Handwritten word recognition with character and inter-character neural networks
Authors:
- M. MohamedMMM. Mohamed
- Jung-Hsien ChiangJCJung-Hsien Chiang
- 1 February 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 27 (1) , 158-164
Abstract
An off-line handwritten word recognition system is described. Images of handwritten words are matched to lexicons of candidate strings. A word image is segmented into primitives. The best match between sequences of unions of primitives and a lexicon string is found using dynamic programming. Neural networks assign match scores between characters and segments. Two particularly unique features are that neural networks assign confidence that pairs of segments are compatible with character confidence assignments and that this confidence is integrated into the dynamic programming. Experimental results are provided on data from the U.S. Postal Service.Keywords
This publication has 12 references indexed in Scilit:
- Handwritten word recognition with character and inter-character neural networksIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1997
- Neural and fuzzy methods in handwriting recognitionComputer, 1997
- Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniquesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Dynamic-programming-based handwritten word recognition using the Choquet fuzzy integral as the match functionJournal of Electronic Imaging, 1996
- Comparison of crisp and fuzzy character neural networks in handwritten word recognitionIEEE Transactions on Fuzzy Systems, 1995
- Handprinted word recognition on a NIST data setMachine Vision and Applications, 1995
- A multilayer neural network system for computer access securityIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Off-line handwritten word recognition using a hidden Markov model type stochastic networkIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- The first census optical character recognition system conference1992
- A fuzzy K-nearest neighbor algorithmIEEE Transactions on Systems, Man, and Cybernetics, 1985