Comparison of crisp and fuzzy character networks in handwritten word recognition
Paul Gader, Magdi A. Mohamed, Jung-Hsien Chiang · NASA STI Repository (National Aeronautics and Space Administration) · 1992
Experiments involving handwritten word recognition on words taken from images of handwritten address blocks from the United States Postal Service mailstream are described. The word recognition algorithm relies on the use of neural networks at the character level. The neural networks are trained using crisp and fuzzy desired outputs. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level.