No description available.

The medial axis skeleton is a thin line graph that preserves the topology of a region. The skeleton has often been cited as a useful representation for shape description, region interpretation, and object recognition. Unfortunately, the computation of the skeleton is extremely sensitive to variations in the bounding contour. In this paper, we describe a robust method for computing the medial axis skeleton across a variety of scales. The resulting scale-space is parametric with the complexity of the skeleton, where the complexity is defined as the number of branches in the skeleton.

Visual motion carries information about the dynamics of ascene. Automatic interpretation of this information isimportant when designing computer systems forvisualnavigation, surveillance, human-computer interaction, browsingof video databases and other growing applications. In this thesis, we address the issue of motionrepresentation for the purpose of detecting and recognizingmotion patterns in video sequences. We localize the motion inspace and time and propose to use local spatio-temporal imagefeatures as primitives when representing and recognizingmotions. To detect such features, we propose to maximize ameasure of local variation of the image function over space andtime and show that such a method detects meaningful events inimage sequences. Due to its local nature, the proposed methodavoids the in.uence of global variations in the scene andovercomes the need for spatial segmentation and tracking priorto motion recognition. These properties are shown to be highlyuseful when recognizing human actions in complexscen es. Variations in scale and in relative motions of the cameramay strongly in.uence the structure of image sequences andtherefore the performance of recognition schemes. To addressthis problem, we develop a theory of local spatio-temporaladaptation and show that this approach provides invariance whenanalyzing image sequences under scaling and velocitytransformations. To obtain discriminative representations ofmotion patterns, we also develop several types of motiondescriptors and use them for classifying and matching localfeatures in image sequences. An extensive evaluation of thisapproach is performed and results in the context of the problemof human action recognition are presented. I n summary, this thesis provides the following contributions:(i) it introduces the notion of local features in space-timeand demonstrates the successful application of such featuresfor motion interpretation; (ii) it presents a theory and anevaluation of methods for local adaptation with respect toscale and velocity transformations in image sequences and (iii)it presents and evaluates a set of local motion descriptors,which in combination with methods for feature detection andfeature adaptation allow for robust recognition of humanactions in complexs cenes with cluttered and non-stationarybackgrounds as well as camera motion.

<p>Visual motion carries information about the dynamics of ascene. Automatic interpretation of this information isimportant when designing computer systems forvisualnavigation, surveillance, human-computer interaction, browsingof video databases and other growing applications.</p><p>In this thesis, we address the issue of motionrepresentation for the purpose of detecting and recognizingmotion patterns in video sequences. We localize the motion inspace and time and propose to use local spatio-temporal imagefeatures as primitives when representing and recognizingmotions. To detect such features, we propose to maximize ameasure of local variation of the image function over space andtime and show that such a method detects meaningful events inimage sequences. Due to its local nature, the proposed methodavoids the in.uence of global variations in the scene andovercomes the need for spatial segmentation and tracking priorto motion recognition. These properties are shown to be highlyuseful when recognizing human actions in complexscen es.</p><p>Variations in scale and in relative motions of the cameramay strongly in.uence the structure of image sequences andtherefore the performance of recognition schemes. To addressthis problem, we develop a theory of local spatio-temporaladaptation and show that this approach provides invariance whenanalyzing image sequences under scaling and velocitytransformations. To obtain discriminative representations ofmotion patterns, we also develop several types of motiondescriptors and use them for classifying and matching localfeatures in image sequences. An extensive evaluation of thisapproach is performed and results in the context of the problemof human action recognition are presented. I</p><p>n summary, this thesis provides the following contributions:(i) it introduces the notion of local features in space-timeand demonstrates the successful application of such featuresfor motion interpretation; (ii) it presents a theory and anevaluation of methods for local adaptation with respect toscale and velocity transformations in image sequences and (iii)it presents and evaluates a set of local motion descriptors,which in combination with methods for feature detection andfeature adaptation allow for robust recognition of humanactions in complexs cenes with cluttered and non-stationarybackgrounds as well as camera motion.</p>

nÃo hà / This work presents a scale-space based approach to assist dynamic resource provisioning. The application of this theory makes it possible to eliminate the presence of irrelevant information from a signal that can potentially induce wrong or late decision making. Dynamic provisioning involves increasing or decreasing the amount of resources allocated to an application in response to workload changes. While monitoring both resource consumption and application-specic metrics is fundamental in this process since the latter is of great importance to infer information about the former, dealing with these pieces of information to provision resources in dynamic environments poses a big challenge. The presence of unwanted characteristics, or noise, in a signal that represents the monitored metrics favors misleading interpretations and is known to aect forecast models. Even though some forecast models are robust to noise, reducing its inuence may decrease training time and increase eciency. Because a dynamic environment demands decision making and predictions on a quickly changing landscape, approximations are necessary. Thus it is important to realize how approximations give rise to limitations in the forecasting process. On the other hand, being aware of when detail is needed, and when it is not, is crucial to perform ecient dynamic forecastings. In a cloud environment, resource provisioning plays a key role for ensuring that providers adequately accomplish their obligation to customers while maximizing the utilization of the underlying infrastructure. Experiments are shown considering simulation of both reactive and proactive strategies scenarios with a real-world trace that corresponds to access rate. Results show that embodying scale-space theory in the decision making stage of dynamic provisioning strategies is very promising. It both improves workload analysis, making it more meaningful to our purposes, and lead to better predictions.

