Study on Automated Approach to Recognize Characters for Handwritten and Historical Document

摘要

Script recognition is the mechanism of automatic script analysis and recognition whereby intensive study has been carried out and a significant amount of papers on this problem have been released over the past. But there are still a few issues to be solved, particularly in Indian historical manuscripts. This literature examines the Script recognition with reference to multi-script document and different historical scripts such as Kurdish-Latin, Devanagari, Grantha, Arabic handwritten characters, Bangladesh, Devanagari and Gurumukhi, ancient Chinese, Arabic, Nam Character, Greek, Nastalique Urdu, Georgian handwritten, Nandinagari, and Hebrew, which provide the course of study that focuses on the framework for script recognition. This review concentrates on scope of prediction, dataset type, the methods used for data preprocessing, and measures of performance used for analysis. On the basis of this survey, Current research constraints have been recognized and future study specifications are emphasized in the area of modeling historical manuscripts.