Skip to content

Latest commit

 

History

9 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

♻️ PlasticClassifier: Advanced CNN for Waste Sorting

LinkedIn Email


Plastic pollution is a big global problem, and sorting waste correctly is key to solving it. This project uses a CNN model to sort plastic waste into different types, making automated waste management easier.

Dataset

The dataset used for this project is the Waste Classification Data by Sashaank Sekar. It contains a total of 25,077 labeled images, divided into two categories: Organic and Recyclable. This dataset is designed to facilitate waste classification tasks using machine learning techniques.

Key Details

  • Total Images: 25,077
  • Training Data: 22,564 images (85%)
  • Test Data: 2,513 images (15%)
  • Classes: Organic and Recyclable
  • Purpose: To aid in automating waste management and reducing the environmental impact of improper waste disposal

Approach

  • Reviewed various waste management strategies and relevant white papers.
  • Examined the composition of household waste.
  • Divided the waste into two categories: Organic and Recyclable.
  • Leveraged IoT and machine learning to automate the waste classification process.

Dataset Link

You can access the dataset here: Waste Classification Data

Note: Ensure appropriate dataset licensing and usage guidelines are followed.

Weekly Progress

This section will be updated weekly with progress details and corresponding Jupyter Notebooks.

Week 1: Libraries, Data Import, and Setup

Date: 20th January 2025 – 27th January 2025

Activities

  • Imported the required libraries and frameworks.
  • Set up the project environment.
  • Explored the dataset structure.

Note: If the file takes too long to load, you can view the Kaggle notebook directly: Kaggle Notebook.

Technologies Used

  • Python
  • TensorFlow/Keras
  • OpenCV
  • NumPy
  • Pandas
  • Matplotlib

Future Scope

  • Expanding the dataset to include more plastic waste categories.
  • Deploying the model as a web or mobile application for real-time use.
  • Integration with IoT-enabled waste management systems.

Contributing

Contributions are welcome! If you would like to contribute, please open an issue or submit a pull request.


Made with ❤️ by Neha Maurya
📧 mauryaneha2006@gmail.com  |  🔗 LinkedIn

About

Plastic pollution is a big global problem, and sorting waste correctly is key to solving it. This project uses a CNN model to sort plastic waste into different types, making automated waste management easier .

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages