Dissertations / Theses on the topic 'Laplacian of Gaussian'

L'objectif de cette thèse est l'étude d'un descripteur d'images adapté à une grande variété d'applications. Nous cherchons à obtenir un descripteur robuste et discriminant, facile à adapter et peu coûteux en calcul et en mémoire.Nous définissons un nouveau descripteur, composé de valeurs du Laplacien à différentes échelles et de valeurs d'une transformée de Fourier radiale, calculées à partir d'une pyramide Gaussienne. Ce descripteur capture une information de forme multi-échelle autour d'un point de l'image. L'expérimentation a montré que malgré une taille mémoire réduite les performances en robustesse et en pouvoir discriminant de ce descripteur sont à la heuteur de l'état de l'art.Nous avons expérimenté ce descripteur avec trois types de tâches différentes.Le premier type de tâche est la mise en correspondance de points-clés avec des images transformées par rotation, changement d'échelle, floutage, codage JPEG, changement de point de vue, ou changement d'éclairage. Nous montrons que la performance de notre descripteur est au niveau des meilleurs descripteurs connus dans l'état de l'art. Le deuxième type de tâche est la détection de formes. Nous avons utilisé le descripteur pour la création de deux détecteurs de personnes, construits avec Adaboost. Comparé à un détecteur semblable construit avec des histogrammes de gradients (HOG) nos détecteurs sont très compétitifs tout en utilisant des descripteurs sensiblement plus compacts. Le dernier type de tâche est la détection de symétries de réflexion dans des images "du monde réel". Nous proposons une technique de détection d'axes potentiels de symétries en miroir. Avec cette tâche nous montrons que notre descripteur peut être genéralisé à des situations complexes. L'expérimentation montre que cette méthode est robuste et discriminante, tout en conservant un faible coût en calcul et en mémoire
In this thesis we explore a new image description method composed of a multi-scale vector of Laplacians of Gaussians, the Laplacian Profile, and a Radial Fourier Transform. This method captures shape information with different proportions around a point in the image. A Gaussian pyramid of scaled images is used for the extraction of the descriptor vectors. The aim of this new method is to provide image description that can be suitable for diverse applications. Adjustability as well as low computational and memory needs are as important as robustness and discrimination power. We created a method with the ability to capture the image signal efficiently with descriptor vectors of particularly small length compared to the state of the art. Experiments show that despite its small vector length, the new descriptor shows reasonable robustness and discrimination power that are competitive to the state of the art performance.We test our proposed image description method on three different visual tasks. The first task is keypoint matching for images that have undergone image transformations like rotation, scaling, blurring, JPEG compression, changes in viewpoint and changes in light. We show that against other methods from the state of the art, the proposed descriptor performs equivalently with a very small vector length. The second task is on pattern detection. We use the proposed descriptor to create two different Adaboost based detectors for people detection in images. Compared to a similar detector using Histograms of Oriented Gradients (HOG), the detectors with the proposed method show competitive performance using significantly smaller descriptor vectors. The last task is on reflection symmetry detection in real world images. We introduce a technique that exploits the proposed descriptor for detecting possible symmetry axes for the two reflecting parts of a mirror symmetric pattern. This technique introduces constraints and ideas of how to collect more efficiently the information that is important to identify reflection symmetry in images. With this task we show that the proposed descriptor can be generalized for rather complicated applications. The set of the experiments confirms the qualities of the proposed method of being easily adjustable and requires relatively low computational and storage requirements while remaining robust and discriminative

One important parameter of interest in remote sensing to date is yield variability. Proper understanding of yield variability provides insight on the geo-positional dependences of field yields and insight on zone management strategies. Estimating cotton yield and observing cotton yield variability has proven to be a challenging problem due to the complex fruiting behavior of cotton from reactions to environmental conditions. Current methods require expensive sensory equipment on large manned aircrafts and satellites. Other systems, such as cotton yield monitors, are often subject to error due to the collection of dust/trash on photo sensors. This study was aimed towards the development of a miniature unmanned aerial system that utilized a first-person view (FPV) color camera for measuring cotton yield variability. Outcomes of the study led to the development of a method for estimating cotton yield variability from images of experimental cotton plot field taken at harvest time in 2014. These plots were treated with nitrogen fertilizer at five different rates to insure variations in cotton yield across the field. The cotton yield estimates were based on the cotton unit coverage (CUC) observed as the cotton boll image signal density. The cotton boll signals were extracted via their diffusion potential in the image intensity space. This was robust to gradients in illumination caused by cloud coverage as well as fruiting positions in the field. These estimates were provided at a much higher spatial resolution (9.0 cm2) at comparable correlations (R2=0.74) with current expensive systems. This method could prove useful for the development of low cost automated systems for cotton yield estimation as well as yield estimation systems for other crops.
Master of Science

