Alexandre Gonçalves Silva

Alexandre Gonçalves Silva
Federal University of Santa Catarina | UFSC · Departamento de Informática e Estatística

Ph.D.

About

55
Publications
10,802
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
165
Citations
Additional affiliations
July 2004 - August 2014
Universidade do Estado de Santa Catarina
Position
  • Professor
February 1996 - November 2009
University of Campinas
Position
  • Student

Publications

Publications (55)
Article
Atherosclerotic cardiovascular disease is the leading cause of death in the world. Ultrasound evaluation of carotid intima-media thickness (cIMT) is a fast and non-invasive approach widely used to estimate cardiovascular risk. However, evaluation of the faint carotid intima sublayer thickness (cIT) is reported to be a better marker of atheroscleros...
Article
Full-text available
Objetivo: Este trabalho apresenta uma revisão de modelos para avaliação de massa corporal e de métodos de visão computacional aplicados à antropometria. A ideia é sugerir um sistema, baseado em fotografia, para aproximação dos atributos usados nessas fórmulas (como o IMC), aplicado à monitoração permanente e automática de indicadores nutricionais e...
Conference Paper
Full-text available
Atherosclerosis is the leading cause of death in the world. It is a cardiovascular disease characterized by the accumulation of inflammatory cells and lipids inside the artery walls. In Brazil, more than 30% of all deaths are due to cardiovascular diseases. The carotid intima-media thickness, obtained from ultrasoundimages,maybeanearlyestimateofathe...
Article
Full-text available
Introduction A new method for segmenting and quantifying the macular area based on morphological alternating sequential filtering (ASF) is proposed. Previous studies show that persons with diabetes present alterations in the foveal avascular zone (FAZ) prior to the appearance of retinopathy. Thus, a proper characterization of FAZ using a method of...
Conference Paper
Full-text available
Resumo: Uma imagem em níveis de cinza pode ser interpretada como uma superfície topográfica, na qual vales são regiões relativamente mais escuras, e montanhas, regiões mais claras em relação à vizinhança. A aplicação de filtros conexos por atributos crescentes, ao reduzir os topos deste relevo, pode remover a ocorrência de máximos regionais. Um val...
Conference Paper
Full-text available
In this work, a vision system has been developed using a frontal camera to monitor the driver, enabling to recognize the use of a cell phone while driving. It is estimated that 80% of car crashes and 65% of near collisions involved drivers who were inattentive in traffic for three seconds before the event. Five videos in real environments were gene...
Article
Full-text available
Bar codes are applied in several tasks to the automation of data acquisition through electronic devices. Withal, markers are used by applications of Augmented Reality and Mobile Robotics. This paper is a survey of applications made in both areas and proposes the development of a marker that incorporates the features of a barcode in two dimensions....
Article
Full-text available
In this work three methods are evaluated to recognize images of products: bag of visual words using artificial descriptors (BOVW), convolutional neural networks(CNN) and natural descriptors (obtained using a pre-trained CNN in a different dataset). In the BOVW the SIFT and SURF descriptors are compared, densely extracted and using MSER, clustered wi...
Conference Paper
The non-invasive visualization of retinal microvasculature is a traditional way to diagnose and predict some diseases. The region of foveal avascular zone (FAZ) is an important tool to quantify the macular ischemic with implications in the visual acuity. In this work, we proposed an automatic segmentation of FAZ using high-resolution retinal images...
Article
Full-text available
Este trabalho consiste no reconhecimento de imagens de produtos, com base em três métodos: palavras visuais por meio de descritores artificiais Bag of Visual Words (BOVW), redes neurais convolucionais (CNN) e descritores naturais (obtidos através de uma rede neural previamente treinada em uma base distinta). Na técnica BOVW são comparados os descri...
Conference Paper
Full-text available
It is estimated that 80% of crashes and 65% of near collisions involved drivers inattentive to traffic for three seconds before the event. This paper develops an algorithm for extracting characteristics allowing the cell phones identification used during driving a vehicle. Experiments were performed on sets of images with 100 positive images (with...
Conference Paper
In this work, segmentation is an intermediate step in the registration and 3D reconstruction of the lung. New MR imaging protocols have been used to enhance the lung internal structures and, consequently, the lung boundary is weakened. This fact turns the segmentation of lung MR images particularly difficult. The algorithm proposed herein uses morp...
Article
Full-text available
O sistema terrestre de transporte possui grande influência na vida moderna, mas a manutenção de cada quilômetro da rede rodoviária é uma tarefa difícil, dada a sua extensão. A avaliação das condições de estradas pode ser um trabalho cansativo se realizado sem auxílio computacional automatizado; por isso, sistemas semiautomatizados de análise de est...
Conference Paper
Full-text available
It is estimated that 80% of crashes and 65% of near collisions involved drivers inattentive to traffic for three seconds before the event. This paper develops an algorithm for extracting characteristics allowing the cell phones identification used during driving a vehicle. Experiments were performed on sets of images with 100 positive images (with...
