias filamentosas, de forma a possibilitar análise instantânea, computadorizada, sem necessidades de recolher, preparar e transportar amostras. O ISM previamente desenvolvido na Hochschule Mannheim teve que ser adaptado para análise de águas residuais, especialmente em termos de impermeabilidade e a criação de um mecanismo de limpeza. Com a utilização de uma nova objetiva, o novo ISM foi simplificado para um tubo único e um sistema de limpeza ativado externamente baseado em magnetismo foi criado. Um algoritmo de processamento de imagens foi elaborado para reconhecimento e medição de comprimento de estruturas filamentosas, permitindo avaliação em tempo real de imagens sem qualquer técnica de marcadores, contraste de fase ou diluição. O mesmo consiste em três operações principais: pré-processamento e binarização; reconhecimento de filamentos por meio de mapeamento de dis- tâncias e descritores de forma; e, finalmente, medição e visualização do comprimento de cada filamento. Um protótipo construído via impressão 3D foi utilizado para avaliação o novo design do microscópio, fornecendo imagens com resolução bastante próxima das adquiridas com a versão anterior do sistema. O mecanismo de limpeza desenvolvido mostrou-se efetivo, capaz de remover partículas sedimentadas acima das lentes durante os testes. Para avaliação do algoritmo de processamento de imagens, amostras de uma planta industrial de lodo ativado foram coletadas semanalmente por um período de doze meses e imageadas sem qualquer condicionamento prévio, replicando condições reais de ambiente. Experimentos demonstraram que o algoritmo desenvolvido identifica corretamente tendências de aumento/decréscimo da concentração de filamentos, o que constitui o principal parâmetro para tomadas de decisão. Para imagens de referência cujos filamentos foram marcados por especialistas, o algoritmo reconheceu corretamente 80% dos pixels atribuídos a filamentos, com uma taxa de falso positivos de até 24%. Um tempo de execução médio de 0,7 segundo por imagem foi obtido, provando sua aptidão para formar uma ferramenta de monitoramento em tempo real.