• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
10.11606/D.55.2004.tde-04122014-160036
Document
Author
Full name
Luis Marcelo Bortolotti
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2004
Supervisor
Committee
Traina, Agma Juci Machado (President)
Gonzaga, Adilson
Marques, Fátima de Lourdes dos Santos Nunes
Title in Portuguese
Recuperação de imagens médicas por conteúdo considerando regiões definidas pela energia
Keywords in Portuguese
Não disponível
Abstract in Portuguese
O grande aumento do volume de informações gerado pelos sistemas de aquisição de imagens em hospitais tem levado ao desenvolvimento de sistemas que permitam a organização e o acesso à informação de forma organizada e rápida. Com o surgimento dos sistemas PACS (Picture Archiving and Communication System) surgiu a possibilidade de armazenar em um só sistema todas as informações dos pacientes. Este projeto implementa, técnicas para a extração de características de imagens para permitir consultas por similaridade. Para uma dada imagem, ela c processada utilizando um subespaço de baixa frequência definido por uma transformada de wavelets. Sobre este subespaço. o método localiza os Minimum Bound Rectangles (MBR) de regiões da imagem por meio dos gráficos de energia. Então a análise de textura é feita sobre essas regiões. Esses dados são utilizados na construção dos vetores de características da imagem para permitir a realização de consultas baseadas em conteúdo.
Title in English
Content-based medical image retrieval considering the regions defined by energy
Keywords in English
Not available
Abstract in English
The continuous increasing in the amount of information generated by the imaging devices in hospitais and medicai centers has motivated the developrnent of applications to organize, store and distribute the information acquired. The developrnent of PACS (Picture Archiving and Communication Systems) attended such demand. PACS allow to store ali the data from the patients in a single environment, letting the physicians to promptly have such information, besides to transmit and share the images and data to other centers. This project implements techniques for image feature extraction to support the processing of similarity queries. For a given image, it is processed using a low frequency subspace defined by a wavelet transform. Over this subspace, the technique locates regions in the image using the Energy plots. Tinis, the Minimuni Bound Rectangles (MBR) of such image regions aro defined. After that, a texture analysis is made on these regions, employing co-occurrences matrixes. This will lead to the construction of the images' feature vectors to allow content-based image queries.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2014-12-04
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
Centro de Informática de São Carlos
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2019. All rights reserved.