A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN
P V Bhagyasree, Ajay James, Saravanan Chandran · 2019
Handwritten Character Recognition (HCR) plays an important role in Optical character Recognition (OCR) and Pattern Recognition (PR), as it has a good number of applications in various fields. HCR contributes extremely to the growth of automation and are applicable in the areas of bank cheque, medical prescriptions, tax returns etc. But handwritten characters are much more difficult to recognize than the printed characters due to difference in writing styles for different people. Both conventional approaches and deep learning techniques have been used for handwritten character recognition. Deep learning techniques such as Convolutional Neural Networks always shows better accuracy than the conventional techniques. In this paper a new deep learning techniques, namely Directed Acyclic Graph - Convolutional Neural Network (DAG-CNN) is used for handwritten character recognition.