On-line Character Recognition for Handwritten Kannada Characters using Wavelet Features and Neural Classifier

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.

[1]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[2]  S. H. Joseph.  Processing of engineering line drawings for automatic input to CAD , 1989, Pattern Recognit..

[3]  Andrew F. Laine,et al.  Wavelet descriptors for multiresolution recognition of handprinted characters , 1995, Pattern Recognit..

[4]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[5]  B. L. Deekshatulu,et al.  Recognition of Printed Telugu Characters , 1977 .

[6]  Pietro G. Morasso,et al.  Recognition experiments of cursive dynamic handwriting with self-organizing networks , 1993, Pattern Recognit..

[7]  King-Sun Fu,et al.  Shape Discrimination Using Fourier Descriptors , 1977, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ulrich Bodenhausen,et al.  A connectionist recognizer for on-line cursive handwriting recognition , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Wentai Liu,et al.  Optical recognition of handwritten Chinese characters: Advances since 1980 , 1993, Pattern Recognit..

[10]  Majid Ahmadi,et al.  Recognition of handwritten numerals with multiple feature and multistage classifier , 1995, Pattern Recognit..

[11]  Isabelle Guyon,et al.  Design of a neural network character recognizer for a touch terminal , 1991, Pattern Recognit..

[12]  Lambert Schomaker,et al.  Using stroke- or character-based self-organizing maps in the recognition of on-line, connected cursive script , 1993, Pattern Recognit..