The aim of this project is to design an algorithm that identifies the Area of Interest (AOI) in ELISpot and FluoroSpot images. ELISpot and FluoroSpot are two varieties of a biochemical test used to analyze immune responses by quantifying the amount of cytokine secreted by cells. ELISpot and FluoroSpot images show a well that contains the cytokinesecreting cells which appear as scattered spots. Prior to counting the number of spots, it is required to detect the area in which to count the spots, i.e. the area delimited by the contour of the well. We propose to use the Circle Hough Transform together with filtering and the Laplacian of Gaussian edge detector in order to accurately detect such area. Furthermore we develop an outlier removal method that contributes to increase the robustness of the proposed detection method. Finally we compare our algorithm with another algorithm already in use. A Swedish biotech company called Mabtech has implemented an AOI identifier in the same field. Our proposed algorithm proves to be more robust and provides consistent results for all the images in the dataset.

The aim of the thesis is detection of a known object in series of pictures. Detection is divided into two methods. First method is based on edge and color detection and comparison. Edge detection is based on detection using both Gradient and Laplacian, so on the first-order and the second-order derivative. Sobel operators were used as well as Laplacian of gaussian method. Thresholding is also used as well as autothreshold calculation. There are two variants of color detection considered in the thesis, direct color comparison and detection based on interest color search. The second part of the thesis is based on interested point detection using a modified SURF method to detect a known object in series of pictures.

This thesis addresses statistical estimation and testing of signals over a graph when measurements are noisy and high-dimensional. Graph structured patterns appear in applications as diverse as sensor networks, virology in human networks, congestion in internet routers, and advertising in social networks. We will develop asymptotic guarantees of the performance of statistical estimators and tests, by stating conditions for consistency by properties of the graph (e.g. graph spectra). The goal of this thesis is to demonstrate theoretically that by exploiting the graph structure one can achieve statistical consistency in extremely noisy conditions. We begin with the study of a projection estimator called Laplacian eigenmaps, and find that eigenvalue concentration plays a central role in the ability to estimate graph structured patterns. We continue with the study of the edge lasso, a least squares procedure with total variation penalty, and determine combinatorial conditions under which changepoints (edges across which the underlying signal changes) on the graph are recovered. We will shift focus to testing for anomalous activations in the graph, using the scan statistic relaxations, the spectral scan statistic and the graph ellipsoid scan statistic. We will also show how one can form a decomposition of the graph from a spanning tree which will lead to a test for activity in the graph. This will lead to the construction of a spanning tree wavelet basis, which can be used to localize activations on the graph.

Matrix function approximation is a current focus of worldwide interest and finds application in a variety of areas of applied mathematics and statistics. In this thesis we focus on the approximation of A..=2b, where A 2 Rnn is a large, sparse symmetric positive definite matrix and b 2 Rn is a vector. In particular, we will focus on matrix function techniques for sampling from Gaussian Markov random fields in applied statistics and the solution of fractional-in-space partial differential equations. Gaussian Markov random fields (GMRFs) are multivariate normal random variables characterised by a sparse precision (inverse covariance) matrix. GMRFs are popular models in computational spatial statistics as the sparse structure can be exploited, typically through the use of the sparse Cholesky decomposition, to construct fast sampling methods. It is well known, however, that for sufficiently large problems, iterative methods for solving linear systems outperform direct methods. Fractional-in-space partial differential equations arise in models of processes undergoing anomalous diffusion. Unfortunately, as the fractional Laplacian is a non-local operator, numerical methods based on the direct discretisation of these equations typically requires the solution of dense linear systems, which is impractical for fine discretisations. In this thesis, novel applications of Krylov subspace approximations to matrix functions for both of these problems are investigated. Matrix functions arise when sampling from a GMRF by noting that the Cholesky decomposition A = LLT is, essentially, a `square root' of the precision matrix A. Therefore, we can replace the usual sampling method, which forms x = L..T z, with x = A..1=2z, where z is a vector of independent and identically distributed standard normal random variables. Similarly, the matrix transfer technique can be used to build solutions to the fractional Poisson equation of the form n = A..=2b, where A is the finite difference approximation to the Laplacian. Hence both applications require the approximation of f(A)b, where f(t) = t..=2 and A is sparse. In this thesis we will compare the Lanczos approximation, the shift-and-invert Lanczos approximation, the extended Krylov subspace method, rational approximations and the restarted Lanczos approximation for approximating matrix functions of this form. A number of new and novel results are presented in this thesis. Firstly, we prove the convergence of the matrix transfer technique for the solution of the fractional Poisson equation and we give conditions by which the finite difference discretisation can be replaced by other methods for discretising the Laplacian. We then investigate a number of methods for approximating matrix functions of the form A..=2b and investigate stopping criteria for these methods. In particular, we derive a new method for restarting the Lanczos approximation to f(A)b. We then apply these techniques to the problem of sampling from a GMRF and construct a full suite of methods for sampling conditioned on linear constraints and approximating the likelihood. Finally, we consider the problem of sampling from a generalised Matern random field, which combines our techniques for solving fractional-in-space partial differential equations with our method for sampling from GMRFs.

