The goal of this thesis is to build an interactive tool for analyzing the quality of a digital image and predicting the scale at which it may be published. Since edges are present almost everywhere in most digital images, we use a mathematical edge model as the basis of analysis. In particular, we are interested in the luminance and chromaticity behavior at edge boundaries. We use this model to develop PhETA — Photograph Edge Transition Analyzer — an interactive tool that allows novice users to view and understand the results gained from this analysis in a clear and simple manner. / Master of Science

This diploma thesis deals with different ways of grayscale image processing of veins in a finger of human hand. The process consists of vein structure extraction, and then this structure is compared with collection of provided snapshots. First of all we introduced problem of biometric systems and image processing. There are presented also some commercial solutions from the same field. Within the detailed description of image processing we suggested different modifications in adaptive thresholding algorithm, feature extraction, which continues into comparison of vein structures. Thesis is closed by testing and final review.

Orientador: Paulo Roberto Gardel Kurka / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-08-07T00:20:23Z (GMT). No. of bitstreams: 1 Rudek_Marcelo_D.pdf: 2300973 bytes, checksum: e02ac88751e4619e52590e1ee9fb82b5 (MD5) Previous issue date: 2006 / Resumo: O trabalho apresenta um método baseado em imagens digitais para a determinação da posição espacial e do volume ocupado por um sólido. O objetivo é conhecer estes parâmetros sem a necessidade da reconstrução tridimensional completa do objeto. A aplicação da técnica proposta é baseada nas projeções da imagem do objeto a ser medido. O processo se baseia na utilização de uma caixa de contorno (bounding box) que pode ser ajustada sobre uma região de interesse na imagem. A posição desta caixa de contorno descreve a orientação espacial do objeto, e as suas dimensões espaciais definem o volume aproximado do sólido. O trabalho propõe um método para ajustar as arestas da caixa de contorno sobre as bordas do objeto, usando como referencial os pontos de fuga que formam os vértices da caixa de contorno. Os vértices formam um conjunto reduzido de pontos e a reconstrução tridimensional destes pontos permite definir um polígono retangular no espaço que representa as informações métricas do objeto real. O contexto do trabalho se situa no campo da visão computacional e processamento de imagens utilizando um conjunto de ferramentas aplicadas à teoria de reconstrução 3D. São apresentados os resultados obtidos da aplicação do método para imagens reais, bem como é descrita uma aplicação do método em um ambiente de manufatura integrada / Abstract: This work presents a method based on digital images to determine the spatial position and volume occupied by a solid. The objective is to find these parameters without a complete tri­dimensional reconstruction of the object. The application of this technique is based on the image projections of a solid target. The process is based on a contour bounding box that is adjusted around a region of interest. The box position describes the object spatial orientation and its spatial dimensions can define the approximated volume. The work proposes a method to adjust the contour box lines on the object borders using vanishing points as reference to form each vertex of the bounding box. The vertices form a reduced set of points and the 3D reconstruction of such points can define a rectangular polygon in the space representing the metric information about the real object. The work is within the context of computer vision and image processing by the use of a set of 3D reconstruction tools. Results obtained of the application of this method to real images are presented, as well as an application to an integrated manufacturing process / Doutorado / Projeto Mecanico / Doutor em Engenharia Mecânica

The thesis introduces methods used for an ellipse detection. Each method is theoretically described in current subsection. The description includes methods like Hough transform, Random Hough transform, RANSAC, Genetic Algorithm and improvements with optimalization. Further there are described modifications of current procedures in the thesis to reach better results. Next to the last chapter represents testing parameters of speed, quality and accuracy of implemented algorithms. There is a conclusion of testing and a result discussion at the end.

This thesis is dedicated to techniques for motion detection in video sequences. There is summary of several possible approaches to solve this matter in theoretical and practical point of view. Principles of motion detection based on difference between frames are discussed in details. Great attention is made for image description by new method Local Binary Patterns which allows creating of incredibly fast and accurate motion detector. Vital part of this thesis is application for monitoring and testing motion algorithms on video sequences in different environments. Results of measuring enables to determine best approaches for concrete place and reader might find it useful in case of designing his own motion detectors.