• 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.18.2018.tde-25012018-143919
Document
Author
Full name
Evelina Maria de Almeida Neves
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 1995
Supervisor
Committee
Gonzaga, Adilson (President)
Paiva, Maria Stela Veludo de
Traina, Agma Juci Machado
Title in Portuguese
Reconhecimento óptico de caracteres isolados baseado em suas características fundamentais
Keywords in Portuguese
Reconhecimento de caracteres
Abstract in Portuguese
Foi projetado um sistema para reconhecimento multifonte de caracteres alfabéticos isolados, impressos em letras maiúsculas, usando extração de características topológicas. Através da especificação de um conjunto apropriado de características, tais como traços verticais, horizontais e inclinados, áreas abertas e fechadas, denominadas aqui de características fundamentais, o reconhecimento foi determinado baseado na comparação de vetores de características. Os resultados de reconhecimento com protótipos de fontes impressas mostraram que o sistema proposto é capaz de fazer a leitura de diferentes tipos de caracteres impressos a uma taxa de precisão de 98.83%. Este trabalho também apresenta uma revisão descritiva dos aspectos básicos da aquisição, pré-processamento e extração de características da imagem. São apresentados ainda alguns aspectos históricos e mencionados alguns sistemas de OCR disponíveis comercialmente.
Title in English
not available
Keywords in English
not available
Abstract in English
A multifont character recognition system has been designed by making use of topological feature extraction to recognize capital isolated letters. By properly specifying a set of features such as vertical, horizontal and slant strokes, curvatures, open and closed areas, named here fundamental features, the recognition has been performed based on feature vector matching. Recognition experiments with a prototype system for a variety of printed fonts show that the proposed system is capable of reading different types of printed characters at an accuracy rate of 98,83%. This work also presents a descriptive review about the basic aspects of image acquisition, preprocessing, feature extraction, historical aspects and commercially available OCR systems.
 
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
2018-01-25
 
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.