Submitted by Milena Rubi ( ri.bso@ufscar.br) on 2017-10-17T16:07:35Z No. of bitstreams: 1 CUNHA_Bruno_2017.pdf: 1281922 bytes, checksum: 605ecd45f46a3b67332ed6bd13043af5 (MD5) / Approved for entry into archive by Milena Rubi ( ri.bso@ufscar.br) on 2017-10-17T16:07:44Z (GMT) No. of bitstreams: 1 CUNHA_Bruno_2017.pdf: 1281922 bytes, checksum: 605ecd45f46a3b67332ed6bd13043af5 (MD5) / Approved for entry into archive by Milena Rubi ( ri.bso@ufscar.br) on 2017-10-17T16:07:53Z (GMT) No. of bitstreams: 1 CUNHA_Bruno_2017.pdf: 1281922 bytes, checksum: 605ecd45f46a3b67332ed6bd13043af5 (MD5) / Made available in DSpace on 2017-10-17T16:08:04Z (GMT). No. of bitstreams: 1 CUNHA_Bruno_2017.pdf: 1281922 bytes, checksum: 605ecd45f46a3b67332ed6bd13043af5 (MD5) Previous issue date: 2016-11-10 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / This work proposes both a study and a development of an algorithm for super-resolution of digital images using projections onto convex sets. The method is based on a classic algorithm for spatial super-resolution which considering the subpixel information present in a set of lower resolution images, generate an image of higher resolution and better visual quality. We propose the incorporation of a new restriction based on the Richardson-Lucy algorithm in order to restore and recover part of the spatial frequencies lost during the degradation and decimation process of the high resolution images. In this way the algorithm provides a hybrid approach based on projections onto convex sets which is capable of promoting both the spatial and spectral image super-resolution. The proposed approach was compared with the original algorithm from Sezan and Tekalp and later with a method based on a robust framework that is considered nowadays one of the most effective methods for super-resolution. The results, considering both the visual and the mean square error analysis, demonstrate that the proposed method has great potential promoting increased visual quality over the images studied. / Este trabalho visa o estudo e o desenvolvimento de um algoritmo para super-resolução de imagens digitais baseado na teoria de projeções sobre conjuntos convexos. O método é baseado em um algoritmo clássico de projeções sobre restrições convexas para super- resolução espacial onde se busca, considerando as informações subpixel presentes em um conjunto de imagens de menor resolução, gerar uma imagem de maior resolução e com melhor qualidade visual. Propomos a incorporação de uma nova restrição baseada no algoritmo de Richardson-Lucy para restaurar e recuperar parte das frequências espaciais perdidas durante o processo de degradação e decimação das imagens de alta resolução. Nesse sentido o algoritmo provê uma abordagem híbrida baseada em projeções sobre conjuntos convexos que é capaz de promover simultaneamente a super-resolução espacial e a espectral. A abordagem proposta foi comparada com o algoritmo original de Sezan e Tekalp e posteriormente com um método baseado em um framework de super-resolução robusta, considerado um dos métodos mais eficazes na atualidade. Os resultados obtidos, considerando as análises visuais e também através do erro médio quadrático, demonstram que o método proposto possui grande potencialidade promovendo o aumento da qualidade visual das imagens estudadas.

