Digitization of handwritten Devanagari text using CNN transfer learning – A better customer service support

Devanagari script is one of the bases of various language scripts in India. With the growth of computing and technology, manual systems are replaced by automated one. The purpose of this research is to automate the existing manual system for digitization of Devanagari script with the use of an automated approach so that it saves time, antique data. The prescriptions given by the expert doctors and the treatments which are present in ancient Vedic literature are useful for handling patients with serious diseases. Digitization helps in easy access, manipulation, and longer storage of this data. Unlike Western languages such as English, Devanagari, is a famous script in India which does not have formal digitization tools. This work employs the best suited techniques that are useful to enhance the recognition rate and configures a Convolutional Neural Network (CNN) for effective Devanagari handwritten text recognition (DHTR). This approach uses Devanagari handwritten character dataset (DHCD) which is a vigorous open dataset with 46 classes of Devanagari characters and each of this class has two thousand different images. After recognition, conflict resolution is subtle for effective recognition therefore, this approach provides an arrangement to the user to handle the conflicts. This approach obtains promising results in terms of accuracy and training time.