https://github.com/imnotamr/vegetableclassificationappfehu

A Streamlit-based web application for vegetable classification using a deep learning model. Developed as part of a university project (This project is submitted to Dr. Ahmed Badawy and Eng. Noor Eldeen Magdy, Faculty of Engineering, Helwan University, as part of a coursework requirement).
https://github.com/imnotamr/vegetableclassificationappfehu

deep-learning helwan-university image-classification keras streamlit tensorflow

Last synced: about 1 month ago
JSON representation

A Streamlit-based web application for vegetable classification using a deep learning model. Developed as part of a university project (This project is submitted to Dr. Ahmed Badawy and Eng. Noor Eldeen Magdy, Faculty of Engineering, Helwan University, as part of a coursework requirement).

• Host: GitHub
• URL: https://github.com/imnotamr/vegetableclassificationappfehu
• Owner: imnotamr
• License: apache-2.0
• Created: 2024-12-21T21:31:27.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-12-22T19:44:37.000Z (about 2 months ago)
• Last Synced: 2024-12-22T20:30:32.537Z (about 2 months ago)
• Topics: deep-learning, helwan-university, image-classification, keras, streamlit, tensorflow
• Language: Python
• Homepage: https://vegetableclassificationfehu.streamlit.app/
• Size: 101 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

README

        
#  Vegetable Classification App

This project features a Vegetable Classification App, built using a state-of-the-art Convolutional Neural Network (CNN). The app allows users to upload images of vegetables and receive accurate classifications, along with confidence scores for each category.

Check out the App ---> [Vegetable Classification App](https://vegetableclassificationfehu.streamlit.app/) 

#  Features

###  Image Upload:

Upload vegetable images (JPG, PNG, or JPEG formats).

###  Deep Learning Model:

Utilizes a CNN trained on 15 vegetable classes for high accuracy.

###  Confidence Scores:

Visualizes classification probabilities with a bar chart.

###  Streamlit Deployment:

Easy-to-use interface accessible via a web browser.

### 📂 Project Structure

Vegetable-Classification-App/

├── streamlit_app.py          

├── requirements.txt          

├── model/

│   └── Vegetable_model_last.h5  

├── README.md                 

└── assets/                   

#  How It Works

## Upload an Image:

Users upload a vegetable image in JPG/PNG format.

## Model Prediction:

The app uses the pre-trained CNN to classify the vegetable.

## Display Results:

Predicted vegetable name and Confidence scores for all 15 classes, displayed as a bar chart.

### Supported Vegetable Classes:

Bean, Bitter_Gourd, Bottle_Gourd, Brinjal, Broccoli, Cabbage, Capsicum, Carrot, Cauliflower, Cucumber, Papaya, Potato, Pumpkin, Radish, Tomato

#  Deployment

Using Streamlit Cloud

The app is deployed via Streamlit Cloud for easy access. Check it out here:

Vegetable Classification App

#  Model Details

### Framework:

TensorFlow/Keras

### Model Type:

Convolutional Neural Network (CNN)

### Classes:

15 vegetable types

### Training Dataset:

High-resolution vegetable images

### Output Layer:

Softmax for multi-class classification

#  Contributing

Contributions are welcome! If you’d like to improve the model, app interface, or documentation:

1. Fork the repository.

2. Create a feature branch.

3. Submit a pull request.

   

#  License

This project is licensed under the MIT License. Feel free to use and modify the code as needed.

#  Acknowledgments

## Team Members:

Amr Ahmed, Mohamed Yasser, Omar Khaled, Ibrahim Mahmoud.

## Frameworks:

TensorFlow, Keras, Streamlit.

## Special Thanks:

Open-source communities for making this possible.

# Contact

If you have any questions or suggestions, feel free to reach out:

## Email: [email protected]

## GitHub: @imnotamr

### 🌟 Don’t forget to star the repository if you find it useful!