Submitted by Milena Rubi (milenarubi@ufscar.br) on 2017-06-01T14:27:18Z No. of bitstreams: 1 ANTUNES_FILHO_Amauri_2016.pdf: 23049873 bytes, checksum: 5246fc4b37bd3364d5abf8cf81fbdb6f (MD5) / Approved for entry into archive by Milena Rubi (milenarubi@ufscar.br) on 2017-06-01T14:27:31Z (GMT) No. of bitstreams: 1 ANTUNES_FILHO_Amauri_2016.pdf: 23049873 bytes, checksum: 5246fc4b37bd3364d5abf8cf81fbdb6f (MD5) / Approved for entry into archive by Milena Rubi (milenarubi@ufscar.br) on 2017-06-01T14:39:27Z (GMT) No. of bitstreams: 1 ANTUNES_FILHO_Amauri_2016.pdf: 23049873 bytes, checksum: 5246fc4b37bd3364d5abf8cf81fbdb6f (MD5) / Made available in DSpace on 2017-06-01T14:39:33Z (GMT). No. of bitstreams: 1 ANTUNES_FILHO_Amauri_2016.pdf: 23049873 bytes, checksum: 5246fc4b37bd3364d5abf8cf81fbdb6f (MD5) Previous issue date: 2016-12-09 / Não recebi financiamento / The super-resolution aims to obtain a higher resolution image, using information from one or more low resolution images. There are different applications where super-resolution may be used, such as medical and forensic images. This work proposes a study and development of algorithms, based on Tekalp and Sezan’s algorithm, using the projection onto convex sets theory, in order to obtain super-resolution, therefore obtaining a higher resolution image, from a low resolution images set, with subpixel informations. We proposed the adition of a convex restriction based on Richardon-Lucy’s algorithm, modified to be weighted by Canny’s filter, along with total variation regularization, aiming to restore frequencies lost during high resolution images decimation and degradation processes . Therefore, we have a hybrid approach, that implements spatial and spectral super-resolution simultaneously, based on projection onto convex sets. The obtained results by the proposed algorithms were compared to Tekalp and Sezan’s base algorithm. The visual analysis of the images, along with the mean square error were taken in consideration for comparisons. In development, grayscale images were used, but the methods are extensible for color images. Results showed improvement in the obtained images, with less noise, blurring and more edge definition than the low resolution images. We conclude that the approach has potential for medical applications and forensic computation. / A super-resolução tem por objetivo a obtenção de uma imagem de maior resolução, utilizando informações de uma ou mais imagens de baixa resolução. Existem diferentes aplicações onde a utilização da super-resolução é empregada, como imagens médicas e forenses. A proposta deste trabalho é o estudo e desenvolvimento de algoritmos, baseados no algoritmo de Tekalp e Sezan, que utilizam a teoria de projeções sobre conjuntos convexos com o objetivo de super-resolução, obtendo uma imagem de maior resolução a partir de um conjunto de imagens com informações subpixel. Propomos também, uma restrição convexa baseada no algoritmo de Richardson-Lucy, modificado para ser ponderado pelo filtro de Canny, juntamente com regularização total variation, com o intuito de restaurar frequências perdidas durante os processos de decimação e degradação das imagens de alta resolução. Com isso temos uma abordagem híbrida, que implementa super-resolução espacial e espectral simultaneamente, baseada em projeções sobre conjuntos convexos. Os resultados obtidos pelos algoritmos propostos foram comparados com o algoritmo base de Tekalp e Sezan. Para as comparações, levou-se em consideração a análise visual das imagens juntamente com o erro quadrático médio. No desenvolvimento, foram utilizadas imagens em tons de cinza, mas os métodos são extensíveis para imagens coloridas. Os resultados apresentaram melhoria nas imagens obtidas em relação as imagens de baixa resolução, minimizando o ruído, o borramento e melhor definição das bordas. Concluímos que a abordagem possui potencial para aplicações médicas e em computação forense.