In 3D modelling software, deformations are used to add, to remove, or to modify geometric features of existing 3D models to create new models with similar but slightly different details. Traditional techniques for deforming virtual 3D models require users to explicitly define control points and regions of interest (ROIs), and to define precisely how to deform ROIs using control points. The awkwardness of defining these factors in traditional 3D modelling software makes it difficult for people with limited experience of 3D modelling to deform existing 3D models as they expect. As applications which require virtual 3D model processing become more and more widespread, it becomes increasingly desirable to lower the "difficulty of use" threshold of 3D model deformations for users. This thesis argues that the user experience, in terms of intuitiveness and ease of use, of a user interface for deforming virtual 3D models, can be greatly enhanced by employing sketch-based 3D model deformation techniques, which require the minimal quantities of interactions, while keeping the plausibility of the results of deformations as well as the responsiveness of the algorithms, based on modern home grade computing devices. A prototype system for sketch-based 3D model deformations is developed and implemented to support this hypothesis, which allows the user to perform a deformation using a single deforming stroke, eliminating the need to explicitly select control points, the ROI and the deforming operation. GPU based accelerations have been employed to optimise the runtime performance of the system, so that the system is responsive enough for real-time interactions. The studies of the runtime performance and the usability of the prototype system are conducted to provide evidence to support the hypothesis.

Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.

Les etudes sur la vision et la segmentation en traitement d'images numeriques trouvent un interet commun dans l'utilisation du laplacien d'une gaussienne. Le filtre lgfti, construit par integration de la transformee de fourier du laplacien d'une gaussienne dans l'espace des echelles, complete l'arsenal des filtrages du type laplacien. Le filtre lgfti offre des possibilites puissantes, car selon les bornes d'integration choisies on peut selectionner differemment les frequences utiles; il est donc plus adapte que le laplacien d'une gaussienne a la segmentation primitive. Nous avons montre qu'il etait necessaire d'avoir des images de reference pour effectuer les comparaisons. Les bases d'un tel ensemble de reference sont proposees. L'automatisation a montre l'importance d'analyser la sensibilite d'une methode a ses parametres. Nous suggerons donc un schema d'analyse des methodes de segmentation, en fonction de leurs parametres et de leurs resultats

CoordenaÃÃo de AperfeiÃoamento de Pessoal de NÃvel Superior
Nesta dissertacÃo, estudaremos algumas propriedades das SuperfÃcies de Weingarten lineares em R3. Estas, sÃo imersÃes de uma superfÃcie abstrata S em R3, para as quais existem trÃs nÃmeros reais a, b e c, nÃo todos nulos, satisfazendo 2aH(P) + bK(P) = c para todo P 2 S, sendo H a curvatura mÃdia e K a curvatura Gaussiana de S, respectivamente. Daremos uma estimativa para a altura de uma SuperfÃcie de Weingaten Linear ElÃptica (a2 + bc > 0), compacta, em relacÃo a um plano. TambÃm daremos uma estimativa para 2aH + bK em uma superfÃcie de Weingarten linear compacta e em um grÃfico compacto com bordo planar convexo. TambÃm, vamos provar o seguinte resultado: Seja S um disco topolÃgico fechado e : S −! R3 uma imersÃo linear de Weingarten satisfazendo a2+bc >0. Se a imagem do bordo de S, (@S), à uma linha de curvatura entÃo (S) està contido em um plano ou numa esfera. Para provar este resultado, precisaremos do cÃlculo dos laplacianos de duas funcÃes, em relacÃo a uma mÃtrica Riemanniana especial (ProposicÃo 2.2) .

The focus of this thesis is on facial biometrics; specifically in the problems of face detection and face recognition. Despite intensive research over the last 20 years, the technology is not foolproof, which is why we do not see use of face recognition systems in critical sectors such as banking. In this thesis, we focus on three sub-problems in these two areas of research. Firstly, we propose methods to improve the speed-accuracy trade-off of the state-of-the-art face detector. Secondly, we consider a problem that is often ignored in the literature: to decrease the training time of the detectors. We propose two techniques to this end. Thirdly, we present a detailed large-scale study on self-updating face recognition systems in an attempt to answer if continuously changing facial appearance can be learnt automatically.
L'objectiu d'aquesta tesi és sobre biometria facial, específicament en els problemes de detecció de rostres i reconeixement facial. Malgrat la intensa recerca durant els últims 20 anys, la tecnologia no és infalible, de manera que no veiem l'ús dels sistemes de reconeixement de rostres en sectors crítics com la banca. En aquesta tesi, ens centrem en tres sub-problemes en aquestes dues àrees de recerca. En primer lloc, es proposa mètodes per millorar l'equilibri entre la precisió i la velocitat del detector de cares d'última generació. En segon lloc, considerem un problema que sovint s'ignora en la literatura: disminuir el temps de formació dels detectors. Es proposen dues tècniques per a aquest fi. En tercer lloc, es presenta un estudi detallat a gran escala sobre l'auto-actualització dels sistemes de reconeixement facial en un intent de respondre si el canvi constant de l'aparença facial es pot aprendre de forma automàtica.

