Automatic visual dictionary generation through Optimum-Path Forest clustering

Image categorization by means of bag of visual words has received increasing attention by the image processing and vision communities in the last years. In these approaches, each image is represented by invariant points of interest which are mapped to a Hilbert Space representing a visual dictionary which aims at comprising the most discriminative features in a set of images. Notwithstanding, the main problem of such approaches is to find a compact and representative dictionary. Finding such representative dictionary automatically with no user intervention is an even more difficult task. In this paper, we propose a method to automatically find such dictionary by employing a recent developed graph-based clustering algorithm called Optimum-Path Forest, which does not make any assumption about the visual dictionary's size and is more efficient and effective than the state-of-the-art techniques used for dictionary generation. © 2012 IEEE.

Automatic landslide recognition through Optimum-Path Forest

In this paper we shed light over the problem of landslide automatic recognition using supervised classification, and we also introduced the OPF classifier in this context. We employed two images acquired from Geoeye-MS satellite at March-2010 in the northwest (high steep areas) and north sides (pipeline area) covering the area of Duque de Caxias city, Rio de Janeiro State, Brazil. The landslide recognition rate has been assessed through a cross-validation with 10 runnings. In regard to the classifiers, we have used OPF against SVM with Radial Basis Function for kernel mapping and a Bayesian classifier. We can conclude that OPF, Bayes and SVM achieved high recognition rates, being OPF the fastest approach. © 2012 IEEE.

Automatic fiscal stabilizers

Includes bibliography

Computer techniques towards the automatic characterization of graphite particles in metallographic images of industrial materials

The automatic characterization of particles in metallographic images has been paramount, mainly because of the importance of quantifying such microstructures in order to assess the mechanical properties of materials common used in industry. This automated characterization may avoid problems related with fatigue and possible measurement errors. In this paper, computer techniques are used and assessed towards the accomplishment of this crucial industrial goal in an efficient and robust manner. Hence, the use of the most actively pursued machine learning classification techniques. In particularity, Support Vector Machine, Bayesian and Optimum-Path Forest based classifiers, and also the Otsu's method, which is commonly used in computer imaging to binarize automatically simply images and used here to demonstrated the need for more complex methods, are evaluated in the characterization of graphite particles in metallographic images. The statistical based analysis performed confirmed that these computer techniques are efficient solutions to accomplish the aimed characterization. Additionally, the Optimum-Path Forest based classifier demonstrated an overall superior performance, both in terms of accuracy and speed. © 2012 Elsevier Ltd. All rights reserved.

Fault current limiter using transformer and modular device of YBCO coated conductor

In this work, we report on the evaluation of a superconducting fault current limiter (SFCL). It is consisted of a modular superconducting device combined with a short-circuited transformer with a primary copper winding connected in series to the power line and the secondary side short-circuited by the superconducting device. The basic idea is adding a magnetic component to contribute to the current limitation by the impedance reflected to the line after transition of the superconducting device. The evaluation tests were performed with a prospective current up to 2 kA, with the short-circuited transformer of 2.5 kVA, 220 V/660 V connected to a test facility of 100 kVA power capacity. The resistive SFCL using a modular superconducting device was tested without degradation for a prospective fault current of 1.8 kA, achieving the limiting factor 2.78; the voltage achieved 282 V corresponding to an electric field of 11 V/m. The test performed with the combined SFCL (xsuperconducting device + transformer) using series and toroidal transformers showed current limiting factor of 3.1 and 2 times, respectively. The test results of the combined SFCL with short-circuited transformer showed undesirable influence of the transformer impedance, resulting in reduction of the fault current level. © 2002-2011 IEEE.

Wavelets in the computed evaluation of mammographic accreditation phantom images

This paper presents a novel approach to the computed assessment of a mammographic phantom device. The approach shown here is fully automated and is based on the automatic selection of the region of interest, in the use of the discrete wavelet transform (DWT) and morphological operators to assess the quality of the American College of Radiology (ACR) mammographic phantom images. The algorithms developed here have succesfully scored 30 images obtained with different combinations of voltage applied to the tube and exposure and could notice the differences in the radiographs due to the different level of exposure to radiation. © 2013 Springer-Verlag.

