Abstract
The present method of segregating solid waste material is hand picking method and it is prone to dangerous to waste picker’s health because of harmful substances into garbage. So to simplify this process, an automated computer vision-based system will be able to segregate the waste using object detection method. The feature extraction of different solid waste material images is an essential task before object detection. We have used Trashnet dataset along with custom dataset which contains small scale waste materials so as to classify and detect the small scale objects effectively. We have tested and analysed a well-known deep learning models like VGG16, VGG19, ResNet50 and AlexNet, as a result after experimentation we found that VGG16 has 98% training accuracy, 76% test accuracy and data augmentation was applied to increase the accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adedeji O, Wang Z et al (2019) Intelligent waste classification system using deep learning convolutional neural network. In: 2nd international conference on sustainable materials processing and manufacturing
Melinte DO et al (2020) Deep convolutional neural networks object detector for real-time waste identification MDPI. Appl Sci 2020(10):7301
Murthy CB et al (2020) Investigations of object detection in images/videos using various deep learning techniques and embedded platforms—a comprehensive review. Appl Sci 10:3280
Wadmare J, Patil S (2020) Improvising weakly supervised object detection (WSOD) using deep learning technique 9(3). ISSN: 2249–8958
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: ICLR 2015
Xiao J, Wang J (2020) Application of a novel and improved VGG-19 network in the detection of workers wearing masks. J Phys Conf Series, CMVIT 2020
Zhang KHX (2015) Deep Residual learning for image recognition, computer vision and pattern recognition, arXiv:1512.03385
Krizhevsky A et al (2017) ImageNet classification with deep convolutional neural networks, communications of the ACM, vol 60, no 6
Thung GT, GitHub repository. Available online: https://github.com/garythung/trashnet
Brintha VP, Rekha R, Nandhini J, Sreekaarthick N, Ishwaryaa B, Rahul R (2020) Automatic classification of solid waste using deep learning. In: Proceedings of international conference on artificial intelligence, smart grid and smart city applications
Sreelakshmi K, Akarsh S (2019) Capsule neural networks and visualization for segregation of plastic and non-plastic wastes. In: 5th international conference on advanced computing & communication systems (ICACCS)
Nowakowski P, Pamuła T (2020) Application of deep learning object classifier to improve e-waste collection planning. Elsevier
Adedeji O, Wang Z (2019) Intelligent waste classification system using deep learning convolutional neural network 2nd international conference on sustainable materials processing and manufacturing. Available online at www.sciencedirect.com Procedia Manufacturing
Seredkin AV et al (2019) Development of a method of detection and classification of waste objects on a conveyor for a robotic sorting system. J Phys: Conf Ser 1359:012127
Rabano SL, Cabatuan MK, Sybingco E, Dadios EP, Calilung EJ (2018) Common garbage classification using MobileNet IEEE
Singh D (2021) Polyth-Net: classification of polythene bags for garbage segregation using deep learning. In: International conference on sustainable energy and future electric transportation
Bird JJ, Faria DR (2018) A study on CNN transfer learning for image classification. In: Conference on computational intelligence
Wang Y, Li Y et al (2020) The influence of the activation function in a convolution neural network model of facial expression recognition. Appl Sci 10:1897
Salman S, Liu X (2019) Overfitting mechanism and avoidance in deep neural networks. arXiv:1901.06566v1
Acknowledgements
This work was shortlisted for the final round of Avishkar Research convention and appreciated this work in Hackathon-2021 on “Recycling Metals, Plastics & Scrap Tyres: Circular Economy Road map to Build a Green India”
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wadmare, J.G., Patil, S.R. (2022). A Vision-Based Approach for Solid Waste Materials Feature Extraction Using Deep Learning Techniques. In: Bhalla, S., Bedekar, M., Phalnikar, R., Sirsikar, S. (eds) Proceeding of International Conference on Computational Science and Applications . Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-19-0863-7_9
Download citation
DOI: https://doi.org/10.1007/978-981-19-0863-7_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0862-0
Online ISBN: 978-981-19-0863-7
eBook Packages: EngineeringEngineering (R0)