https://github.com/ilieschibane/web-application-for-arabic-ocr-using-deep-learning
A Deep learning model for arabic optical character recognition
https://github.com/ilieschibane/web-application-for-arabic-ocr-using-deep-learning
arabic character-segmentation convolutional-neural-networks deep-learning flask generative-adversarial-network javascript ocr python pytorch reactjs tensorflow
Last synced: about 1 year ago
JSON representation
A Deep learning model for arabic optical character recognition
- Host: GitHub
- URL: https://github.com/ilieschibane/web-application-for-arabic-ocr-using-deep-learning
- Owner: IliesChibane
- License: mit
- Created: 2022-10-01T14:58:50.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-02T13:17:21.000Z (over 3 years ago)
- Last Synced: 2025-03-30T15:47:08.466Z (about 1 year ago)
- Topics: arabic, character-segmentation, convolutional-neural-networks, deep-learning, flask, generative-adversarial-network, javascript, ocr, python, pytorch, reactjs, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 27.5 MB
- Stars: 3
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# DL-Arabic-OCR
In this project we will create deep learning models and data augmentation techniques using different librairies like tensorflow and pytorch for arabic optical characther recognition.
#### Requirements
- Python 3.8
- CUDA 11.7
- anaconda-navigator
#### Setup
Create an annaconda environement and use this command to install all the neccesary librairies
```bash
pip install numpy pandas matplotlib seaborn scikit-learn opencv jupyter flask tensorflow torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu117
```
After this all you need to do is start coding using your code editor of your choice
#### Download the model
The model being too heavy to be push on github it has to be download from this [google drive link](https://drive.google.com/file/d/19hVNPWHn3c2S2YDq1sYrogn-SpIJb_ud/view?usp=sharing)
Once done all you need to do is to put the model on the tf-file folder