Use of algorithms for semi-automatic quantification of pulmonary fibrosis and emphysema

Obtaining a semi-automatic quantification of pathologies found in the lung, through images of high resolution computed tomography (HRCT), is of great importance to aid in medical diagnosis. Paraccocidioidomycosis (PCM) is a systemic disease that affects the lung and even after effective treatment leaves sequels such as pulmonary fibrosis and emphysema. It is very important to the area of tropical diseases that the lung injury be quantified more accurately. In this stud, we propose the development of algorithms in computational environment Matlab® able to objectively quantify lung diseases such as fibrosis and emphysema. The program consists in selecting the region of interest (ROI), and through the use of density masks and filters, obtaining the lesion area quantification in relation to the healthy area of the lung. The proposed method was tested on 15 exams of HRCT of patients with confirmed PCM. To prove the validity and effectiveness of the method, we used a virtual phantom, also developed in this research. © 2013 Springer-Verlag.

Soil erodibility assessment in a pasture and forest remnant using the inderbitzen device

Brazil has the largest cattle herd in the world with approximately 200 million head. An important feature of the Brazilian cattle industry is that most of its herd is raised on pasture, which constitutes one of the most economical and practical ways to produce and provide food for cattle. However, this production model is mishandled and can lead to soil degradation. Maintaining soil quality is essential for the conservation of natural ecosystems and the areas of production, thus soil quality improves the conditions for biogeochemical cycles. In this context, the objective of this study was to develop a device for testing the Inderbitzen way of assessing soil erodibility in two situations of usage and occupation. Therefore, one area was used as a sample collection occupied by grazing and the other as a forest fragment; both located in the city of Sorocaba in Sao Paulo State, Brazil. Thus, we concluded that the proposed device - the Inderbitzen - proved capable of assessing soil erodibility of the pasture and remnant forest. Accordingly, there was a tendency for a smaller loss of forest soils in the remnant when compared to the degraded pasture. The greatest resistance of the soil erosion in the forest remnant may be associated with the amount of organic matter released by the forest litter in all its diversity, influencing the quality of the structure of aggregates. © 2013 WIT Press.

Automatic microstructural characterization and classification using artificial intelligence techniques on ultrasound signals

Secondary phases such as Laves and carbides are formed during the final solidification stages of nickel based superalloy coatings deposited during the gas tungsten arc welding cold wire process. However, when aged at high temperatures, other phases can precipitate in the microstructure, like the γ″ and δ phases. This work presents a new application and evaluation of artificial intelligent techniques to classify (the background echo and backscattered) ultrasound signals in order to characterize the microstructure of a Ni-based alloy thermally aged at 650 and 950 °C for 10, 100 and 200 h. The background echo and backscattered ultrasound signals were acquired using transducers with frequencies of 4 and 5 MHz. Thus with the use of features extraction techniques, i.e.; detrended fluctuation analysis and the Hurst method, the accuracy and speed in the classification of the secondary phases from ultrasound signals could be studied. The classifiers under study were the recent optimum-path forest (OPF) and the more traditional support vector machines and Bayesian. The experimental results revealed that the OPF classifier was the fastest and most reliable. In addition, the OPF classifier revealed to be a valid and adequate tool for microstructure characterization through ultrasound signals classification due to its speed, sensitivity, accuracy and reliability. © 2013 Elsevier B.V. All rights reserved.

Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Modelagem numérica do escoamento em válvulas automáticas de compressores pelo Método da Fronteira Imersa

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Avaliação das alterações radiográficas após tratamento endodôntico de dentes com lesão periapical empregando dois programas de interpretação de imagens

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Proposta de uma máquina para processo de abrasão baseado na combinação de algumas características da lapidação e retificação

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Retificador entrelaçado boost, no modo de condução descontínua, com técnica de correção da corrente de entrada e elevado fator de potência, para aplicação em sistema trólebus

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento de um sistema de posicionamento automático para painéis fotovoltaicos

Pós-graduação em Agronomia (Energia na Agricultura) - FCA