This thesis is concerned with the development of an optimization based approach to solving labelling problems which involve the assignment of image entities into interpretation categories in computer vision. Attention is mainly focussed on the theoretical basis and computational aspect of continuous relaxation for solving a discrete labelling problem based on an optimization framework. First, a theoretical basis for continuous relaxation is presented which includes the formulation of a discrete labelling problem as a continuous minimization problem and an analysis of labelling unambiguity associated with continuous relaxation. The main advantage of the formulation over existing formulations is the embedding of relational measurements into the specification of a consistent labelling. The analysis provides a sufficient condition for a continuous labelling formulation to ensure that a consistent labelling is unambiguous. Second, a continuous relaxation labelling algorithm based on mean field theory is presented with the aim of approximating simulated annealing in a deterministic manner. The novelty of the algorithm lies in the utilization of mean field theory technique to avoid stochastic optimization for approximating the global optimum of a consistent labelling criterion. This is contrast to the conventional methods which find a local optimum near an initial estimate of labelling. A special three-frame discrete labelling problem of establishing trinocular stereo correspondence and a mixed labelling problem of interpreting image entities in terms of cylindrical objects and their locations are also addressed. For the former, two orientation based geometric constraints are suggested for matching lines among three viewpoints and a method is presented to find a consistent labelling using simulated annealing. For the latter, the image interpretation of 3D cylindrical objects and their 3D locations is achieved using three knowledge sources: edge map, region map and the ground plane constraint. The method differs from existing methods in that it exploits an integrated use of multiple image cues to simplify the interpretation task and improve the interpretation performance. Experimental results on both synthetic data and real images are provided to demonstrate the viability and the potential of the proposed methods throughout the thesis.

En quel sens les livres que Deleuze a écrits sur le cinéma sont-ils des livres de philosophie ? Dans une démarche généalogique, notre travail montre comment Deleuze « capture » de façons différentes les œuvres de quatre philosophes – Kant, Bergson, Peirce, Spinoza – afin de lui permettre d’avancer dans sa propre philosophie. A partir d’une rencontre avec le cinéma dans son ensemble, Deleuze prolonge sa réflexion sur l’empirisme transcendantal, reconsidère la question de l’image et des signes, revisite secrètement l’éthique de Spinoza afin de nous proposer une nouvelle éthique, qui ne répond plus à la question « Que peut un corps ? » mais à sa généralisation « Que peut une image ? ». Suivant la figure d’un spinozisme post-kantien que nous identifions chez Deleuze, le temps comme affect de soi par soi chez Kant équivaut aux auto-affections du second genre de connaissance chez Spinoza : le temps devient le lieu où se déploie la vie spirituelle dans l’attribut de la pensée. A la fois genèse de la sensibilité, cosmogonie, sémiotique et éthique, L’Image-mouvement et L’Image-temps construisent une génétique des puissances de l’image dont les œuvres singulières des cinéastes sont à la fois les jalons et les pierres de touche : la rencontre avec ces œuvres permet à la philosophie de Deleuze de subir l’épreuve du réel et de la faire bifurquer au gré des rencontres avec les pensées des cinéastes. Deleuze se sert du cinéma, qui devient la vérification expérimentale de sa philosophie, cependant que le cinéma « capture » Deleuze, et l’amène à tracer des cheminements de pensée inédits. Dans cette parade amoureuse, Deleuze est la guêpe, le cinéma l’orchidée. / To what extent are the books written by Deleuze about cinéma philosophy books ? Following a genealogical reasoning, our study shows how Deleuze “captures” in different ways the works of four philosophers – Kant, Bergson, Peirce, Spinoza – in order to get ahead in his own philosophy. From his encounter with cinema as a whole, Deleuze continues his reflection about transcendental empiricism, reconsidering the issue of image ands signs and secretly revisiting Spinoza’s ethics to offer a new system of ethics which no longer answers the question “What can a body live ?” but its generalization “what can an image live ?” Following the figure of a post-kantian spinozism that we have identified in Deleuze’s work, time as an affect of the self by the self in Kant’s philosophy can be equated with the self-affections of the second kind of knowledge in Spinoza’s work : time becomes the place where spiritual life can spread in the attribute of thought. Being at the same time a genesis of sensitivity, a cosmogony, semiotics and ethics, The Movement-image and The Time-image constitute a system of genetics of image powers of which film-makers singular creations are both the landmarks and the touchstones : Deleuze’s encounter with these movies allows his philosophy to undergo the test of the real and to make it change its course each time he meets a film-maker’s thinking. Deleuze uses cinema which becomes the experimental checking of his philosophy where as cinema “captures” Deleuze and leads him to open up new ways of thinking. In this mating display, Deleuze is the wasp and cinema is the orchid.

