On-line Character Recognition for Handwritten Kannada Characters using Wavelet Features and Neural Classifier
Srinivasa Rao Kunte, R. D. Sudhaker Samuel · IETE Journal of Research · 2000
The rapid advancement of the computer industry has led to computerization of various fields throughout the world, including India. Great emphasis is given to facilitate the users to interact with the computers in their local languages. Users will be more comfortable to input the instructions by their handwriting rather than through the existing local languages-converted-English keyboards. Since Kannada language is very rich in alphabet, for keying-in most of the Kannada characters, a combination of key strokes has to be used in such converted keyboards. This is very tedious and requires considerable practice and effort. An obvious solution is to input the instructions by handwriting. This paper reports the details of an on-line character recognition system for the Kannada characters developed by the authors that extracts the novel wavelet features from the contour of character written using a digitizer tablet pen. The conventional feedforward multilayer neural network is used as classifier. The results obtained are most encouraging and the system can be extended to other similar Indian languages, particularly, Telugu.