<p>A common problem when using background models to segment moving objects from video sequences is that objects cast shadow usually significantly differ from the background and therefore get detected as foreground. This causes several problems when extracting and labeling objects, such as object shape distortion and several objects merging together. The purpose of this thesis is to explore various possibilities to handle this problem.</p><p>Three methods for statistical background modeling are reviewed. All methods work on a per pixel basis, the first is based on approximating the median, the next on using Gaussian mixture models, and the last one is based on channel representation. It is concluded that all methods detect cast shadows as foreground.</p><p>A study of existing methods to handle cast shadows has been carried out in order to gain knowledge on the subject and get ideas. A common approach is to transform the RGB-color representation into a representation that separates color into intensity and chromatic components in order to determine whether or not newly sampled pixel-values are related to the background. The color spaces HSV, IHSL, CIELAB, YCbCr, and a color model proposed in the literature (Horprasert et al.) are discussed and compared for the purpose of shadow detection. It is concluded that Horprasert's color model is the most suitable for this purpose.</p><p>The thesis ends with a proposal of a method to combine background modeling using Gaussian mixture models with shadow detection using Horprasert's color model. It is concluded that, while not perfect, such a combination can be very helpful in segmenting objects and detecting their cast shadow.</p>

Multimedia retrieval systems are very important today with millions of content creators all over the world generating huge multimedia archives. Recent developments allows for content based image and video retrieval. These methods are often quite slow, especially if applied on a library of millions of media items. In this research a novel image retrieval method is proposed, which utilizes spatial metadata on images. By finding clusters of images based on their geographic location, the spatial metadata, and combining this information with existing content- based image retrieval algorithms, the proposed method enables efficient presentation of high quality image retrieval results to system users. Clustering methods considered include Vector Quantization, Vector Quantization LBG and DBSCAN. Clustering was performed on three different similarity measures; spatial metadata, histogram similarity or texture similarity. For histogram similarity there are many different distance metrics to use when comparing histograms. Euclidean, Quadratic Form and Earth Mover’s Distance was studied. As well as three different color spaces; RGB, HSV and CIE Lab.

Background Subtraction is one of the fundamental pre-processing steps in video processing. It helps to distinguish between foreground and background for any given image and thus has numerous applications including security, privacy, surveillance and traffic monitoring to name a few. Unfortunately, no single algorithm exists that can handle various challenges associated with background subtraction such as illumination changes, dynamic background, camera jitter etc. In this work, we propose a Multiple Background Model based Background Subtraction (MB2S) system, which is universal in nature and is robust against real life challenges associated with background subtraction. It creates multiple background models of the scene followed by both pixel and frame based binary classification on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Comprehensive evaluation of proposed approach on publicly available test sequences show superiority of our system over other state-of-the-art algorithms.

A common problem when using background models to segment moving objects from video sequences is that objects cast shadow usually significantly differ from the background and therefore get detected as foreground. This causes several problems when extracting and labeling objects, such as object shape distortion and several objects merging together. The purpose of this thesis is to explore various possibilities to handle this problem. Three methods for statistical background modeling are reviewed. All methods work on a per pixel basis, the first is based on approximating the median, the next on using Gaussian mixture models, and the last one is based on channel representation. It is concluded that all methods detect cast shadows as foreground. A study of existing methods to handle cast shadows has been carried out in order to gain knowledge on the subject and get ideas. A common approach is to transform the RGB-color representation into a representation that separates color into intensity and chromatic components in order to determine whether or not newly sampled pixel-values are related to the background. The color spaces HSV, IHSL, CIELAB, YCbCr, and a color model proposed in the literature (Horprasert et al.) are discussed and compared for the purpose of shadow detection. It is concluded that Horprasert's color model is the most suitable for this purpose. The thesis ends with a proposal of a method to combine background modeling using Gaussian mixture models with shadow detection using Horprasert's color model. It is concluded that, while not perfect, such a combination can be very helpful in segmenting objects and detecting their cast shadow.