<p>The usage of automatic fingerprint identification systems as a means of identification and/or verification have increased substantially during the last couple of years. It is well known that small deviations may occur within a fingerprint over time, a problem referred to as template ageing. This problem, and other reasons for deviations between two images of the same fingerprint, complicates the identification/verification process, since distinct features may appear somewhat different in the two images that are matched. Commonly used to try and minimise this type of problem are different kinds of fingerprint image enhancement algorithms. This thesis tests different methods within the scale-space framework and evaluate their performance as fingerprint image enhancement methods. </p><p>The methods tested within this thesis ranges from linear scale-space filtering, where no prior information about the images is known, to scalar and tensor driven diffusion where analysis of the images precedes and controls the diffusion process. </p><p>The linear scale-space approach is shown to improve correlation values, which was anticipated since the image structure is flattened at coarser scales. There is however no increase in the number of accurate matches, since inaccurate features also tends to get higher correlation value at large scales. </p><p>The nonlinear isotropic scale-space (scalar dependent diffusion), or the edge- preservation, approach is proven to be an ill fit method for fingerprint image enhancement. This is due to the fact that the analysis of edges may be unreliable, since edge structure is often distorted in fingerprints affected by the template ageing problem. </p><p>The nonlinear anisotropic scale-space (tensor dependent diffusion), or coherence-enhancing, method does not give any overall improvements of the number of accurate matches. It is however shown that for a certain type of template ageing problem, where the deviating structure does not significantly affect the ridge orientation, the nonlinear anisotropic diffusion is able to accurately match correlation pairs that resulted in a false match before they were enhanced.</p>

The usage of automatic fingerprint identification systems as a means of identification and/or verification have increased substantially during the last couple of years. It is well known that small deviations may occur within a fingerprint over time, a problem referred to as template ageing. This problem, and other reasons for deviations between two images of the same fingerprint, complicates the identification/verification process, since distinct features may appear somewhat different in the two images that are matched. Commonly used to try and minimise this type of problem are different kinds of fingerprint image enhancement algorithms. This thesis tests different methods within the scale-space framework and evaluate their performance as fingerprint image enhancement methods. The methods tested within this thesis ranges from linear scale-space filtering, where no prior information about the images is known, to scalar and tensor driven diffusion where analysis of the images precedes and controls the diffusion process. The linear scale-space approach is shown to improve correlation values, which was anticipated since the image structure is flattened at coarser scales. There is however no increase in the number of accurate matches, since inaccurate features also tends to get higher correlation value at large scales. The nonlinear isotropic scale-space (scalar dependent diffusion), or the edge- preservation, approach is proven to be an ill fit method for fingerprint image enhancement. This is due to the fact that the analysis of edges may be unreliable, since edge structure is often distorted in fingerprints affected by the template ageing problem. The nonlinear anisotropic scale-space (tensor dependent diffusion), or coherence-enhancing, method does not give any overall improvements of the number of accurate matches. It is however shown that for a certain type of template ageing problem, where the deviating structure does not significantly affect the ridge orientation, the nonlinear anisotropic diffusion is able to accurately match correlation pairs that resulted in a false match before they were enhanced.

The shapes of naturally occurring objects characteristically involve spatial events occurring at many scales. This paper offers a symbolic approach to constructing a primitive shape description across scales for 2D binary (silhouette) shape images: grouping operations are performed over collections of tokens residing on a Scale-Space Blackboard. Two types of grouping operations are identified that, respectively: (1) aggregate edge primitives at one scale into edge primitives at a coarser scale and (2) group edge primitives into partial-region assertions, including curved- contours, primitive-corners, and bars. This approach avoids several drawbacks of numerical smoothing methods.

La première partie de la thèse introduit une méthode de déquantification de l'image qui améliore les propriétés statistiques du champ de gradient. Nous appliquons notre méthode à la détection de segments significatifs développée par Agnès Desolneux.La seconde partie présente une méthode d'évaluation du flou dans les images naturelles. Nous tirons profit du scale space morphologique pour permettre une évaluation aussi précise que possible de la quantité de flou local, sans connaissances sur le noyau.

No description available.