top of page

Trash Detection System 🗑️🔍

Project Type: Group ProjectTechnologies Used: Python, TensorFlow/Keras, OpenCV, CNN, YOLO, Pandas, Matplotlib, SeabornDataset: Custom Labeled Trash Images

Overview

This project focused on developing an object detection system to classify and identify trash in images. Our team built and compared two deep learning models: a Convolutional Neural Network (CNN) and YOLO (You Only Look Once). The goal was to determine the best-performing model in terms of accuracy and efficiency. I was responsible for developing and optimizing the CNN model.

Key Contributions

Model Development: Implemented a CNN model using TensorFlow/Keras to detect and classify trash items.

Data Preprocessing: Labeled and augmented image data, applied resizing, and normalized pixel values.

Training & Optimization: Experimented with different architectures, dropout rates, and batch sizes to improve model performance.

Evaluation & Comparison: Compared CNN with YOLO based on accuracy, precision-recall, and inference speed.

Visualization: Created bounding box visualizations and accuracy/loss plots to analyze model performance


🔗 Interactivity & Links

📌 GitHub Repository: (https://github.com/mqarmout/TACO_object_detection.git)

📌Live Demo:( http://35.224.185.15:5000/)

Would you like to tweak any details or add more metrics?

R

© 2024 by Yonatan .

bottom of page