Research Article
Modified Chain Code Histogram Feature for Handwritten Character Recognition
@INPROCEEDINGS{10.1007/978-3-642-27299-8_64, author={Jitendra Jain and Soyuj Sahoo and S. Mahadeva Prasanna and G. Siva Reddy}, title={Modified Chain Code Histogram Feature for Handwritten Character Recognition}, proceedings={Advances in Computer Science and Information Technology. Networks and Communications. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part I}, proceedings_a={CCSIT PART I}, year={2012}, month={11}, keywords={Differential Chain Code Histogram Handwritten Character Recognition Misclassification Rate Feature combination}, doi={10.1007/978-3-642-27299-8_64} }- Jitendra Jain
Soyuj Sahoo
S. Mahadeva Prasanna
G. Siva Reddy
Year: 2012
Modified Chain Code Histogram Feature for Handwritten Character Recognition
CCSIT PART I
Springer
DOI: 10.1007/978-3-642-27299-8_64
Abstract
In this work, we have proposed modified chain code histogram (CCH) based feature extraction method for handwritten character recognition (HCR) applications. This modified approach explores the dynamic nature of directional information, available in character patterns, by introducing the Differential CCH which is termed as Delta (Δ) CCH. A comparable and higher recognition rate is reported which emphasizes that the dynamic nature of directional information captured by the ΔCCH is as important as that of CCH. All the experiments are conducted on MNIST handwritten numeral database. Finally, an improved recognition rate is observed at higher end by using combination of both the features which shows the effectiveness of dynamic directional feature in the classification of handwritten character patterns.
