Optical Character Recognition System for Nepali Language Using ConvNet
Manish K. Sharma, Bidhan Bhattarai · 2017
This paper describes the implementation of CNN (Convolution Neural Network) based Optical Character Recognition System for Nepali Language, a commonly spoken language in Nepal. The system has been developed in python using Keras[1] library on top of Theano[2] and numpy[3]. The system has been trained using a set of real world[4] and synthesized data sets considering various noise conditions. The tests have also been carried out in a similar setup. This paper details the experiment by discussing the concept, implementation details and overall interpretation of the system.