La mesure de la forme 3D du visage est une problématique qui attire de plus en plus de chercheurs et qui trouve son application dans des domaines divers tels que la biométrie, l’animation et la chirurgie faciale. Les solutions actuelles sont souvent basées sur des systèmes projecteur/caméra et utilisent de la lumière structurée pour compenser l’insuffisance de la texture faciale. L’information 3D est ensuite calculée en décodant la distorsion des patrons projetés sur le visage. Une des techniques les plus utilisées de la lumière structurée est la codification sinusoïdale par décalage de phase qui permet une numérisation 3D de résolution pixélique. Cette technique exige une étape de déroulement de phase, sensible à l’éclairage ambiant surtout quand le nombre de patrons projetés est limité. En plus, la projection de plusieurs patrons impacte le délai de numérisation et peut générer des artefacts surtout pour la capture d’un visage en mouvement. Une alternative aux approches projecteur-caméra consiste à estimer l’information 3D par appariement stéréo suivi par une triangulation optique. Cependant, le modèle calculé par cette technique est généralement non-dense et manque de précision. Des travaux récents proposent la super-résolution pour densifier et débruiter les images de profondeur. La super-résolution a été particulièrement proposée pour les caméras 3D TOF (Time-Of-Flight) qui fournissent des scans 3D très bruités. Ce travail de thèse propose une solution de numérisation 3D à faible coût avec un schéma de super-résolution spatio-temporelle. Elle utilise un système multi-caméra étalonné assisté par une source de projection non-étalonnée. Elle est particulièrement adaptée à la reconstruction 3D de visages, i.e. rapide et mobile. La solution proposée est une approche hybride qui associe la stéréovision et la codification sinusoïdale par décalage de phase, et qui non seulement profite de leurs avantages mais qui surmonte leurs faiblesses. Le schéma de la super-résolution proposé permet de corriger l’information 3D, de compléter la vue scannée du visage en traitant son aspect déformable. / 3D face measurement is increasingly demanded for many applications such as bio-metrics, animation and facial surgery. Current solutions often employ a structured light camera/projector device to overcome the relatively uniform appearance of skin. Depth in-formation is recovered by decoding patterns of the projected structured light. One of the most widely used structured-light coding is sinusoidal phase shifting which allows a 3Ddense resolution. Current solutions mostly utilize more than three phase-shifted sinusoidal patterns to recover the depth information, thus impacting the acquisition delay. They further require projector-camera calibration whose accuracy is crucial for phase to depth estimation step. Also, they need an unwrapping stage which is sensitive to ambient light, especially when the number of patterns decreases. An alternative to projector-camera systems consists of recovering depth information by stereovision using a multi-camera system. A stereo matching step finds correspondence between stereo images and the 3D information is obtained by optical triangulation. However, the model computed in this way generally is quite sparse. To up sample and denoise depth images, researchers looked into super-resolution techniques. Super-resolution was especially proposed for time-of-flight cameras which have very low data quality and a very high random noise. This thesis proposes a3D acquisition solution with a 3D space-time non-rigid super-resolution capability, using a calibrated multi-camera system coupled with a non calibrated projector device, which is particularly suited to 3D face scanning, i.e. rapid and easily movable. The proposed solution is a hybrid stereovision and phase-shifting approach, using two shifted patterns and a texture image, which not only takes advantage of the assets of stereovision and structured light but also overcomes their weaknesses. The super-resolution scheme involves a 3D non-rigid registration for 3D artifacts correction in the presence of small non-rigid deformations as facial expressions.

