• 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
https://doi.org/10.11606/D.55.2023.tde-10012024-152602
Document
Author
Full name
Endi Daniel Coelho Silva
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2023
Supervisor
Committee
Traina, Agma Juci Machado (President)
Batista Neto, João do Espírito Santo
Schiabel, Liliane Ventura
Schor, Paulo
Title in Portuguese
Técnicas de representação semântica de imagens por Bags of Complex Signatures - BoCS
Keywords in Portuguese
Bag of visual words
CBIR
Processamento de imagens
Recuperação de imagens baseada em conteúdo
Semântica de imagens
Abstract in Portuguese
Devido ao grande número de imagens geradas no nosso cotidiano que devem ser armazenadas e utilizadas posteriormente, surgiu a necessidade da criação de mecanismos eficientes para o gerenciamento de imagens em grandes bases de dados. Os sistemas de recuperação de imagens baseada em conteúdo são uma das principais ferramentas para realizar esse tipo de tarefa. No entanto, esse tipo de sistema muitas vezes não atende à expectativa do usuário, pois a forma como as imagens são representadas (características de baixo nível, como textura, forma e cor) não conseguem representar a semântica do pensamento humano. A representação de imagens utilizando palavras visuais, também conhecida por Bag of Visual Words (BoVW), é uma das mais famosas formas de tentar representar semanticamente o conteúdo de imagens. Portanto, o objetivo deste trabalho é desenvolver um método baseado no paradigma BoVW que consiga representar as imagens carregando informação semântica, possibilitando que essas representações possam ser utilizadas em sistemas de recuperação de imagens baseada em conteúdo e tragam resultados que sejam mais próximos às expectativas do usuário.
Title in English
Techniques for Semantic Representation of Images using Bags of Complex Signatures - BoCS
Keywords in English
Bag of visual words
CBIR
Content-based image retrieval
Image processing
Semantical representation
Abstract in English
Due to the large number of images generated in our daily lives that must be stored and used later, there is a need to create efficient mechanisms for managing images in large databases. Contentbased image retrieval systems are one of the main tools to perform this type of task. However, this type of system often does not meet the users expectations, because of the way images are represented (low-level characteristics, such as texture, shape and color) cannot represent the semantics of the humans thought. The representation of images using visual words also known as Bag of Visual Words (BoVW), is one of the most famous ways of trying to represent the content of images semantically. Therefore, the objective of this work is to develop a method based on the BoVW paradigm that is able to represent images carrying semantic information, enabling these representations to be used in content-based image retrieval systems and bring results that are more consistent with what the user want.
 
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
2024-01-10
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.