A novel feature extraction technique for the recognition of segmented handwritten characters
- 11 October 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
High accuracy character recognition techniques canprovide useful information for segmentation-basedhandwritten word recognition systems. This researchdescribes neural network-based techniques for segmentedcharacter recognition that may be applied to thesegmentation and recognition components of an off-linehandwritten word recognition system. Two neuralarchitectures along with two different feature extractiontechniques were investigated. A novel technique forcharacter feature extraction is discussed and comparedwith others in the literature. Recognition results above80% are reported using characters automaticallysegmented from the CEDAR benchmark database as wellas standard CEDAR alphanumerics.Keywords
This publication has 10 references indexed in Scilit:
- Machine and human recognition of segmented characters from handwritten wordsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Cursive digit and character recognition in CEDAR databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A new segmentation algorithm for handwritten word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Neural-based solutions for the segmentation and recognition of difficult handwritten words from a benchmark databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Handwritten word recognition with character and inter-character neural networksIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1997
- Neural-network classifiers for recognizing totally unconstrained handwritten numeralsIEEE Transactions on Neural Networks, 1997
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Building a new generation of handwriting recognition systemsPattern Recognition Letters, 1993
- High accuracy character recognition algorithm using fourier and topological descriptorsPattern Recognition, 1984
- A fast parallel algorithm for thinning digital patternsCommunications of the ACM, 1984