Towards Building A Robust Large-Scale Bangla Text Recognition Solution Using A Unique Multiple-Domain Character-Based Document Recognition Approach

Bangla is one of the world's top ten popular languages in terms of the number of speakers. It also happens to have a complex script primarily because of complex characters, e.g. graphemes, composed of multiple single characters, and the characteristic short-hands, e.g. vowel diacritics, and con...

Full description

Saved in:
Bibliographic Details
Published in2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) pp. 1393 - 1399
Main Authors Rabby, Akm Shahariar Azad, Islam, Md. Majedul, Islam, Zahidul, Hasan, Nazmul, Rahman, Fuad
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2021
Subjects
Buildings
Character recognition
Conferences
Document Processing
Handwriting
Machine learning
OCR
Optical character recognition software
Recognition
Segmentation
Text recognition
Online AccessGet full text

Cover

More Information
Summary:Bangla is one of the world's top ten popular languages in terms of the number of speakers. It also happens to have a complex script primarily because of complex characters, e.g. graphemes, composed of multiple single characters, and the characteristic short-hands, e.g. vowel diacritics, and consonant diacritics making the number of classes of this script recognition quite large, varied, and challenging. In this paper, we present a unique large-scale Bangla document OCR solution based on character-level recognition modules. We have tested our approach on two independent domains: printed and handwritten documents. We also applied our solution to three subdomains within the printed domain: computer-composed documents, letterpress documents, and typewritten documents. Our extensive experiments show that our approach achieves state-of-the-art performance on handwritten and printed documents.
DOI:10.1109/ICMLA52953.2021.00225