Optical Text Recognition in Nepali and Bengali: A Transformer-based Approach

2024-04-03 · S M Rakib Hasan, Aakar Dhakal, Md Humaion Kabir Mehedi, Annajiat Alim Rasel

Efforts on the research and development of OCR systems for Low-Resource Languages are relatively new. Low-resource languages have little training data available for training Machine Translation systems or other systems. Even though a vast amount of text has been digitized and made available on the internet the text is still in PDF and Image format, which are not instantly accessible. This paper discusses text recognition for two scripts: Bengali and Nepali; there are about 300 and 40 million Bengali and Nepali speakers respectively. In this study, using encoder-decoder transformers, a model was developed, and its efficacy was assessed using a collection of optical text images, both handwritten and printed. The results signify that the suggested technique corresponds with current approaches and achieves high precision in recognizing text in Bengali and Nepali. This study can pave the way for the advanced and accessible study of linguistics in South East Asia.

📄 PDF Abstract BibTeX arXiv:2404.02375

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Machine Translation Optical Character Recognition (OCR)

GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer

2025-09-22 · Md. Mahmudul Hasan, Ahmed Nesar Tahsin Choudhury, Mahmudul Hasan, Md. Mosaddek Khan arxiv

Despite Bengali being the sixth most spoken language in the world, handwritten text recognition (HTR) systems for Bengali remain severely underdeveloped. The complexity of Bengali script--featuring conjuncts, diacritics,…

Handwritten Text Recognition

Optimizing Nepali PDF Extraction: A Comparative Study of Parser and OCR Technologies

2024-07-05 · Prabin Paudel, Supriya Khadka, Ranju G. C., Rahul Shah

This research compares PDF parsing and Optical Character Recognition (OCR) methods for extracting Nepali content from PDFs. PDF parsing offers fast and accurate extraction but faces challenges with non-Unicode Nepali fon…

Optical Character Recognition Optical Character Recognition (OCR)

End-to-End Optical Character Recognition for Bengali Handwritten Words

2021-05-09 · Farisa Benta Safir, Abu Quwsar Ohi, M. F. Mridha, Muhammad Mostafa Monowar 외

Optical character recognition (OCR) is a process of converting analogue documents into digital using document images. Currently, many commercial and non-commercial OCR systems exist for both handwritten and printed copie…

Optical Character Recognition Optical Character Recognition (OCR)

bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents

2023-08-21 · Imam Mohammad Zulkarnain, Shayekh Bin Islam, Md. Zami Al Zunaed Farabe, Md. Mehedi Hasan Shawon 외

Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low-resource languages, including Bengal…

distortion correction Optical Character Recognition Optical Character Recognition (OCR)

Bengali Handwritten Digit Recognition using CNN with Explainable AI

2022-12-23 · MD Tanvir Rouf Shawon, Raihan Tanvir, Md. Golam Rabiul Alam

Handwritten character recognition is a hot topic for research nowadays. If we can convert a handwritten piece of paper into a text-searchable document using the Optical Character Recognition (OCR) technique, we can easil…

Explainable Artificial Intelligence (XAI)Handwritten Digit Recognition Optical Character Recognition Optical Character Recognition (OCR)