Handwritten OCR for Indic Scripts: A Comprehensive Overview of Machine Learning and Deep Learning Techniques

Abstract

The potential uses of cursive optical character recognition, commonly known as OCR, in a number of industries, particularly document digitization, archiving, even language preservation, have attracted a lot of interest lately. In the framework of optical character recognition (OCR), the goal of this research is to provide a thorough understanding of both cutting-edge methods and the unique difficulties presented by Indic scripts. A thorough literature search was conducted in order to conduct this study, during which time relevant publications, conference proceedings, and scientific files were looked for up to the year 2023. As a consequence of the inclusion criteria that were developed to concentrate on studies only addressing Handwritten OCR on Indic scripts, 53 research publications were chosen as the process's outcome. The review provides a thorough analysis of the methodology and approaches employed in the chosen study. Deep neural networks, conventional feature-based methods, machine learning techniques, and hybrid systems have all been investigated as viable answers to the problem of effectively deciphering Indian scripts, because they are famously challenging to write. To operate, these systems require pre-processing techniques, segmentation schemes, and language models. The outcomes of this methodical examination demonstrate that despite the fact that Hand Scanning for Indic script has advanced significantly, room still exists for advancement. Future research could focus on developing trustworthy models that can handle a range of writing styles and enhance accuracy using less-studied Indic scripts. This profession may advance with the creation of collected datasets and defined standards.