Light microscopes are essential research tools in biology and medicine. Cell and tissue staining methods have improved immensely over the years and microscopes are now equipped with digital image acquisition capabilities. The image data produced require development of specialized analysis methods. This thesis presents digital image analysis methods for cell image data in 2D, 3D and time sequences. Stem cells have the capability to differentiate into specific cell types. The mechanism behind differentiation can be studied by tracking cells over time. This thesis presents a combined segmentation and tracking algorithm for time sequence images of neural stem cells.The method handles splitting and merging of cells and the results are similar to those achieved by manual tracking. Methods for detecting and localizing signals from fluorescence stained biomolecules are essential when studying how they function and interact. A study of Smad proteins, that serve as transcription factors by forming complexes and enter the cell nucleus, is included in the thesis. Confocal microscopy images of cell nuclei are delineated using gradient information, and Smad complexes are localized using a novel method for 3D signal detection. Thus, the localization of Smad complexes in relation to the nuclear membrane can be analyzed. A detailed comparison between the proposed and previous methods for detection of point-source signals is presented, showing that the proposed method has better resolving power and is more robust to noise. In this thesis, it is also shown how cell confluence can be measured by classification of wavelet based texture features. Monitoring cell confluence is valuable for optimization of cell culture parameters and cell harvest. The results obtained agree with visual observations and provide an efficient approach to monitor cell confluence and detect necrosis. Quantitative measurements on cells are important in both cytology and histology. The color provided by Pap (Papanicolaou) staining increases the available image information. The thesis explores different color spaces of Pap smear images from thyroid nodules, with the aim of finding the representation that maximizes detection of malignancies using color information in addition to quantitative morphological parameters. The presented methods provide useful tools for cell image analysis, but they can of course also be used for other image analysis applications.

Cette thèse traite de problèmes liés à la couleur. En particulier, on s’intéresse à des problématiques communes à la colorisation d’images, de vidéos et au rehaussement de contraste. Si on considère qu’une image est composée de deux informations complémentaires, une achromatique (sans couleur) et l’autre chromatique (en couleur), les applications étudiées consistent à traiter une de ces deux informations en préservant sa complémentaire. En colorisation, la difficulté est de calculer une image couleur en imposant son niveau de gris. Le rehaussement de contraste vise à modifier l’intensité d’une image en préservant sa teinte. Ces problématiques communes nous ont conduits à étudier formellement la géométrie de l’espace RGB. On a démontré que les espaces couleur classiques de la littérature pour résoudre ces types de problème conduisent à des erreurs. Un algorithme, appelé spécification luminance-teinte, qui calcule une couleur ayant une teinte et une luminance données est décrit dans cette thèse. L’extension de cette méthode à un cadre variationnel a été proposée. Ce modèle a été utilisé avec succès pour rehausser les images couleur, en utilisant des hypothèses connues sur le système visuel humain. Les méthodes de l’état-de-l’art pour la colorisation d’images se divisent en deux catégories. La première catégorie regroupe celles qui diffusent des points de couleurs posés par l’utilisateur pour obtenir une image colorisée (colorisation manuelle). La seconde est constituée de celles qui utilisent une image couleur de référence ou une base d’images couleur et transfèrent les couleurs de la référence sur l’image en niveaux de gris (colorisation basée exemple). Les deux types de méthodes ont leurs avantages et inconvénients. Dans cette thèse, on propose un modèle variationnel pour la colorisation basée exemple. Celui-ci est étendu en une méthode unifiant la colorisation manuelle et basée exemple. Enfin, nous décrivons des modèles variationnels qui colorisent des vidéos tout en permettent une interaction avec l’utilisateur. / This thesis deals with problems related to color. In particular, we are interested inproblems which arise in image and video colorization and contrast enhancement. When considering color images composed of two complementary information, oneachromatic (without color) and the other chromatic (in color), the applications studied in this thesis are based on the processing one of these information while preserving its complement. In colorization, the challenge is to compute a color image while constraining its gray-scale channel. Contrast enhancement aims to modify the intensity channel of an image while preserving its hue.These joined problems require to formally study the RGB space geometry. In this work, it has been shown that the classical color spaces of the literature designed to solve these classes of problems lead to errors. An novel algorithm, called luminance-hue specification, which computes a color with a given hue and luminance is described in this thesis. The extension of this method to a variational framework has been proposed. This model has been used successfully to enhance color images, using well-known assumptions about the human visual system. The state-of-the-art methods for image colorization fall into two categories. The first category includes those that diffuse color scribbles drawn by the user (manual colorization). The second consists of those that benefits from a reference color image or a base of reference images to transfer the colors from the reference to the grayscale image (exemplar-based colorization). Both approach have their advantages and drawbacks. In this thesis, we design a variational model for exemplar-based colorization which is extended to a method unifying the manual colorization and the exemplar-based one. Finally, we describe two variational models to colorize videos in interaction with the user.

