MLPNN based handwritten character recognition using combined feature extraction
- 1 May 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1155-1159
- https://doi.org/10.1109/ccaa.2015.7148550
Abstract
Statistical techniques for off-line character recognition are not flexible and adaptive enough for new handwriting constraints. Offline handwritten character recognition of English alphabets using a three layered feed forward neural network is presented in this paper. The proposed recognition system describes the evaluation of feed forward neural network by combining four different feature extraction approaches(box approach, diagonal distance approach, mean and gradient operations). The proposed recognition system performs well on the benchmark dataset CEDAR (Centre of Excellence for Document Analysis And Recognition).Keywords
This publication has 21 references indexed in Scilit:
- Neural network language models for off-line handwriting recognitionPattern Recognition, 2013
- Interactive Fuzzy Model Based Recognition of Handwritten NumeralsJournal of Pattern Recognition Research, 2011
- Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Gujarati handwritten numeral optical character reorganization through neural networkPattern Recognition, 2010
- Fuzzy model based recognition of handwritten numeralsPattern Recognition, 2007
- A three-dimensional neural network model for unconstrained handwritten numeral recognition: a new approachPattern Recognition, 1998
- Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural networkIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- High accuracy optical character recognition using neural networks with centroid ditheringIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
- Off-line handwritten word recognition using a hidden Markov model type stochastic networkIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Handwritten digit recognition by neural networks with single-layer trainingIEEE Transactions on Neural Networks, 1992