Chapter
3D reconstruction from planar contours using the heuristic approach implements rules for three different phases of the process: correspondence, tiling and branching. We have analyzed existing algorithms and have been able to isolate their constituent pieces which allowed us to foresee many other possible (atomic) contributions. These pieces of algo...
Article
The diaphragm is an important component of the respiratory pumping process. Orthogonal temporal sequences of MR images are acquired in free breathing without use of contrast. The vertical intersection between two orthogonal temporal sequences is determined, the diaphragmatic level in the vertical segment is determined and used to perform the tempor...
Conference Paper
Este artigo descreve o processo de identificação de produtos utilizando extração de características através do algoritmo SURF, redução da dimensionalidade dos descritores utilizando contagem de frequência e classificação com algoritmos de aprendizado supervisionado rede perceptron multicamadas (MLP) e máquinas de vetor de suporte (SVM). A rede MLP...
Conference Paper
Full-text available
Este artigo descreve o processo de identificação de produtos utilizando extração de características através do algoritmo SURF, redução da dimensionalidade dos descritores utilizando contagem de frequência e classificação com algoritmos de aprendizado supervisionado rede perceptron multicamadas (MLP) e máquinas de vetor de suporte (SVM). A rede MLP...
Data
Full-text available
Conference Paper
Full-text available
In United States around 100,000 accidents are caused by drowsy drivers, resulting in over 1,500 deaths and 71,000 injuries per year. The driver inattention caused half of 126,000 accidents on brazilian federal highways (in 2010). This paper presents methods for face location, analysis of eye state (opened or closed) and drowsiness detection of driv...
Article
Full-text available
Resumo-Este artigo visa descrever e comparar as principais técnicas presentes na literatura para a avaliação objetiva de qualidade de vídeo no padrão H.264, aplicada a sistemas de transmissão de TV Digital. A avaliação objetiva idealmente permite a obtenção de uma métrica de qualidade automática, dispensando o uso de observadores humanos. Essa aval...
Article
This paper presents a 3D reconstruction (by 3D-snake) of the longitudinal axis of an electrical arc (discharge) in evolution based on stereo pairs of images. The accuracy of such tracking depends strongly on the halting of the iterative relaxation process that adjusts the 3D-snake. The key aspect to make such decision is detecting when each project...
Chapter
Uma imagem é representada normalmente como um objeto matricial ou um conjunto de pixels (picture elements) dispostos em uma grade bidimensional. Cada pixel caracteriza uma coordenada espacial e registro associado de um ou mais valores, representando uma cor, intensidade de cinza, ou bit que indica preto ou branco. Algoritmos de processamento de ima...
Article
This paper presents an industrial robot guided by a vision system into a work cell that will be installed into head block finishing casting line at a foundry company. The robot tasks will be the handling of head blocks between the stations of the work cell. The developed vision system identifies the head block model using the Pearson Correlation an...
Conference Paper
A gray-level image can be represented by a component tree, based on the inclusion relation of connected regions obtained by threshold decomposition. The great advantage of this structure is the efficient determination of a set of attributes for each component of the image, being widely used in morphological filtering (for instance, area as attribut...
Conference Paper
Full-text available
Adessowiki is a collaborative environment for teaching and research in image processing. Adessowiki is composed of a collection of collaborative web pages in the form of a wiki. The articles of this wiki can embed programming code that will be executed on the server when the page is rendered, incorporating the results as figures, texts and tables o...
Article
Full-text available
Marker-based Augmented Reality applications rely on images that contain a thick border and an internal symbol to address a three dimensional virtual object. The border facilitates recognizing the marker in the space and the internal symbol helps differentiate amongst a small set of objects. This last capacity can be increased by the use of two-dime...
Article
A gray-scale image can be interpreted as a topographical surface, and represented by a component tree, based on the inclusion relation of connected components obtained by threshold decomposition. Relations between plateaus, valleys or mountains of this relief are useful in computer vision systems. An important definition to characterize the topogra...
Article
Full-text available
This paper presents an algorithm for automatic detection of predominant color and logo (trademark) of vehicles. The color classification is based on the definition of fuzzy sets and pertinence rules of pixels from the segmentation of metallic part of the vehicle. Moreover, logo segmentation is obtained from appropriated morphological operators.
Conference Paper
Full-text available
A gray-level image can be interpreted as a topographical surface, and represented by a component tree, based on the inclusion relation of connected components obtained by threshold decomposition. Relations between plateaus, valleys or mountains of this relief are useful in computer vision systems. An important definition to characterize the topogra...
Article
Full-text available
