"WBSUBNdb_text: Bangla handwritten text document dataset" is a Bangla text dataset containing 1383 offline handwritten text documents contributed by 190 writers. The dataset is composed of both simple and compound characters.
-
Updated
Jun 1, 2024
"WBSUBNdb_text: Bangla handwritten text document dataset" is a Bangla text dataset containing 1383 offline handwritten text documents contributed by 190 writers. The dataset is composed of both simple and compound characters.
✍️ Bengali Alphabet (বাংলা বর্ণমালা)
EasyOCR is basically Optical Character Reading package that belongs from PyTorch. Using this texts from the images can be extracted easily, documents, texts can be scanned. For License Plate's Number Recognition, it can be applicable easily as it can extract the texts. About License Plate's Number, there are several language's character plates a…
The default auto correct dictionary added in avro Bangla keyboard doesn't contain enough word. So, this is my approach to enrich the dictionary. This file contains the correct spelling of commonly used Bangla words.
Implementation of the paper 'Towards Full page Offline Bangla Handwritten Text Recognition using Image-to-Sequence Architecture'. For details, please read the README section.
An interactive Optical Character Recognition Prototype for Bangla and English. Made with Gradio and Pytesseract.
Line and Word Segmentation for Bangla Handwritten Text Recognition
This repo contains all the project task resources and links from NLP course which is offered by BRAC University.
Python wrapper for cross platform tesseract OCR engine with multiple languages (e.g. Bangla)
Handwritten Bangla Symbol Recognition With DenseNet
Synthetic data generation for bangla OCR
A snipping tool to Extract Bangla Text By snipping using cursor from anywhere on the screen.
A Bangla license plates dataset (synthetic), generated with a mixture of deep learning and image processing. The labels are in darknet yolo format. [.txt, .data, .names]
OCR for Bangla language and all other languages.
EkushNet is the first research which can recognize Bangla handwritten basic characters, digits, modifiers, and compound characters. Handwritten recognition is one of the most interesting issue in present time due to its variant applications and help to make the old form and information digitization and reliable.
Bangla OCR System Developed from SUST based on ICIEV 2016 paper, "An efficient way for segmentation of Bangla characters in printed document using curved scanning"
Add a description, image, and links to the bangla-ocr topic page so that developers can more easily learn about it.
To associate your repository with the bangla-ocr topic, visit your repo's landing page and select "manage topics."