Dans le cadre de cette thèse, nous proposons une solution au problème de l'estimation du mouvement 3D d'objets dont la surface est réfléchissante, lequel est très complexe quand leurs caractéristiques géométriques à elles seules ne permettent pas de définir des indices caractéristiques d'un mouvement. Nous avons focalisé notre étude sur le cas particulier de la sphère, dont la parfaite symétrie complique au maximum le problème d'estimation du mouvement.En effet, lorsqu'une sphère est affectée d'un mouvement de rotation pure autour d'un de ses axes, ses contours extérieurs apparaissent statiques. Ces derniersn'apportent donc pas d'information utilisable par le système pour estimer le mouvement. Nous proposons donc une approche se basant sur la texture dans un schéma de mise en correspondance 3D/2D modifié. Ici, cette information est exploitée différemment si elle provient d'une composante spéculaire ou diffuse.Enfin, nous démontrons que la propriété réfléchissante de la surface n'est plus considérée comme un obstacle mais que au contraire, cette propriété procure une information supplémentaire sur le mouvement recherché. / Recovering 3D motion of reflective objects in image sequences is still a cumbersome problem for computer vision. One common approach is to track geometric features of the object such as contours and edges since they are rather insensitive to light reflections. However, such basic features fail to recover the actual 3D motion in some cases. For example, the external contour of a sphere rotating about one of its axes remains static in the image. In thisthesis, we propose a new approach to 3D motion recovery of a reflective sphere visible in an image sequence.Instead of tracking only geometric features, our technique makes use of texture information in a slightly modified image alignment method. Unlike in classical image alignment methods, texture information is processed differently whether it comes from a diffuse or a specular light component.Using this technique, we show that motion estimation is not only possible when dealing with reflective objects, but also that specular components can offer information about the 3D motion. Finally, we present some results obtained from the analysis of image sequences.

M.Ing. / This dissertation proposes a marker-free visual based interface device to be used with menu driven systems. This system, called HandsFree, uses the Graphics Processing Unit (GPU) together with Shader technology to perform the image processing. HandsFree makes use of a web camera to gain user input without requiring elementary computer skills. Background subtraction was used to extract user input from the images. The problems usually obtained with background subtraction were overcome by using an averaging technique. Test results proved HandsFree to be robust against different coloured backgrounds and skin tones, different lighting intensity and sudden change in lighting intensity.

This diploma thesis is focused on the analysis of internal and external image of the company ABC. This firm has not wished to be specified. The main goal of this thesis was to analyze image of the company ABC operating on the logistics market in the Czech republic. This goal was fulfilled and according to the results, firm has a positive image from the employee and customer point of view. The reader can find final references in the application part of this thesis. First minor goal was to help reader to identify key points of this topic and extend his knowledge about the image of company. The reader can acquire broader information about mentioned topic in the theoretical part and following sections of this diploma thesis improve her/his ability related to the image of specific company. Second minor goal was to describe internal employee point of view and present it to the employer, company ABC. This goal was accomplished as there is a lot of important information and data included in the replies to the questionnaire. Third minor goal was to characterize Czech logistics market and define competitive companies based on the knowledge of employees and customers of the enterprise ABC. The company is considered as one of the main firms but is not the market leader. It was not possible to analyze customer point of view since the internal NPA file did not contain it or the data was incomplete. The author of this diploma thesis used own questionnaire and internal NPA file received by the company ABC to extract the results. He also used a combination of the literal transcription method and following cluster creating technique to construe the conclusions.

No description available.

