Various biomedical technologies like CT, MRI and PET scanners provide detailed cross-sectional views of the human anatomy. The image information obtained from these scanning devices is typically represented as large data sets whose sizes vary from several hundred megabytes to about one hundred gigabytes. As these data sets cannot be stored on one's local hard drive, SDSC provides a large data repository to store such data sets. These data sets need to be accessed by researchers around the world to collaborate in their research. But the size of these data sets make them difficult to be transmitted over the current network. This thesis presents a 3-D Haar wavelet algorithm which enables these data sets to be transformed into smaller hierarchical representations. These transformed data sets are transmitted over the network and reconstructed to a 3-D volume on the client's side through progressive refinement of the images and 3-D texture mapping techniques.

Submitted by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-04-09T13:57:30Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Reprodução Não Autorizada.pdf: 47716 bytes, checksum: 0353d988c60b584cfc9978721c498a11 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-04-09T13:57:42Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Reprodução Não Autorizada.pdf: 47716 bytes, checksum: 0353d988c60b584cfc9978721c498a11 (MD5) / Made available in DSpace on 2018-04-09T13:57:42Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Reprodução Não Autorizada.pdf: 47716 bytes, checksum: 0353d988c60b584cfc9978721c498a11 (MD5) Previous issue date: 2012-09-24 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This dissertation work presents the development of a new evaluation method for Haar classifiers designed to locate faces in images, in order to help researchers choose the best classifier for their own need, as well as to propose a new metric to evaluate future classifiers designed for face location. Face location, the primary step of the vision-based automated systems, finds the face area in the input image. An accurate location of the face is still a challenging task, but it enables a more efficient segmentation, making the identification and recognition of individuals more accurate. Viola-Jones framework has been widely used by researchers in order to detect the location of faces and objects in a given image. Face detection classifiers, used by Viola-Jones framework, are shared by the scientific and academic community. Nevertheless, few works have studied their accuracy. By applying 10 of these classifiers in two different face databases (FEI and Yale), an analysis was made and a new heuristic was created considering scores given to 22 facial landmarks. The results appear to be more accurate than the ones obtained by the only heuristic proposed by another work, developed so far. / Este trabalho de dissertação apresenta o desenvolvimento de um novo método de avaliação de classificadores Haar para localização de faces em imagens, com a finalidade de auxiliar pesquisadores na escolha do melhor classificador dentre os disponíveis atualmente, assim como oferecer uma nova métrica para avaliar futuros classificadores de localização facial. A localização facial, primeira etapa de sistemas biométricos pela face, limita as regiões das faces na imagem de entrada. A localização precisa da face ainda é uma tarefa desafiadora, e possibilita uma segmentação da área da face mais eficaz, aumentando a acurácia no processo de identificação e reconhecimento de indivíduos. O framework Viola-Jones tem sido amplamente utilizado por pesquisadores para detecção e localização de objetos e faces. Classificadores de detecção facial que utilizam o método Viola-Jones são compartilhados pela comunidade científica e acadêmica. Porém, pouco é discutido sobre a precisão de tais classificadores. Com a aplicação de 10 classificadores em dois bancos de faces distintas entre si (FEI e Yale), uma análise foi realizada e um novo método de avaliação foi proposto. Neste método uma nova métrica foi desenvolvida, levando em consideração scores dados a 22 pontos faciais. Os resultados obtidos mostraram-se mais precisos que a única metodologia de avaliação de classificadores de face Haar presente até o momento.

In this thesis, we establish the underlying research background necessary for tackling the problem of phase-shifting in the wavelet transform domain. Solving this problem is the key to reducing the redundancy and huge storage requirement in Image-Based Rendering (IBR) applications, which utilize wavelets. Image-based methods for rendering of dynamic glossy objects do not truly scale to all possible frequencies and high sampling rates without trading storage, glossiness, or computational time, while varying both lighting and viewpoint. This is due to the fact that current approaches are limited to precomputed radiance transfer (PRT), which is prohibitively expensive in terms of memory requirements when both lighting and viewpoint variation are required together with high sampling rates for high frequency lighting of glossy material. At the root of the above problem is the lack of a closed-form run-time solution to the nontrivial problem of rotating wavelets, which we solve in this thesis. We specifically target Haar wavelets, which provide the most efficient solution to solving the tripleproduct integral, which in turn is fundamental to solving the environment lighting problem. The problem is divided into three main steps, each of which provides several key theoretical contributions. First, we derive closed-form expressions for linear phase-shifting in the Haar domain for one-dimensional signals, which can be generalized to N-dimensional signals due to separability. Second, we derive closed-form expressions for linear phase-shifting for two-dimensional signals that are projected using the non-separable Haar transform. For both cases, we show that the coefficients of the shifted data can be computed solely by using the coefficients of the original data. We also derive closed-form expressions for non-integer shifts, which has not been reported before. As an application example of these results, we apply the new formulae to image shifting, rotation and interpolation, and demonstrate the superiority of the proposed solutions to existing methods. In the third step, we establish a solution for non-linear phase-shifting of two-dimensional non-separable Haar-transformed signals, which is directly applicable to the original problem of image-based rendering. Our solution is the first attempt to provide an analytic solution to the difficult problem of rotating wavelets in the transform domain.

Rapid progress is being made towards the realization of autonomous cars. Since the technology is in its early stages, human intervention is still necessary in order to ensure hazard-free operation of autonomous driving systems. Substantial research efforts are underway to enhance driver and passenger safety in autonomous cars. Toward that end GreedyHaarSpiker, a real-time vision-based lane detection algorithm is proposed for road lane detection in different weather conditions. The algorithm has been implemented in Python 2.7 with OpenCV 3.0 and tested on a Raspberry Pi 3 Model B ARMv8 1GB RAM coupled to a Raspberry Pi camera board v2. To test the algorithm’s performance, the Raspberry Pi and the camera board were mounted inside a Jeep Wrangler. The algorithm performed better in sunny weather with no snow on the road. The algorithm’s performance deteriorated at night time or when the road surface was covered with snow.

