A fuzzy based classification scheme for unconstrained handwritten Devanagari character recognition
Authors:
- 1 January 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
The large data set and similar structural features of the characters in Devanagari script demand a highly efficient classification and recognition system. This paper presents a novel approach for the recognition of unconstrained handwritten Devanagari characters. The system is based on multi-stage classification scheme. The classification stages categorize the characters into smaller groups. The classification is done using two stages, first stage is based on fuzzy inference system and second stage is based on structural parameters. The fuzzy system improves the classification over crisp classification. The classified characters are passed to the feature extraction stage. The final stage implements feed forward neural network for character recognition. The recognition accuracy achieved by the proposed method is 96.95%.Keywords
This publication has 12 references indexed in Scilit:
- A Novel Multi-feature Multi-classifier Scheme for Unconstrained Handwritten Devanagari Character Recognition2010
- Input Fuzzy Modeling for the Recognition of Handwritten Hindi Numerals2007
- Fuzzy Model Based Recognition of Handwritten Hindi Numerals using Bacterial Foraging2007
- Fuzzy model based recognition of handwritten numeralsPattern Recognition, 2006
- Indian script character recognition: a surveyPattern Recognition, 2004
- Unconstrained handwritten character recognition based on fuzzy logicPattern Recognition, 2003
- Partitioning and searching dictionary for correction of optically read Devanagari character stringsInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Devnagari numeral recognition by combining decision of multiple connectionist classifiersSādhanā, 2002
- On how to describe shapes of Devanagari characters and use them for recognition1999
- Feature extraction methods for character recognition-A surveyPattern Recognition, 1996