Script independent handwritten numeral recognition
Rajaram Sanjeev Kunte, R. D. Sudhaker Samuel · 2006
This paper presents an off-line handwritten recognition system for numerals that is independent of the script. Numeral set from five major Indian language and English language are selected for recognition. Wavelets that have been progressively used in pattern recognition and many character recognition systems are used in our system to extract the features of numerals. Neural classifiers have been effectively used for the classification of numerals. An overall recognition rate of 92.3% has been obtained. The recognition scheme in general can be used for any language and particularly for applications like postal address automation.