A Review on Recyclable Material Classification using Deep Learning

DOI

10.2991/978-94-6463-858-5_105How to use a DOI?

Keywords

Waste Management; Deep Learning; Convolution Neural Networks; Sensor Fusion; AI powered systems

Abstract

The growing concerns about urbanization and environmental troubles make waste management a crucial hassle worldwide. Conventional garbage segregation is bulky, much less efficient, and at risk of mistake, which means there is a dire need for present day high-tech automated trash sorting technology. Recent innovations in sensor and deep learning technology paint an optimistic picture of waste segregation efficiency. Other strategies that this review covers are Convolutional Neural Networks such as EfficientNet, InceptionNet, hybrid models like CNN-LSTM that have been overly accurate in waste type among many others. Such systems often include sensors including gas and near-infrared (NIR) sensors for improving the identification and sorting of several waste items. Still, there exist several challenges for this invention, such as low variability in datasets, dependence on sensor, and a real time processing problem. The existence of performance barriers for sensor significantly reduces the overall efficiency of modern construction mainly attributed to dark color plastics and complex types of waste. Future research efforts aim towards solving these issues through usage of increasingly complex methods of fusion of sensors, increase the datasets, and also through the improved real-time processing capabilities. Such developments in technology may be quite promising concerning AI-driven waste management systems in relation to the reduction of environmental impact and enhanced recycling, significantly supporting sustainable urban living. This review paper will delve deeper into a few of the works carried out in this region to identify gaps and suggest future directions.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kanna Vinoothna
AU  - Mardhav Paluvai
AU  - Keloth Tanuja
AU  - S. M. Naveen  Raja
PY  - 2025
DA  - 2025/11/04
TI  - A Review on Recyclable Material Classification using Deep Learning
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1261
EP  - 1270
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_105
DO  - 10.2991/978-94-6463-858-5_105
ID  - Vinoothna2025
ER  -