Skip to content

adnanegrb/PlasticSense

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🗑️ PlasticSense: Smart Waste Sorting, AI Module

Accuracy F1 Score Model Framework

PlasticSense is an AI-powered waste classification system developed at Sorbonne Université ( Fablab Laboratory ). An image of the waste is fed to a lightweight neural network that classifies it as recyclable or non-recyclable in real time.

📄 Full Technical Reports

For a complete and detailed breakdown of the methodology, dataset, model architecture, training pipeline, and results:

Language Report Details
🇬🇧 English PlasticSense_report_EN.pdf Transfer learning, MobileNetV3-Small fine-tuning, augmentations, Early Stopping, CosineAnnealingLR — full results: 97.7% test accuracy
🇫🇷 Français PlasticSense_rapport_FR.pdf Jeu de données, méthodologie complète, progression V1→V4, discussion des résultats

Everything is covered in detail in both reports, from the raw dataset construction to the final deployed model.

Results

  • 🎯 Test Accuracy : 97.7%
  • 📈 Best Validation Accuracy : 98.4%
  • ⚖️ F1 Score : 0.977
  • 🚩 Initial Target : 90% (exceeded by +7.7 points)

Progress across versions

Version Accuracy What changed
V1 68.4% Baseline model
V2 73.6% First dataset cleanup
V3 84.6% Added real iPhone photos
V4 97.7% Full optimized pipeline

How it works

Image input
     ↓
MobileNetV3-Small classifies
     ↓
Recyclable ♻️  /  Non-recyclable 🚯

Installation

git clone https://github.com/adnanegrb/PlasticSense.git
cd PlasticSense
pip install -r requirements.txt

Usage

Train the model:

python train.py

Run inference on a single image:

python inference.py --image path/to/image.jpg

Output example:

♻️  RECYCLABLE
   Confidence : 98.3%

Dataset

The dataset is not included in this repo. See dataset/README.md for download instructions.

8,832 images split into two classes: recyclable (plastic, paper, cardboard, metal) and non-recyclable (biological waste, mixed trash). Split: 80% train / 10% val / 10% test.

Model

MobileNetV3-Small pretrained on ImageNet, with the last 3 blocks unfrozen for fine-tuning. Trained with AdamW optimizer, CosineAnnealingLR scheduler, WeightedRandomSampler, and Early Stopping (patience = 3).

Author

Mohammed Adnane Garab — Sorbonne Université
GitHub

License

MIT License

About

AI-powered plastic detection and classification system using computer vision. Identifies and categorizes plastic waste types for recycling and environmental monitoring. Real-time inference with high accuracy.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages