Bengali Handwriting Recognition and Conversion to Editable Text

Chowdhury, S. M. Mazharul Hoque; Wasee, Farhan Rahman; Islam, Mohammad Shafiqul; Zaman, Hasan U.

doi:10.1109/icaecc.2018.8479487

Cited by 4 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A spell checker reduced the number of mistakes to 8.9% and 21.5 %, respectively. This approach is likely to work on numerous additional Abugida scripts related to Bangla.Sadia Chowdhury et al [10] suggested a system that accepts a scanned picture of Bengali handwritten text as input and outputs an editable version of that text after processing. The system is divided into many parts, the most important of which are image processing, machine learning via neural network training, and finally, detection of Bengali letters.…”

Section: Related Workmentioning

confidence: 99%

Offline Handwritten Character Recognition Including Compound Character from Scanned Document

Ahmed

Uddi̇n

Khan

et al. 2022

AJRCoS

View full text Add to dashboard Cite

Recognizing the handwritten characters and converting them into machine-editable text is very tedious due to the diversity of writing styles and character patterns. Extracting data from images and identifying the characters becomes more complicated when a language consists of compound structures and characters, such as Bengali. There has been a lack of programs for recognizing Bengali scripted basic and com-plex numeric signs and letters with high accuracy. This paper develops a novel approach to extracting and identifying Bengali handwritten primary characters, digits, and primarily used compound characters. In this proposed model, an image containing Bengali handwritten text takes as input and processed. Then processed images are segmented into lines and characters. The features are extracted from segmented characters and recognized using a Convolutional Neural Network (CNN). The CNN obtains 98.23% accuracy in the training dataset and 96.02% in the validation dataset. Apart from that, the proposed model has gained 89.6% precision and 92.6% recall scores on scanned image data.

show abstract

Section: Related Workmentioning

confidence: 99%