L'analyse de texture a été largement étudiée dans la littérature et une grande variété de descripteurs de texture ont été proposés. Parmi ceux-ci, les motifs binaires locaux (LBP) occupent une part importante dans la plupart des applications d'imagerie couleur ou de reconnaissance de formes et sont particulièrement exploités dans les problèmes d'analyse de texture. Généralement, les images couleurs acquises sont représentées dans l'espace colorimétrique RGB. Cependant, il existe de nombreux espaces couleur pour la classification des textures, chacun ayant des propriétés spécifiques qui impactent les performances. Afin d'éviter la difficulté de choisir un espace pertinent, la stratégie multi-espace couleur permet d'utiliser simultanémentles propriétés de plusieurs espaces. Toutefois, cette stratégie conduit à augmenter le nombre d'attributs, notamment lorsqu'ils sont extraits de LBP appliqués aux images couleur. Ce travail de recherche est donc axé sur la réduction de la dimension de l'espace d'attributs générés à partir de motifs binaires locaux par des méthodes de sélection d'attributs. Dans ce cadre, nous considérons l'histogramme des LBP pour la représentation des textures couleur et proposons des approches conjointes de sélection de bins et d'histogrammes multi-espace pour la classification supervisée de textures. Les nombreuses expériences menées sur des bases de référence de texture couleur, démontrent que les approches proposées peuvent améliorer les performances en classification comparées à l'état de l'art. / Texture analysis has been extensively studied and a wide variety of description approaches have been proposed. Among them, Local Binary Pattern (LBP) takes an essential part of most of color image analysis and pattern recognition applications. Usually, devices acquire images and code them in the RBG color space. However, there are many color spaces for texture classification, each one having specific properties. In order to avoid the difficulty of choosing a relevant space, the multi color space strategy allows using the properties of several spaces simultaneously. However, this strategy leads to increase the number of features extracted from LBP applied to color images. This work is focused on the dimensionality reduction of LBP-based feature selection methods. In this framework, we consider the LBP histogram and bin selection approaches for supervised texture classification. Extensive experiments are conducted on several benchmark color texture databases. They demonstrate that the proposed approaches can improve the state-of-the-art results.

This thesis is focused on texture analysis methods. The project contains an overview of widely used methods. The main aim of the thesis is to develop a method for texture analysis of retinal images, which will be used for distinction of two patient groups, one with glaucoma eyes and one healthy. It is observed that glaucoma patients don´t have a texture on the eye ground. Preprocessing of the images is found by transfer of the image to different color spaces to achieve the best emphasis of the eye ground texture. Co-occurrence matrix is chosen for texture analysis of this data. The thesis contains detail description of the chosen solutions and feature discussion and the result is a list of features, which can be used for distinction between glaucoma and healthy eyes. The method is implemented in Matlab environment.

The diploma thesis is dividend into four parts. The first part describes basic terms in video technology (luminance, hue, diagrams CIE). The second part includes types of colour spaces RGB, HSV, CMY(K), YUV, YCbCr, YIQ. In the third and fourth part, these theoretical findings are used to propound laboratory observations. The laboratory observation processes the colour rendition of the colours in video technology. In the Matlab software, a user system environment was developed for operations with measured values. The software is capable of recalculating chromaticity coordinates between different colour spaces, to screen colours into diagrams CIE and to show the vectors of colours. The device used for measuring was Chromametr Konica Minolta CS-100A. A manual for the device was created. The laboratory observation was measured and processed in the form of a laboratory protocol.

Este trabalho apresenta uma nova metodologia para mapeamento no espaço de cor colorimétrico CIEXYZ, dos valores de triestímulo obtidos em um espaço de cor não colorimétrico definido pelas curvas de sensibilidade de um sensor eletrônico. A inovação do método proposto é realizar o mapeamento através de três redes neurais artificiais sendo que cada uma é especializada em mapear cores com um determinado triestímulo dominante. É feita a comparação dos resultados do mapeamento com vários trabalhos publicados sobre mapeamento de um espaço de cor em outro usando diversas técnicas. Os resultados mostram a eficiência do método proposto e permitem sua utilização em equipamentos para medir cores, incrementando sua precisão. / This work presents a new method for mapping a non colorimetric color space defined by the sensitivity curves of an electronic color sensor to the colorimetric color space CIEXYZ. The novelty of the proposed method is to perform the mapping by a set of three artificial neural networks, each one specialized in mapping colors with a specific dominant tristimulus. The results are compared with the ones obtained in published works about the mapping of color spaces, using several methods. The results of the method proposed in this work show that it is efficient and it can be used in equipments for measuring colors, improving its precision.