Towards artificially intelligent recycling Improving image processing for waste classification
Auteurs : Youpeng Yu, Ryan Grammenos
Résumé scientifique
The ever-increasing amount of global refuse is overwhelming the waste and recycling management industries. The need for smart systems for environmental monitoring and the enhancement of recycling processes is thus greater than ever. Amongst these efforts lies IBM's Wastenet project which aims to improve recycling by using artificial intelligence for waste classification. The work reported in this paper builds on this project through the use of transfer learning and data augmentation techniques to ameliorate classification accuracy. Starting with a convolutional neural network (CNN), a systematic approach is followed for selecting appropriate splitting ratios and for tuning multiple training parameters including learning rate schedulers, layers freezing, batch sizes and loss functions, in the context of the given scenario which requires classification of waste into different recycling types. Results are compared and contrasted using 10-fold cross validation and demonstrate that the model developed achieves a 91.21% test accuracy. Subsequently, a range of data augmentation techniques are then incorporated into this work including flipping, rotation, shearing, zooming, and brightness control. Results show that these augmentation techniques further improve the test accuracy of the final model to 95.40%. Unlike other work reported in the field, this paper provides full details regarding the training of the model. Furthermore, the code for this work has been made open-source and we have demonstrated that the model can perform successful real-time classification of recycling waste items using a standard computer webcam.
Les articles autour de lui, par date et par proximité
Plus haut, c’est plus proche de cet article ; à gauche, c’est plus ancien. Les traits relient les articles proches entre eux : les groupes de traits sont des sous-thèmes. Sélectionnez un point pour voir pourquoi il est là. Retour au résumé de cet article
Les articles autour de celui-ci
Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.
Les articles les plus proches
-
Enhancing Sustainability through Automated Waste Classification: A Machine Intelligence FrameworkA. Sleem · 2023 · Sustainable Machine Intelligence Journal · cité 7 fois · Pas encore résumé
Résumé scientifique
This study presents a novel framework integrating a deep learning image classifier into waste classification systems for enhancing sustainability. Leveraging diverse waste image datasets, our approach employs a convolutional neural network (CNN) architecture tailored for precise waste material identification and sorting from images. Through transfer learning and dataset augmentation techniques, the CNN model demonstrates robust performance in real-time waste categorization, surpassing conventional methods. Experimental validation using comprehensive waste image datasets showcases notable advancements in classification accuracy and operational efficiency. The results underscore the potential …
-
Efficient Source-Level Waste Segregation Using CNN-Based Waste Classifier with IoT-Enabled Smart Bins and Mobile ApplicationK. B. Shah, S. Visalakshi, B. Paneru et al. · 2025 · 2025 International Conference on Emerging Smart Computing and Informatics (ESCI) · cité 5 fois · Pas encore résumé
Résumé scientifique
Image processing and deep learning techniques have demonstrated their efficacy as valuable tools for classifying municipal solid waste. This study presents a comparative review of the recent advancement in waste classification techniques and their significance. Further, an attempt has been made to prepare a reliable dataset by integrating datasets from the public domain and web images. Architectures consisting of pre-trained models, namely Inception V3, ResNet, VGG19, DenseNet, and Xception, based on Convolution Neural Networks, were considered. In that process, it was observed that models Inception V3 and Xception were performing exceptionally well. Further, both the models were fine-tuned …
-
Convolutional Neural Network Based Technique for Efficient Waste ClassificationSoumadeep Sarkar, Saheb Sarkar, Somashree Gorai et al. · 2024 · 2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI) · cité 4 fois · Pas encore résumé
Résumé scientifique
Waste management has proved to be a significant environmental challenge due to the increasing global population and limited recycling efforts. This study proposes an approach using deep learning and computer vision techniques to automate waste sorting. By employing convolutional neural networks like ResNet50v2 and VGG16, along with Transfer Learning, a robust model capable of accurately categorizing waste for recycling and disposal has been developed. Through preprocessing and data augmentation techniques, we have tried to improve the performance of our models. Through our experiment, we have demonstrated that VGG16 and ResNet50 models are 93.45 and 93.02 percent accurate respectively. This …