La caractérisation des dynamiques de sous-mésoéchelle (<10km) à la surface de l'océan et leurs impacts sur les processus océaniques globaux sont des enjeux scientifiques majeurs. L'imagerie satellitaire est un outil essentiel dans ce contexte, qui présente toutefois des limitations liées aux instruments de télédétection. Dans le cas des images de température de surface des océans (SST), les mesures satellitaires des structures océaniques sont limitées par la résolution grossière des capteurs micro-ondes (~50km) d'une part, et par la sensibilité aux conditions climatiques (e.g., couverture nuageuse) des instruments de mesure infrarouge haute-résolution. Dans cette thèse, nous nous intéressons à l'analyse, la modélisation et la reconstruction des structures turbulentes haute-résolution capturées par imagerie satellitaire de SST, et proposons quatre contributions principales. Dans un premier temps, nous développons une méthode de filtrage conjointe Fourier-ondelettes pour le prétraitement d'artefacts géométriques dans les observations satellitaires infrarouges. Dans un deuxième temps, nous nous focalisons sur la caractérisation de la variabilité géométrique de champs de température de surface (SST) en utilisant des modèles de marches aléatoires appliqués aux lignes de niveaux. En particulier, nous considérons des processus aléatoires de type schramm Loewner (SLE). Nous nous intéressons ensuite à la modélisation stochastique des variabilités inter-échelles de champs de SST. Des modèles stochastiques de textures multivariées sont introduits. Ces modèles permettent de reproduire des propriétés statistiques et spectrales similaires à celles des données ayant servi à les calibrer. Nous développons ensuite des méthodes de super-résolution de champs de SST conditionnellement à une observation basse-résolution. Nous utilisons des modèles multivariés de textures formulés dans le domaine des ondelettes, en exploitant l'apprentissage d'à priori statistiques (i.e., covariances et covariances croisées) des différentes sous-bandes à partir d'images haute-résolution. Des contraintes supplémentaires imposées sur la phase de Fourier des différentes sous-bandes simulées permettent la reconstruction de structures géométriques marquées tels que les fronts. Nous démontrons la pertinence de la méthode proposée sur des images satellitaires de SST obtenues à partir du capteur Modis/Aqua. / The characterization of sub-mesoscale dynamics (<10 km) in the ocean surface and their impact on global ocean processes are major scientific issues. Satellite imagery is an essential tool within this framework. However, the use of remote sensing techniques still raise challenging. For instance, regarding Sea Surface Temperature (SST) images, satellite measurements of oceanic structures are limited by the coarse resolution of microwave sensors (~50km) on one hand, and by sensitivity to climatic conditions (eg., Cloud cover) of high-resolution infrared instruments on the other hand. In this thesis, we are interested in analysis, modeling and reconstruction of high-resolution turbulent structures captured by satellite SST imagery. In this context, we propose four main contributions. First, we develop a joint Fourier-Wavelet filtering method for the pre-processing of geometrical noises in satellite-based infrared observations, namely the striping noises. Secondly, we focus on the characterization of the geometric variability of sea surface temperature (SST) fields using random walk models applied to SST isolines. In particular, we consider the class of Schramm Loewner evolution curves (SLE). We then focus on the stochastic modeling of the cross-scale variabilities of SST fields. Stochastic multivariate texture-based models are introduced. These models are designed to reproduce several statistics and spectral properties that are observed on the data that are used to calibrate the model. We then develop our framework for stochastic super-resolution of SST fields conditionally to low-resolution observations. We use multivariate texture-based models formulated in the wavelet domain. These models exploit the formulation of statistical and spectral priors (i.e., covariances and cross-covariances) on wavelet subbands. These priors are directly learned from exemplar high-resolution images. Additional constraints imposed on the Fourier-phase of the different simulated subbands allow the reconstruction of coherent geometric structures such as the edge information. Our method is tested and validated using infrared high-resolution satellite SST images provided by Aqua Modis sensor.

