Ancient document recognition Using Fuzzy Methods
João M. C. Sousa, J.R. Caldas Pinto, Cláudia Ribeiro, João M. Gil · 2005
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%