Abstract
In this work, a novel model for recognition of handwritten Kannada characters using transfer learning from Devanagari handwritten recognition system is presented. The objective is to use the knowledge of large data corpus of Devanagari recognition system as training data to perform the recognition of handwritten Kannada characters that has a smaller data corpus. The transfer of knowledge for recognition is carried out using deep learning network architecture to VGG19 NET. VGG19 NET is defined of five blocks of hidden layers, two dense fully connected layers and an output layer. Each block (except block1) consists of four convolution layers along with a max pooling layer. In proposed classification framework, Devanagari character set consists of totally 92000 images with 46 classes and Kannada character set is built with 81654 for training and 9401 for testing, for about 188 classes with each class comprising of 200–500 sample image. A total of 1,23,654 data samples is employed for training with VGG19 NET. For experimentation 9401 samples of about 188 classes built of about 40–100 samples in each classes is used and for which accuracy close to 90% is achieved. Validated accuracy after evaluation in 10 epochs with VGG19 NET, it has recorded an accuracy of 73.51% with a loss of 16.18%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have