Cette thèse vise à améliorer la résolution en trois dimensions grâce à une technique récente d’imagerie : la microscopie tomographique diffractive (MTD). Son principe est d’éclairer l’objet successivement sous différents angles en lumière cohérente, de détecter le champ diffracté en phase et en amplitude, et de reconstruire la carte 3D de permittivité de l’objet par un algorithme d’inversion. La MTD s’est avérée capable de combiner plusieurs modalités utiles pour la microscopie sans marquage, telles que plein champ, champ sombre, à contraste de phase, confocale, ou encore la microscopie à synthèse d’ouverture 2D ou 3D. Toutes sont basées sur des approximations scalaires et linéaires, ce qui restreint leur domaine d’application pour restituer l’objet de manière quantitative. A l’aide d’une inversion numérique rigoureuse prenant en compte la polarisation du champ et le phénomène de diffusion multiple, nous sommes parvenus à reconstruire la carte 3D de permittivité d’objets avec une résolution de λ/4. Une amélioration supplémentaire la portant à λ/10 a été rendue possible par l’insertion d’information a priori sur l’objet dans l’algorithme d’inversion. Enfin, la résolution axiale est moins bonne du fait de l’asymétrie des schémas d’illumination et de détection dans les microscopes. Pour s’affranchir de cette limitation, une configuration de tomographie assistée par miroir a été implémentée et a mis en évidence un pouvoir de séparation axial meilleur que λ/2. Au final, la MTD s’est illustrée comme un outil de caractérisation puissant pour reconstruire en 3D les objets ainsi que leurs indices optiques, à des résolutions bien supérieures à celles des microscopes conventionnels. / This PhD thesis is devoted to the three-dimensional isotropic resolution improvement using optical tomographic diffraction microscopy (TDM), an emerging optical microscope technique. The principle is to illuminate the sample successively with various angles of coherent light, collect the complex (amplitude and phase) diffracted field and reconstruct the sample 3D permittivity map through an inversion algorithm. A single TDM measurement was shown to combine several popular microscopy techniques such as bright-field microscope, dark-field microscope, phase-contrast microscope, confocal microscope, 2D and 3D synthetic aperture microscopes. All rely on scalar and linear approximations that assume a linear link between the object and the field diffracted by it, which limit their applicability to retrieve the object quantitatively. Thanks to a rigorous numerical inversion of the TDM diffracted field data which takes into account the polarization of the field and the multiple scattering process, we were able to reconstruct the 3D permittivity map of the object with a λ/4 transverse resolution. A further improvement to λ/10 transverse resolution was achieved by providing a priori information about the sample to the non-linear inversion algorithm. Lastly, the poor axial resolution in microscopes is due to the fundamental asymmetry of illumination and detection. To overcome this, a mirror-assisted tomography configuration was implemented, and has demonstrated a sub-λ/2 axial resolution capability. As a result, TDM can be seen as a powerful tool to reconstruct objects in three-dimensions with their optical material properties at resolution far superior to conventional microscopes.

High quality image /video has become an integral part in our day-to-day life ranging from many areas of science, engineering and medical diagnosis. All these imaging applications call for high resolution, properly focused and crisp images. However, in real situations obtaining such a high quality image is expensive, and in some cases it is not practical. In imaging systems such as digital camera, blur and noise degrade the image quality. The recorded images look blurred, noisy and unable to resolve the finer details of the scene, which are clearly notable under zoomed conditions. The post processing techniques based on computational methods extract the hidden information and thereby improve the quality of the captured images. The study in this thesis focuses on deconvolution and eventually blind de-convolution problem of a single frame captured at low light imaging conditions arising from digital photography/surveillance imaging applications. Our intention is to restore a sharp image from its blurred and noisy observation, when the blur is completely known/unknown and such inverse problems are ill-posed/twice ill-posed. This thesis consists of two major parts. The first part addresses deconvolution/blind deconvolution problem using Bayesian approach with fuzzy logic based gradient potential as a prior functional. In comparison with analog cameras, artifacts are visible in digital cameras when the images are enlarged and there is a demand to enhance the resolution. The increased resolution can be in spatial, temporal or even in both the dimensions. Super resolution reconstruction methods reconstruct images/video containing spectral information beyond that is available in the captured low resolution images. The second part of the thesis addresses resolution enhancement of observed monochromatic/color images using multiple frames of the same scene. This reconstruction problem is formulated in Bayesian domain with an aspiration of reducing blur, noise, aliasing and increasing the spatial resolution. The image is modeled as Markov random field and a fuzzy logic filter based gradient potential is used to differentiate between edge and noisy pixels. Suitable priors are adaptively applied to obtain artifact free/reduced images. In this work, all our approaches are experimentally validated using standard test images. The Matlab based programming tools are used for carrying out the validation. The performance of the approaches are qualitatively compared with results of recently proposed methods. Our results turn out to be visually pleasing and quantitatively competitive.

