Bangla Handwritten Character Recognition (BHCR)

Overview

This repository contains the dataset and research code used for Bangla Handwritten Character Recognition (BHCR). The goal of this project is to develop a machine learning model capable of recognizing Bangla handwritten alphabet characters from image inputs.

The repository includes:

A Bangla handwritten character image dataset
A Jupyter Notebook implementing the training and evaluation pipeline

This work was developed as part of a research project on Bangla Optical Character Recognition (OCR).

Repository Structure

BHCR-project/
│
├── BHCR Dataset.zip
│
├── banglaalpha.ipynb
│
└── README.md

Files Description

BHCR Dataset.zip

Compressed dataset containing Bangla handwritten character images. Each folder represents a specific Bangla character class and contains multiple handwritten samples in PNG format.

Example structure:

BHCR Dataset/
   ├── অ/
   ├── আ/
   ├── ই/
   ├── ঈ/
   └── ...

Each directory contains multiple handwritten samples such as:

character_1001.png
character_1002.png
character_1003.png

banglaalpha.ipynb

Jupyter Notebook that contains:

Data loading and preprocessing
Dataset visualization
Model implementation
Training and evaluation

The notebook demonstrates the full workflow for Bangla handwritten character classification.

Dataset Description

The dataset consists of handwritten Bangla alphabet characters collected for machine learning training and evaluation.

Features of the dataset:

Image format: PNG
Handwritten samples for multiple Bangla characters
Organized into class folders
Suitable for deep learning and computer vision experiments

This dataset can be used for:

Optical Character Recognition (OCR)
Image classification
Handwritten character recognition
Bengali language AI research

Requirements

To run the notebook, install the required Python libraries.

Example:

pip install numpy
pip install matplotlib
pip install tensorflow
pip install scikit-learn
pip install opencv-python
pip install jupyter

Usage

Extract the dataset:

unzip "BHCR Dataset.zip"

Open the notebook:

jupyter notebook banglaalpha.ipynb

Run the notebook cells to train and evaluate the model.

Applications

This research can be applied in:

Bangla OCR systems
Document digitization
Handwritten text recognition
Educational technology
Bangla language AI systems

Citation

If you use this dataset or code in your research, please cite this repository.

Citation will be added after publication.

License

This project is released under the MIT License.

Author

Researcher: Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Farida Siddiqi Prity, Saydul Akbar Murad, Nick Rahimi

Acknowledgement

This project contributes toward advancing research in Bangla handwritten character recognition and optical character recognition systems.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support