This MSc Thesis deals with face detection in image. In this approach, facial features (eyes, nose, mouth corners) are detected first and then joined to the whole face. For the facial features detection, classifiers trained with AdaBoost algorithm are used. Haar wavelets are used as features for classification.

O modelo semiparamétrico de Cox é frequentemente utilizado na modelagem de dados de sobrevivência, pois é um modelo muito flexível e permite avaliar o efeito das covariáveis sobre a taxa de falha. Uma das principais vantagens é a fácil interpretação, de modo que a razão de riscos de dois indivíduos não varia ao longo do tempo. No entanto, em algumas situações a proporcionalidade dos riscos para uma dada covariável pode não ser válida e, este caso, uma abordagem que não dependa de tal suposição é necessária. Nesta tese, propomos um modelo tipo Cox em que o efeito da covariável e a função de risco basal são representadas via bases de Fourier e ondaletas de Haar clássicas e deformadas. Propomos também um procedimento de predição da função de sobrevivência para um paciente específico. Estudos de simulações e aplicações a dados reais sugerem que nosso método pode ser uma ferramenta valiosa em situações práticas em que o efeito da covariável é dependente do tempo. Por meio destes estudos, fazemos comparações entre as duas abordagens propostas, e comparações com outra já conhecida na literatura, onde verificamos resultados satisfatórios. / The semiparametric Cox model is often considered when modeling survival data. It is very flexible, allowing for the evaluation of covariates effects. One of its main advantages is the easy of interpretation, as long as the rate of the hazards for two individuals does not vary over time. However, this proportionality of the hazards may not be true in some practical situations and, in this case, an approach not relying on such assumption is needed. In this thesis we propose a Cox-type model that allows for time-varying covariate effects, for which the baseline hazard is based on Fourier series and wavelets on a time-frequency representation. We derive a prediction method for the survival of future patients with any specific set of covariates. Simulations and an application to a real data set suggest that our method may be a valuable tool to model data in practical situations where covariate effects vary over time. Through these studies, we make comparisons between the two approaches proposed here and comparisons with other already known in the literature, where we verify satisfactory results.

O modelo semiparamétrico de Cox é frequentemente utilizado na modelagem de dados de sobrevivência, pois é um modelo muito flexível e permite avaliar o efeito das covariáveis sobre a taxa de falha. Uma das principais vantagens é a fácil interpretação, de modo que a razão de riscos de dois indivíduos não varia ao longo do tempo. No entanto, em algumas situações a proporcionalidade dos riscos para uma dada covariável pode não ser válida e, este caso, uma abordagem que não dependa de tal suposição é necessária. Nesta tese, propomos um modelo tipo Cox em que o efeito da covariável e a função de risco basal são representadas via bases de Fourier e ondaletas de Haar clássicas e deformadas. Propomos também um procedimento de predição da função de sobrevivência para um paciente específico. Estudos de simulações e aplicações a dados reais sugerem que nosso método pode ser uma ferramenta valiosa em situações práticas em que o efeito da covariável é dependente do tempo. Por meio destes estudos, fazemos comparações entre as duas abordagens propostas, e comparações com outra já conhecida na literatura, onde verificamos resultados satisfatórios. / The semiparametric Cox model is often considered when modeling survival data. It is very flexible, allowing for the evaluation of covariates effects. One of its main advantages is the easy of interpretation, as long as the rate of the hazards for two individuals does not vary over time. However, this proportionality of the hazards may not be true in some practical situations and, in this case, an approach not relying on such assumption is needed. In this thesis we propose a Cox-type model that allows for time-varying covariate effects, for which the baseline hazard is based on Fourier series and wavelets on a time-frequency representation. We derive a prediction method for the survival of future patients with any specific set of covariates. Simulations and an application to a real data set suggest that our method may be a valuable tool to model data in practical situations where covariate effects vary over time. Through these studies, we make comparisons between the two approaches proposed here and comparisons with other already known in the literature, where we verify satisfactory results.

Σκοπός της παρούσας διπλωματικής εργασίας είναι η κατασκευή ενός συστήματος που να μπορεί να ξεχωρίζει τα οχήματα από άλλα αντικείμενα με τη χρήση κυματιδίου Haar και φίλτρου Gabor (εξαγωγή χαρακτηριστικών) και SVM, RBF για ταξινόμηση. / The aim of this thesis is the construction of a system that will be able to distiguish vehicles from other objects using Haar and Gabor filter (export characteristic) and SVM, RBF for classification.

Description cephalometric images and the characteristic points on the skull for cephalometric analysis. Theoretical analysis of digital image editing and image before the actual detection. The range of possible methods for determining the characteristic points on the face. Experimental verification of edge detectors, Hu moments with neural networks and Haar wavelets with Viola-Jones detector.

The thesis deals with image classifiers and their implementation using FPGA technology. There are discussed weak and strong classifiers in the work. As an example of strong classifiers, the AdaBoost algorithm is described. In the case of weak classifiers, basic types of feature classifiers are shown, including Haar and Gabor wavelets. The rest of work is primarily focused on LBP, LRP and LR classifiers, which are well suitable for efficient implementation in FPGAs. With these classifiers is designed pseudo-parallel architecture. Process of classifications is divided on software and hardware parts. The thesis deals with hardware part of classifications. The designed classifier is very fast and produces results of classification every clock cycle.