Radial basis function and subspace approach for printed Kannada text recognition

Neural network based radial basis function networks (RBFN) and subspace projection approach have been employed to recognize printed Kannada characters. RBFNs are trained with wavelet features using K-means and subspace method is applied on normalized image. Use of structural features for disambiguating confused characters improved the recognition accuracy by 3% in case of subspace and by 1.6% using RBFN. Compared to subspace, a maximum recognition rate of 99.1% is achieved with RBFN using Haar wavelets and structural features.