Ancient document recognition Using Fuzzy Methods

João M. C. Sousa, João R. Caldas Pinto, C. S. Ribeiro, João M. Gil

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


This paper proposes an optical character recognition system based on fuzzy logic for ancient printed documents. The recognition process consists of two stages: training with collected character image examples and classification of new character images. The proposed OCR builds fuzzy membership functions from oriented features extracted using Gabor filter banks. Results on a significant test led to a character recognition success rate of 88%
Original languageEnglish
Title of host publicationThe 14th IEEE International Conference on Fuzzy Systems, 2005. FUZZ '05
Place of PublicationReno, NV, USA
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Print)0-7803-9159-4
Publication statusPublished - 1 May 2005
Event14th IEEE International Conference on Fuzzy Systems - Reno, NV, United States
Duration: 25 May 2005 → …


Conference14th IEEE International Conference on Fuzzy Systems
Country/TerritoryUnited States
CityReno, NV
Period25/05/05 → …


  • Document image processing
  • Feature extraction
  • Fuzzy logic
  • Fuzzy set theory
  • Image classification
  • Optical character recognition
  • Ancient document recognition
  • Fuzzy methods
  • Optical character recognition system
  • Ancient printed documents
  • Character image classification
  • Fuzzy membership functions
  • Gabor filter banks
  • Fuzzy OCR
  • Optical character recognition software
  • Character recognition
  • Packaging
  • Gabor filters
  • Handwriting recognition
  • Typesetting
  • Optical filters
  • Text recognition


Dive into the research topics of 'Ancient document recognition Using Fuzzy Methods'. Together they form a unique fingerprint.

Cite this