The Blind Image Deconvolution/Deblurring (BID) problem was realised in the early 1960s but it still remains a challenging task for the image processing research community to find an efficient, reliable and most importantly a diversely applicable deblurring scheme. The main challenge arises from little or no prior information about the image or the blurring process as well as the lack of optimal restoration filters to reduce or completely eliminate the blurring effect. Moreover, restoration can be marred by the two common side effects of deblurring; namely the noise amplification and ringing artefacts that arise in the deblurred image due to an unrealizable or imperfect restoration filter. Also, developing a scheme that can process different types of blur, especially for real images, is yet to be realized to a satisfactory level. This research is focused on the development of blind restoration schemes for real life blurred images. The primary objective is to design a BID scheme that is robust in term of Point Spread Function (PSF) estimation, efficient in terms of restoration speed, and effective in terms of restoration quality. A desired scheme will require a deblurring measure to act as a feedback of quality regarding the deblurred image and lead the estimation of the blurring PSF. The blurred image and the estimated PSF can then be passed on to any classical restoration filter for deblurring. The deblurring measures presented in this research include blind non-Gaussianity measures as well as blind Image Quality Measures (IQMs). These measures are blind in the sense that they are able to gauge the quality of an image directly from it without the need to reference a high quality image. The non-Gaussianity measures include spatial and spectral kurtosis measures; while the image quality analysers include the Blind/Reference-less Image Spatial QUality Evaluator (BRISQUE), Natural Image Quality Evaluator (NIQE) index and Reblurring based Peak Signal to Noise Ratio (RPSNR) measure. BRISQUE, NIQE and spectral kurtosis, are introduced for the first time as deblurring measures for BID. RPSNR is a novel full reference yet blind IQM designed and used in this research work. Experiments were conducted on different image datasets and real life blurred images. Optimization of the BID schemes has been achieved using a gradient descent based scheme and a Genetic Algorithm (GA). Quantitative results based on full-reference and non-reference IQMs, present BRISQUE as a robust and computationally efficient blind feedback quality measure. Also, parametric and arbitrarily shaped (non-parametric or generic) PSFs were treated for the blind deconvolution of images. The parametric forms of PSF include uniform Gaussian, motion and out-of-focus blur. The arbitrarily shaped PSFs comprise blurs that have a much more complex blur shape which cannot be easily modelled in the parametric form. A novel scheme for arbitrarily shaped PSF estimation and blind deblurring has been designed, implemented and tested on artificial and real life blurred images. The scheme provides a unified base for the estimation of both parametric and arbitrarily shaped PSFs with the BRISQUE quality measure in conjunction with a GA. Full-reference and non-reference IQMs have been utilised to gauge the quality of deblurred images for the BID schemes. In the real BID case, only non-reference IQMs can be employed due to the unavailability of the reference high quality image. Quantitative results of these images depict the restoration ability of the BID scheme. The significance of the research work lies in the BID scheme‘s ability to handle parametric and arbitrarily shaped PSFs using a single algorithm, for single-shot blurred images, with enhanced optimization through the gradient descent scheme and GA in conjunction with multiple feedback IQMs.

A novel approach for the analysis of spinal cord deformation based on a combined technique of non-invasive imaging and medical image processing is presented. A sopposed to traditional approaches where animal spinal cords are exposed and directly subjected to mechanical impact in order to be examined, this approach can be used to quantify deformities of the spinal cord in vivo, so that deformations — specifically those of myelopathy-related sustained compression — of the spinal cord can be computed in its original physiological environment. This, then, allows for a more accurate understanding of spinal cord deformations and injuries. Images of rat spinal cord deformations, acquired using magnetic resonance imaging (MRI), were analyzed using a combination of various image processing methods, including image segmentation, a versor-based rigid registration technique, and a B-spline-based non-rigid registration technique. To verify the validity and assess the accuracy of this approach, several validation schemes were implemented to compare the deformation fields computed by the proposed algorithm against known deformation fields. First, validation was performed on a synthetically-generated spinal cord model data warped using synthetic deformations; error levels achieved were consistently below 6% with respect to cord width, even for large degrees of deformation up to half of the dorsal-ventral width of the cord (50% deflection). Then, accuracy was established using in vivo rat spinal cord images warped using those same synthetic deformations; error levels achieved were also consistently below 6% with respect to cord width, in this case for large degrees of deformation up to the entire dorsal-ventral width of the cord (100% deflection). Finally, the accuracy was assessed using data from the Visible Human Project (VHP) warped using simulated deformations obtained from finite element (FE) analysis of the spinal cord; error levels achieved were as low as 3.9% with respect to cord width. This in vivo, non-invasive semi-automated analysis tool provides a new framework through which the causes, mechanisms, and tolerance parameters of myelopathy-related sustained spinal cord compression, as well as the measures used in neuroprotection and regeneration of spinal cord tissue, can be prospectively derived in a manner that ensures the bio-fidelity of the cord. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

No description available.

No description available.