Computational imaging has been playing an important role in understanding and analysing the captured images. Both image segmentation and restoration has been in-tegral parts of computational imaging. The studies performed in this thesis has been focussed toward developing novel algorithms for image segmentation and restoration. Study related to usage of Morozov Discrepancy Principle in Di use Optical Imaging was also presented here to show that hyper parameter selection could be performed with ease. The Laplacian of Gaussian (LoG) and Canny operators use Gaussian smoothing be-fore applying the derivative operator for edge detection in real images. The LoG kernel was based on second derivative and is highly sensitive to noise when compared to the Canny edge detector. A new edge detection kernel, called as Helmholtz of Gaussian (HoG), which provides higher di suavity is developed in this thesis and it was shown that it is more robust to noise. The formulation of the developed HoG kernel is similar to LoG. It was also shown both theoretically and experimentally that LoG is a special case of HoG. This kernel when used as an edge detector exhibited superior performance compared to LoG, Canny and wavelet based edge detector for the standard test cases both in one- and two-dimensions. The linear inverse problem encountered in restoration of blurred noisy images is typically solved via Tikhonov minimization. The outcome (restored image) of such min-imitation is highly dependent on the choice of regularization parameter. In the absence of prior information about the noise levels in the blurred image, ending this regular-inaction/hyper parameter in an automated way becomes extremely challenging. The available methods like Generalized Cross Validation (GCV) may not yield optimal re-salts in all cases. A novel method that relies on minimal residual method for ending the regularization parameter automatically was proposed here and was systematically compared with the GCV method. It was shown that the proposed method performance was superior to the GCV method in providing high quality restored images in cases where the noise levels are high Di use optical tomography uses near infrared (NIR) light as the probing media to recover the distributions of tissue optical properties with an ability to provide functional information of the tissue under investigation. As NIR light propagation in the tissue is dominated by scattering, the image reconstruction problem (inverse problem) is non-linear and ill-posed, requiring usage of advanced computational methods to compensate this. An automated method for selection of regularization/hyper parameter that incorporates Morozov discrepancy principle(MDP) into the Tikhonov method was proposed and shown to be a promising method for the dynamic Di use Optical Tomography.

Traditionally, source coding (data compression) and channel coding (error protection) are performed separately and sequentially, resulting in what we call a tandem (separate) coding system. In practical implementations, however, tandem coding might involve a large delay and a high coding/decoding complexity, since one needs to remove the redundancy in the source coding part and then insert certain redundancy in the channel coding part. On the other hand, joint source-channel coding (JSCC), which coordinates source and channel coding or combines them into a single step, may offer substantial improvements over the tandem coding approach. This thesis deals with the fundamental Shannon-theoretic limits for a variety of communication systems via JSCC. More specifically, we investigate the reliability function (which is the largest rate at which the coding probability of error vanishes exponentially with increasing blocklength) for JSCC for the following discrete-time communication systems: (i) discrete memoryless systems; (ii) discrete memoryless systems with perfect channel feedback; (iii) discrete memoryless systems with source side information; (iv) discrete systems with Markovian memory; (v) continuous-valued (particularly Gaussian) memoryless systems; (vi) discrete asymmetric 2-user source-channel systems. For the above systems, we establish upper and lower bounds for the JSCC reliability function and we analytically compute these bounds. The conditions for which the upper and lower bounds coincide are also provided. We show that the conditions are satisfied for a large class of source-channel systems, and hence exactly determine the reliability function. We next provide a systematic comparison between the JSCC reliability function and the tandem coding reliability function (the reliability function resulting from separate source and channel coding). We show that the JSCC reliability function is substantially larger than the tandem coding reliability function for most cases. In particular, the JSCC reliability function is close to twice as large as the tandem coding reliability function for many source-channel pairs. This exponent gain provides a theoretical underpinning and justification for JSCC design as opposed to the widely used tandem coding method, since JSCC will yield a faster exponential rate of decay for the system error probability and thus provides substantial reductions in complexity and coding/decoding delay for real-world communication systems.
Thesis (Ph.D, Mathematics & Statistics) -- Queen's University, 2008-05-13 22:31:56.425