The master thesis deals with the topic of detecting faces in digital images. There are generally described and classified the most frequently used methods and discussed their advantages and disadvantages. More detailed is described skin color detection, eye and mouth detection and are teoretically described machine learning algorithms and detection based on Haar-classifiers. The work aims to implementation of these methods in the OpenCV library, it refers to practical application of them a finally compares different provided trained files.

Dans cette thèse, une nouvelle représentation des images couleur basée sur une généralisation du signal analytique est introduite. En utilisant l'analogie entre les conditions de Cauchy-Riemann, qui définissent le caractère holomorphe d'une fonction, et l'équation de Dirac dans l'algèbre de Clifford R_{5,0}, un système d'équations dont la solution est le signal monogène couleur est obtenu. Ce signal est notamment basé sur des noyaux de Riesz ainsi que de Poisson 2D, et une représentation polaire, basée sur un produit géométrique, peut lui être associée. Les applications envisagées reposent majoritairement sur cette représentation polaire et sur les informations de couleur et de structures locales s'y rattachant. Des problématiques liées au flot optique couleur, à la segmentation couleur multi-échelle, au suivi d'objets couleur et à la détection de points d'intérêt sont abordées. En ce qui concerne le flot optique, nous nous intéressons à l'extraction du mouvement d'objets d'une certaine couleur en remplaçant la contrainte de conservation de l'intensité par une contrainte de conservation d'angles. Pour la segmentation, une méthode de détection de contours basée sur de la géométrie différentielle et plus particulièrement sur la première forme fondamentale d'une surface, est proposée afin de déterminer les contours d'objets d'une couleur choisie. Pour le suivi d'objets, nous définissons un nouveau critère de similarité utilisant le produit géométrique que nous insérons dans un filtrage particulaire. Enfin, nous resituons la définition du détecteur de Harris dans le cadre de la géométrie différentielle en faisant le lien entre ce dernier et une version "relaxée" du discriminant du polynôme caractéristique de la première forme fondamentale. Ensuite nous proposons une nouvelle version multi-échelle de ce détecteur en traitant le paramètre d'échelle comme une variable d'une variété de dimension 3. / In this thesis, a novel framework for color image processing is introduced based on the generalization of the analytic signal. Using the analogy between the Cauchy-Riemann conditions and the Dirac equation in the Clifford algebra R_{5,0}, a system of equations which leads to the color monogenic signal is obtained. This latter is based on the Riesz and 2D Poisson kernels, and a polar representation based on the geometric product can be associated to this signal. Some applications using color and local structure information provided by the polar representation are presented. Namely, color optical flow, color segmentation, color object tracking and points of interest are developed. Extraction of optical flow in a chosen color is obtained by replacing the brightness constancy assumption by an angle constancy. Edge detection is based on the first fundamental form from differential geometry in order to segment object in a predefined color. Object tracking application uses a new similarity criterion defined by geometric product of block of vectors. This latter is viewed as the likelyhood measure of a particle filter. Last part of the thesis is devoted to the definition of the Harris detector in the framework of differential geometry and a link between this definition and a relaxed version of the characteristic polynomial discriminant of the first fundamental form is given. In this context, a new scale-space detector is provided as the result of handling the scale parameter as a variable in a 3-manifold.

With the improvement of multimedia technologies such as broadband-enabled HDTV, video on demand and internet TV, the computer and the TV are merging to become a single device. Moreover the previously cited technologies as well as DVD or Blu-ray can provide menu navigation and interactive content. The growing interest in video conferencing led to the integration of the webcam in different devices such as laptop, cell phones and even the TV set. Our approach is to directly use an embedded webcam to remotely control a TV set using hand gestures. Using specific gestures, a user is able to control the TV. A dedicated interface can then be used to select a TV channel, adjust volume or browse videos from an online streaming server. This approach leads to several challenges. The first is the use of a simple webcam which leads to a vision based system. From the single webcam, we need to recognize the hand and identify its gesture or trajectory. A TV set is usually installed in a living room which implies constraints such as a potentially moving background and luminance change. These issues will be further discussed as well as the methods developed to resolve them. Video browsing is one example of the use of gesture recognition. To illustrate another application, we developed a simple game controlled by hand gestures. The emergence of 3D TVs is allowing the development of 3D video conferencing. Therefore we also consider the use of a stereo camera to recognize hand gesture.

This paper deals with study of human movement and using that in identification. In the first part of my work are explained characteristics of human movement and factors which take effect on these characteristics. Practical part is dealing with design of program which is solving mentioned problems. The input of program is created by video sequence with lateral movement of human. The program is finding coordinates of lower limbs joints. From this coordinates are created locomotion characteristics used for human identification. Matching of time behaviors is based on correlation.

The thesis deals with traffic sign detection and recongnition in the urban environment and outside the town. A precondition for implementation of the system is built-in camera, usually in a car rear-view mirror. The camera scans the scene before the vehicle. The image data are transfered to the connected PC, where the data are transformation to information and evalutations. If the sign was detected the system is visually warned the driver. For a successful goal is divided into four separate blocks. The first part is the preparing of the image data. There are color segmentation with knowledge of color combination traffic signs in Czech Republic. Second part is deals with shape detection in segmentation image. Part number three is deals with recognition of inner pictogram and its finding in the image database. The final part is the visual output of displaying founded traffic signs. The thesis has been prepader so as to ensure detection of all relevant traffic signs in three basic color combinations according to existing by Decree of Ministry of Transport of Czech Republic. The result is the source code for the program MATLAB. .