Scribd
Upload
8 views

Waste Materials Using Deep Learning and Image

Detection of Waste Materials Using Deep Learning and Image

Uploaded by

manshakthi0
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views

Waste Materials Using Deep Learning and Image

Detection of Waste Materials Using Deep Learning and Image

Uploaded by

manshakthi0
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Detection of Waste Materials Using Deep Learning and Image

Processing
ABSTRACT

Process of segregating waste prompts the generation of energy out of waste, diminishing
landfills, recycling, and reduction of waste. Erroneous disposal of waste leads to recycling
contamination. Contamination is a tremendous issue to the recycling industry that can be
alleviated with automatic computerized waste sorting. The presence of models or strategies
which help people to sort trash has become extremely important in the right discard of that
garbage. Even though there are various sorts of recycling categories, many people remain
confused or cannot appropriately recognize how to decide the right trash bin to dispose of
every trash. Waste management and systematic sorting of them are considered to be a
significant role in ecological development around the world. Society needs to lessen waste by
recycling and reusing discarded materials that result in reducing environmental problems. This
project aims to create an automated waste detection system using a deep learning algorithm
MobileNetV2. that will gather the waste images or videos from a camera with object
recognition, detection & prediction, and categorize the waste materials like glass, metal, paper,
plastic, and trash so that the waste can be properly dumped in the recyclable and non-
recyclable bin.

MobileNetV2, a lightweight and efficient CNN, combined with the COCO dataset, enables
accurate and efficient object detection. Its speed and adaptability make it ideal for real-world
applications on resource-constrained platforms like mobile devices. The model achieves
impressive results, making it a practical solution for various object detection scenarios with low
memory and power requirements.

System requirements:

 Processor i3 or above
 Disk space 500 GB minimum
 Ram 8 GB minimum
Software requirements:

 Anaconda navigator
 Spyder ide
 Python 3

You might also like