A Review on Handwritten Devanagari Character Recognition

EasyChair Preprint 2128, version 1

Abstract

Due to the vast variation in writing styles, the handwritten text recognition is considered to be challenging task. Hence, the handwritten character recognition is now an active field of research. In India, a large number of people use Devanagari Script to write their documents, but due to large complexity, research work done on this script is very less compared to English script. Hence, handwritten recognition of Devanagari Script is one of the most demanding research works in the area of image processing and pattern recognition.  Feature extraction and classification are important steps of character recognition process which affects the overall accuracy of the recognition system. This paper gives a detailed review on different feature extraction and classification techniques used for recognition of Devanagari script by the researchers over the past few years.

Keyphrases: Artificial Neural Network, CNN, Devanagari, OCR, SVM, k-NN

@booklet{EasyChair:2128,
  author    = {Manoj Sonkusare and Roopam Gupta and Asmita Moghe},
  title     = {A Review on Handwritten Devanagari Character Recognition},
  howpublished = {EasyChair Preprint 2128},
  year      = {EasyChair, 2019}}