-
Benchmarking Deep Learning Models For Automated Waste ClassificationMert Dönmez, S. Baghaee, Ilkay Ulusoy · 2025 · Signal Processing and Communications Applications Conference · cité 1 fois · Pas encore résumé
Résumé scientifique
Recycling is essential for reducing waste, conserving resources, and promoting a more sustainable and efficient use of materials. However, manual sorting is inefficient, prone to human error, and limits recycling efficiency. This study develops an automated waste sorting system using image recognition and deep learning to enhance recycling efficiency and accessibility.To achieve this, three deep learning models—google/vit-base-patch16-224, Falconsai/nsfw image detection, and microsoft/resnet-50 —are compared to determine the most suitable one based on accuracy and computational efficiency. The selected model powers an intelligent recycling system that uses image recognition to efficiently ca…
-
Leveraging Deep Learning and Convolutional Neural Network for Digital Waste Image ClassificationN. Fauzan, P. Sukmasetya, N. Nuryanto · 2025 · E3S Web of Conferences · cité 1 fois · Pas encore résumé
Résumé scientifique
Waste management is a significant environmental challenge, with 14 million tons of waste uncollected in 2023, accumulating at landfill sites. The mixing of household and industrial waste complicates adequate segregation. Baseline sorting techniques are costly in labor, time, and resources. This paper looks at the application of CNNs for the automated sorting of wastes to enhance speed, capacity, and precision. CNNs can be used to classify digital images of waste to minimize the manual work in waste management, especially on a large scale. The research evaluates two CNN architectures—ResNet101 and a custom-designed CNN model—aiming to enhance waste classification. The dataset includes images …
-
Implementation of Convolutional Neural Network in Image-Based Waste ClassificationAdila Qurrota A'Yun, S. Suhartono, T. Lestari · 2025 · JOURNAL OF APPLIED INFORMATICS AND COMPUTING · cité 3 fois · Pas encore résumé
Résumé scientifique
The increasingly complex issue of waste management, particularly in the sorting process, demands efficient and accurate technology-based solution. This study aims to implement the Convolutional Neural Network (CNN) method for image-based waste classification, focusing on two classes paper and plastic. The dataset used consists of 2000 images, with an 80% proportion for training and 20% for testing. This study tested four scenarios combining image augmentation and classification methods, namely threshold and one-hot encoding, and evaluated model performance using accuracy, precision, recall, and F1-score metrics. The best results were obtained in the scenario using image augmentation with the…
-
Garbage Image Classification Based on Deep Learning for Intelligent Waste SortingZi-Xiang Liu · 2026 · 2026 6th International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · cité 2 fois · Pas encore résumé
Résumé scientifique
Intelligent waste sorting is an important technical component of urban environmental governance, yet practical recycling procedures still rely heavily on manual recognition and sorting. Manual sorting is labor-intensive, inefficient, and vulnerable to subjective errors, especially when waste items are visually similar or contaminated. To improve the automation level of waste recognition, this paper investigates a deep-learning-based garbage image classification method on a public six-class garbage image dataset. A ResNet34 baseline without pretraining or data augmentation is first established. Then, an improved training scheme is designed by integrating transfer learning, online data augment…
-
MobileNetV2 Transfer Learning Implementation for Waste ClassificationF. Andriani, Ade Yuliati, Anis Yaturahmah et al. · 2026 · Indonesian Applied Research Computing and Informatics · Pas encore résumé
Résumé scientifique
Waste management issues represent one of the major challenges in maintaining environmental sustainability, as the waste sorting process is still largely performed manually, requiring significant time and effort and relying heavily on human accuracy, which makes it inefficient and prone to errors. Therefore, this study utilizes Artificial Intelligence (AI) technology as a solution to support more effective and sustainable environmental management by proposing the use of the Convolutional Neural Network (CNN) algorithm to classify waste types based on digital images. The data used consist of waste images as inputs in the image processing stage, which are then classified into several waste cate…