This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of various neural network architectures. The best implemented architecture can colorize images, in particular, works well with outdoor areas. The architecture for image super-resolution with residual blocks that was trained with a perceptual loss function performs a double increase in image resolution (4x more pixels in total). Part of this thesis is also an implementation of a web application that uses trained models for image modification.

This diploma thesis deals with image super-resolution with conservation of good quality. Firstly, there are described state of the art methods dealing with this problem, as well as principles of neural networks with focus on convolutional ones. Finally, there is described a few models of convolutional neural network for image super-resolution to double size, which have been trained, tested and compared on newly created database with pictures of people.

VINTERA, J. Spectral anlysis with superesolution. Brno: University of Technology, The Faculty of Electrical Engineering and Communication, 2008. 85 p. Master’s thesis. This thesis deals with the topic of super-resolution spectral analysis in the Signal Processing Toolset. The Signal Processing Toolset is a software component of the LabVIEW 8.1. program equipment. The thesis consists of three main parts. In the first part the basic theoretic concepts of the Model-Based Frequency Analysis are described. The second part serves as a user manual for the super-resolution spectral analysis in the Signal Processing Toolset. The last part describes the application of the theory introduced in the first part, by means of testing the properties of the methods used by the Toolset.

Computer vision is a key component of any autonomous system. Real world computer vision applications rely on a proper and accurate detection and classification of objects. A detection algorithm that doesn’t guarantee reasonable detection accuracy is not applicable in real time scenarios where safety is the main objective. Factors that impact detection accuracy are illumination conditions and image resolution. Both contribute to degradation of objects and lead to low classifications and detection accuracy. Recent development of Convolutional Neural Networks (CNNs) based algorithms offers possibilities for low-light (LL) image enhancement and super resolution (SR) image generation which makes it possible to combine such models in order to improve image quality and increase detection accuracy. This thesis evaluates different CNNs models for SR generation and LL enhancement by comparing generated images against ground truth images. To quantify the impact of the respective model on detection accuracy, a detection procedure was evaluated on generated images. Experimental results evaluated on images selected from NoghtOwls and Caltech Pedestrian datasets proved that super resolution image generation and low-light image enhancement improve detection accuracy by a substantial margin. Additionally, it has been proven that a cascade of SR generation and LL enhancement further boosts detection accuracy. However, the main drawback of such cascades is related to an increased computational time which limits possibilities for a range of real time applications. / Datorseende är en nyckelkomponent i alla autonoma system. Applikationer för datorseende i realtid är beroende av en korrekt detektering och klassificering av objekt. En detekteringsalgoritm som inte kan garantera rimlig noggrannhet är inte tillämpningsbar i realtidsscenarier, där huvudmålet är säkerhet. Faktorer som påverkar detekteringsnoggrannheten är belysningförhållanden och bildupplösning. Dessa bidrar till degradering av objekt och leder till låg klassificerings- och detekteringsnoggrannhet. Senaste utvecklingar av Convolutional Neural Networks (CNNs) -baserade algoritmer erbjuder möjligheter för förbättring av bilder med dålig belysning och bildgenerering med superupplösning vilket gör det möjligt att kombinera sådana modeller för att förbättra bildkvaliteten och öka detekteringsnoggrannheten. I denna uppsats utvärderas olika CNN-modeller för superupplösning och förbättring av bilder med dålig belysning genom att jämföra genererade bilder med det faktiska data. För att kvantifiera inverkan av respektive modell på detektionsnoggrannhet utvärderades en detekteringsprocedur på genererade bilder. Experimentella resultat utvärderades på bilder utvalda från NoghtOwls och Caltech datauppsättningar för fotgängare och visade att bildgenerering med superupplösning och bildförbättring i svagt ljus förbättrar noggrannheten med en betydande marginal. Dessutom har det bevisats att en kaskad av superupplösning-generering och förbättring av bilder med dålig belysning ytterligare ökar noggrannheten. Den största nackdelen med sådana kaskader är relaterad till en ökad beräkningstid som begränsar möjligheterna för en rad realtidsapplikationer.