Given a set of consecutive slices resulting from a non-invasive examining device, there is an expectation to be able to reconstruct the 3D original object regardless if it is a human organ or the channeling of underground petroleum resources. The slices however, identify a set of curves, which need to be properly connected to give rise of a coheren...
Article
This work proposes a generic algorithm of shape detection in a grayscale image from its Max-tree. This structure organizes different connected components in all scales of the image in a hierarchical way offering more semantic information and less elements to process in relation to the traditional grid of pixels representation. Filtering methods and...
Article
Full-text available
This work approaches an alternative man-machine interface using a low cost camera. A mouse architecture by webcam is elaborated from the acquisition of images and processing of simplified markers defined appropriately. An useful equipment is intended in the most varied kinds of environments, with significant tolerance of illumination.
Article
Despite different telangiectasia treatments in the lower limbs, there is no method standardization for results assessment, making comparison between the existing treatments conflicting. To compare the assessment carried out by a group of specialists with the assessment carried out by a computer program, according to clearance degree of telangiectas...
Article
BACKGROUND: Despite different telangiectasia treatments in the lower limbs, there is no method standardization for results assessment, making comparison between the existing treatments conflicting. OBJECTIVE: To compare the assessment carried out by a group of specialists with the assessment carried out by a computer program, according to clearance...
Article
This work proposes the segmentation of grayscale image from of its hierarchical region based representation. The Maxtree structure has demonstrated to be useful for this purpose, offering a semantic vision of the image, therefore, reducing the number of elements to process in relation to the pixel based representation. In this way, a particular sea...
Conference Paper
Full-text available
This paper suggests an hierarchical region based representation to implement detection of shapes in gray-scale images. The max-tree structure has been demonstrated to be useful for this purpose, offering a semantic objects vision of the image, thereby reducing the number of elements to process in relation to the pixel based representation. In this...
Article
Full-text available
This paper presents the Adesso, a computational environment for the development of scientific software. The Adesso environment leverages the reusable software component programming model to support the development and integration of components to several scientific programming platforms. The Adesso system is based on an XML component database and a...
Conference Paper
This work consists in the study, development and implementation of a toolbox for image processing using the Python language and the numerical Python package. This set has "open source" distribution and is adequate for multidimensional mathematical processing. Python is a modern and well projected language, interpreted, "very-high-level", object ori...
Conference Paper
Full-text available
Cement is an essential material for the development of the civil construction. The analysis of cement-based materials is useful in the evaluation of mechanical properties, water absorption, air permeability and evolution of hydration degree. The latter is the motivation of this paper. New advantageous techniques of analysis based on the image infor...
Conference Paper
Full-text available
This paper presents an automatic method to assess telangiectasia degreeing, by estimating the reduction of the varicose area from pre to post-treatment using digital image analysis techniques. First both images are geometrically transformed and color space reduced, in order to make them suitable for processing. Next, the varicose veins are segmente...
Conference Paper
Full-text available
This work consists of the study, development and implementation of an image processing toolbox for the Python language. This environment will be useful in education, research and the development of final applications. The toolbox will be developed using the facilities of the Adesso project for the development of software for scientific computation
Article
Full-text available
Resumo. Este trabalho consiste no estudo, desenvolvimento e implementação de uma caixa de ferramentas de processamento de imagens a partir da linguagem Python e pacote Numerical Python. Este conjunto segue a linha "Open Source" de distribuição sendo bastante adequado ao processamento matemático multidimensional. Python é uma linguagem moderna, inte...
Article
Full-text available
This work describes the Ortoprog platform of submission, and computational exercises automatic verification. The goal is to assist a discipline which lacks of practical complementationof the subjects seen in class. Exercises are proposed and the students receive a remote automatic feedback, in any time, in relation to accuracy of their solutions. M...

Network

Cited By

Projects

Projects (2)
Project
The human eye allows a direct visualization of retinal microvasculature non-invasively. This project consists of research and development of algorithms for segmentation and characterization of avascular foveal zone in fundus images obtained without contrast injection. Statistical for a set of patients (with and without pathologies) can help the analysis of this type of structure by experts, allow the monitoring of their morphology, contributing to prevention of loss of visual acuity.