Les travaux antérieurs sur lesquels il s’appuie
-
Fine-Tuning Models Comparisons on Garbage Classification for RecyclabilityU. Ozkaya, L. Seyfi · 2019 · arXiv.org · preprint, non relu par les pairs · cité 62 fois · Pas encore résumé
Résumé scientifique
In this study, it is aimed to develop a deep learning application which detects types of garbage into trash in order to provide recyclability with vision system. Training and testing will be performed with image data consisting of several classes on different garbage types. The data set used during training and testing will be generated from original frames taken from garbage images. The data set used for deep learning structures has a total of 2527 images with 6 different classes. Half of these images in the data set were used for training process and remaining part were used for testing procedure. Also, transfer learning was used to obtain shorter training and test procedures with and high…
-
WasteNet: Waste Classification at the Edge for Smart BinsGary White, Christian Cabrera, Andrei Palade et al. · 2020 · Computer Vision and Pattern Recognition · preprint, non relu par les pairs · cité 68 fois · Pas encore résumé
Résumé scientifique
Smart Bins have become popular in smart cities and campuses around the world. These bins have a compaction mechanism that increases the bins' capacity as well as automated real-time collection notifications. In this paper, we propose WasteNet, a waste classification model based on convolutional neural networks that can be deployed on a low power device at the edge of the network, such as a Jetson Nano. The problem of segregating waste is a big challenge for many countries around the world. Automated waste classification at the edge allows for fast intelligent decisions in smart bins without needing access to the cloud. Waste is classified into six categories: paper, cardboard, glass, metal, …
-
Automatic Image-Based Waste ClassificationVictoria Ruíz, Á. Sánchez, J. F. Vélez et al. · 2019 · International Work-Conference on the Interplay Between Natural and Artificial Computation · cité 110 fois · Pas encore résumé
-
A Novel Framework for Trash Classification Using Deep Transfer LearningA. H. Vo, Le-Ho-Ang Son, Minh Thanh Vo et al. · 2019 · IEEE Access · cité 178 fois · Pas encore résumé
Résumé scientifique
Nowadays, society is growing and crowded, the construction of automatic smart waste sorter machine utilizing the intelligent sensors is important and necessary. To build this system, trash classification from trash images is an important issue in computer vision to be addressed for integrating into sensors. Therefore, this study proposes a robust model using deep neural networks to classify trash automatically which can be applied in smart waste sorter machines. Firstly, we collect the VN-trash dataset that consists of 5904 images belonging to three different classes including Organic, Inorganic and Medical wastes from Vietnam. Next, this study develops a deep neural network model for trash …
-
Data Analytics Platform for the Optimization of Waste Management ProceduresThanasis Vafeiadis, Alexandros Nizamis, V. Pavlopoulos et al. · 2019 · International Conference on Distributed Computing in Sensor Systems · cité 10 fois · Pas encore résumé
Résumé scientifique
Today, the use of IoT devices, the inter-connectivity of machines and systems, and the development of novel analytic algorithms which are main characteristics of Industry 4.0 are also transferred to other domains connected to the industrial one. The advances on industrial domain have impact on waste management one as these domains are strictly connected. The connection with sensors on industrial partners premises, the big data availability and the significant advances on data analytics, enable the waste management companies to smarten their domain and automate many of their solutions and processes. In this work, we present a data analytics platform for the optimization of waste management pr…
Les articles qui le citent
-
Improving the Deployment of Recycling Classification through Efficient Hyper-Parameter AnalysisMazin Abdulmahmood, R. Grammenos · 2021 · arXiv.org · preprint, non relu par les pairs · cité 3 fois · Pas encore résumé
Résumé scientifique
The paradigm of automated waste classification has recently seen a shift in the domain of interest from conventional image processing techniques to powerful computer vision algorithms known as convolutional neural networks (CNN). Historically, CNNs have demonstrated a strong dependency on powerful hardware for real-time classification, yet the need for deployment on weaker embedded devices is greater than ever. The work in this paper proposes a methodology for reconstructing and tuning conventional image classification models, using EfficientNets, to decrease their parameterisation with no trade-off in model accuracy and develops a pipeline through TensorRT for accelerating such models to ru…
