Volume 12, Issue 10

Text Recognition of Bangla and English Scripts in Natural Scene Images

Author

Mithun Dutta* 1 , Akash Mohajon2 , Shaikat Dev3 , Dhiman sarker Bappi4 and Dr. Jugal Krishna Das5

Abstract

Digital cameras on mobile devices have created several new computational hurdles. Text extraction from natural scene photos collected by such devices
is an issue. This paper presents a method for recognizing English and Bangla text in scene photos. With this framework, it will be possible to recognize and locate text in its natural setting. Text recognition in natural settings is performed on multiple distinct tiers. To begin, a picture is taken using a smart device. Then text localization and text extraction are done. In the final stage, an artificial neural network is used to recognize the text from the image. This is a bilingual project, with results available in both Bengali and English. The system outperforms conventional recognition methods, producing image results with an average accuracy of 85%.

DOI

https://doi.org/10.62226/ijarst20231124

PAGES : 0 | 0 VIEWS | 0 DOWNLOADS


Download Full Article

Mithun Dutta* 1 , Akash Mohajon2 , Shaikat Dev3 , Dhiman sarker Bappi4 and Dr. Jugal Krishna Das5 | Text Recognition of Bangla and English Scripts in Natural Scene Images | DOI : https://doi.org/10.62226/ijarst20231124

Journal Frequency: ISSN 2320-1126, Monthly
Paper Submission: Throughout the month
Acceptance Notification: Within 6 days
Subject Areas: Engineering, Science & Technology
Publishing Model: Open Access
Publication Fee: USD 60  USD 50
Publication Impact Factor: 6.76
Certificate Delivery: Digital

Publish your research with IJARST and engage with global scientific minds