Nutrition Table Extraction Model

Nutrition Table Extraction Model integrating with CUDA, cuDNN, TensorRT
Go»

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Dependencies
   • Installation
3. Contributing
4. License
5. Authors
6. Acknowledgements

About The Project

The Nutrition Table Extraction project aims to develop an efficient solution for automatically detecting and extracting nutrition information from scanned images of nutrition tables..

Here we go to Notebook

This project combines OCR techniques with table extraction models to detect tables within images and extract text in a structured manner, it can handle different types of table formats

Getting Started

In this section provide instructions on how to use this repository to recreate and running project locally.

Dependencies

Here, list all libraries, packages and other dependencies that need to be installed to run your project. Include library versions and how should be installed if a special requirement is needed.

Opsional

Download, install and setup to get more speed using internal GPU Using: CUDA 11.2 cuDNN 8.1.1 TensorRT 8.2.2.1

• Pandas 2.2.3

  pip install pandas==2.2.3

• OpenCV 1.0.0

  pip install cv==1.0.0

• Numpy 1.26.4

  pip install numpy==1.26.4

• Matplotlib 3.9.2

  pip install matplotlib==3.9.2

• Albumentations 3.9.2

  pip install albumentations==1.4.21

• Tensorflow 2.10.1

  pip install tensorflow==2.10.1

Installation

1. Clone the repo

   git clone https://github.com/FITS-AI/Machine_Learning_OCR.git

2. Running the table_extractor.ipynb

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch
3. Commit your Changes
4. Push to the Branch
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Authors

Theodorus Limbong - @linkedin - contacttheodorus@gmail.com

Acknowledgements

Acknowledge any individual, group, institution or service.

• off-nutrition-table-extractor

Thank you