Leyza Elmeri Baldo Dorini

An improved ABC algorithm approach using SURF for face identification

Face recognition is being intensively studied in the areas of computer vision and pattern recognition. Working on still images with multiple faces is a challenging task due to the inherent characteristics of the images, the presence of blur, noise and occlusion, as well as variations of illumination, pose, rotation and scale. Besides being invariant to these factors, face recognition systems must be computationally efficient and robust. Swarm intelligence algorithms can be used for object recognition tasks. Based on this context, we propose a new approach using an improved ABC implementation and the interest point detector and descriptor SURF. To assess the robustness of our approach, we carry out experiments on images of several classes subject to different acquisition conditions.

Wire-mesh sensor, ultrasound and high-speed videometry applied for the characterization of horizontal gas-liquid slug flow

Gas-liquid flows occur in a broad range of industrial applications, for instance in chemical, petrochemical and nuclear industries. Correct understating of flow behavior is crucial for safe and optimized operation of equipments and processes. Thus, measurement of gas-liquid flow plays an important role. Many techniques have been proposed and applied to analyze two-phase flows so far. In this experimental research, data from a wire-mesh sensor, an ultrasound technique and high-speed camera are used to study two-phase slug flows in horizontal pipes. The experiments were performed in an experimental two-phase flow loop which comprises a horizontal acrylic pipe of 26 mm internal diameter and 9 m length. Water and air were used to produce the two-phase flow and their flow rates are separately controlled to produce different flow conditions. As a parameter of choice, translational velocity of air bubbles was determined by each of the techniques and comparatively evaluated along with a mechanistic flow model. Re...

Images Analysis of Horizontal Two-Phase Slug Flows

Multi-phase flow measurements are very common in industrial applications especially of the oil and gas industry. In order to study such pattern one can apply many different techniques such as capacitive probes, X-ray and gamma ray tomography, ultrasound transducers, wire-mesh sensors and high speed videometry. This article describes experimental study of water-air slug in horizontal pipes through non-intrusive image analysis technique. A flow test section comprising of a pipe of 26 mm internal diameter and 9 m long was employed to generate slug flows under controlled conditions. The behavior of the flow was studied using gas and liquid velocities between 0.3 m/s and 2 m/s with 6000 images (500×232 pixels) for each case. The algorithm comprises the automatic analysis of a sequence of frames in MatLab to measure flow characteristics such as Taylor bubble velocity and frequency applying morphological treatment. Finally, the parameters measured through the high speed videometry were compared with theoretical predictions showing that such method can be used to validate other types of sensors in experimental conditions.Copyright

A Samambaia de Barnsley.

Este trabalho objetiva apresentar as ideias matematicas principais da Samambaia de Barnsley, um fractal que recria uma imagem que assemelha-se a uma folha de samambaia da variedade Black Spleenwort e tem como base quatro transformacoes afins elementares.

Uma análise qualitativa de um método gradiente baseado em tensores para imagens coloridas

Este trabalho apresenta uma analise qualitativa de um metodo gradiente baseado em tensores para imagens coloridas. Este metodo consiste na representacao de cores por tensores e na utilizacao de medidas de similaridade entre tensores para mensurar a similaridade entre cores. O gradiente morfologico tensorial em cada pixel da imagem e definido como a maxima dissimilaridade calculada em sua vizinhanca. Sao analisados neste trabalho a forma como cores sao representadas por tensores, algumas medidas de similaridade entre tensores e o gradiente morfologico tensorial.

A mathematical analysis of the Tensorial Morphological Gradient approach

A qualitative analysis of the Tensorial Morphological Gradient approach is presented.Frobenius norm leads the Tensorial Morphological Gradient approach to the best results.Some (dis)similarity measures used in Tensorial Morphological Gradient are not well defined. This paper presents a mathematical analysis of the Tensorial Morphological Gradient, an approach to estimate color image gradients based on a color representation scheme that establishes a correspondence between different color models and tensors. We detail and provide the necessary theoretical explanations for six (dis)similarity measures used to compute the gradient considering the HSV color model and conclude that only one is pertinent to the Tensorial Morphological Gradient approach. The other measures present different types of limitations, including the computation of unbounded values, that disturb the results. The experimental results are consistent with the theoretical conclusions.

Bubble Identification Based on High Speed Videometry Data: Algorithm and Validation

The simultaneous flow of gas and liquid in a pipe is commonly found in several industrial activities, such as crude oil extraction and processing. In order to analyze this (two-phase) flow, many measurement techniques have been proposed, including X-ray, ultrasound, impedance and optical measurement. In this context, although the high speed videometry use is limited in practical cases, it is an important tool to validate other methods in experimental essays. Approaches based on image segmentation have already been considered to analyze gas-liquid flows along vertical pipes, but just a few have focused horizontal experiments, which are also widely found in many applications. This article describes a new technique developed to automatically measure the bubble volume through video analysis. The tests carried out considering horizontal air-water flow images yielded results with good correlation with known volume data, thus showing that the measurements are accurate enough to be considered for the validation of other technologies.