-
CNN Based Smart Waste Segregation and Collection SystemV. Lavanya, G. Shivam, S. Shanmugasundaram et al. · 2024 · International Conference Design, Engineering and Computer Sciences · cité 11 fois · Pas encore résumé
Résumé scientifique
Waste management is an increasing concern in urban areas worldwide, because of population growth and environmental sustainability goals. To address this challenge, this paper presents a Convolutional Neural Network (CNN)-based waste segregation and collection system that uses the power of computer vision and machine learning. The proposed system is used to automate the process of waste segregation, optimizing the sorting of waste into bio-degradable, reusable, recyclable waste and trash in real time. Utilizing a camera for capturing the images of incoming waste materials and moving the waste at their respective collection points. The images are processed using a deep learning YOLOv8 model, w…
-
A Smart Recycling Bin Using Waste Image Classification At The EdgeXueying Li, Ryan Grammenos · 2022 · Computer Vision and Pattern Recognition · preprint, non relu par les pairs · cité 3 fois · Pas encore résumé
Résumé scientifique
Rapid economic growth gives rise to the urgent demand for a more efficient waste recycling system. This work thereby developed an innovative recycling bin that automatically separates urban waste to increase the recycling rate. We collected 1800 recycling waste images and combined them with an existing public dataset to train classification models for two embedded systems, Jetson Nano and K210, targeting different markets. The model reached an accuracy of 95.98% on Jetson Nano and 96.64% on K210. A bin program was designed to collect feedback from users. On Jetson Nano, the overall power consumption of the application was reduced by 30% from the previous work to 4.7 W, while the second syste…
-
IWEEWS: AN INTELLIGENT WASTE EXTRACTOR FOR EFFICIENT WASTE SEGREGATION BY USING DEEP LEARNING TECHNIQUEYash Bobde M, B. Jothi, Akshat Sharma · 2023 · International Journal of Engineering Applied Sciences and Technology · cité 3 fois · Pas encore résumé
Résumé scientifique
Waste segregation is a top priority in many countries across the world. Even in this day and age, many individuals are unable to discern between biodegradable, recyclable, and landfill waste. As a result, the world is currently dealing with a serious basic issue with garbage disposal. In this study, we use deep learning algorithms to handle the trash categorization problem. Organic waste, recyclable rubbish, and landfill garbage are the three major types of waste. A way to speed up the whole process is by doing waste sorting, which could be done by computer using image recognition. CNNs have gradually been used in a number of intelligent trash identification and recycling applications during…
-
Eco-Evolution: Transforming Waste Management Through Convolutional Neural Network Parameter Evolution With OptimizersM. Ali Shah, M. Jan, A. Ullah · 2025 · Cureus Journal of Computer Science · cité 2 fois · Pas encore résumé
Résumé scientifique
Recycling waste materials is critical to reducing the environmental effects of increased waste production. Proper waste separation is critical for speeding recycling procedures. This research uses advanced optimization algorithms to handle the difficulty of classifying waste materials. The complexity of waste material composition and diversity pose a significant challenge for accurate classification, requiring advanced classification algorithms. Convolutional neural networks (CNNs) have developed as effective methods for image classification, such as waste material sorting. However, adjusting CNN parameters to optimize classification accuracy remains a key area of study. This paper suggests …
Aller plus loin
Comment ces articles sont-ils trouvés ?
Nous comparons le titre et le résumé de cet article avec ceux de tous les articles résumés sur ce site, et avec les articles que Semantic Scholar recommande, ceux qu’il cite et ceux qui le citent (pour un article très cité, ses citations les plus récentes et, depuis OpenAlex, les plus citées). Parmi les travaux antérieurs et les suites, les articles qui s’utilisent en profondeur, une méthode qu’il utilise et les suites très citées remontent un peu. Les niveaux (très proche, proche, apparenté) viennent de la similarité des textes, pas d’un jugement de qualité ; * signale un article sans résumé, comparé par son titre. La phrase sous un article est écrite par une IA à partir des deux résumés : vérifiez-la dans les articles. Un article jugé hors sujet par trois lecteurs quitte la liste.
Mis à jour le 5 novembre 2026.