| Title | CompostNet: An Image Classifier for Meal Waste |
|---|---|
| ID_Doc | 67556 |
| Authors | Frost, S; Tor, B; Agrawal, R; Forbes, AG |
| Title | CompostNet: An Image Classifier for Meal Waste |
| Year | 2019 |
| Published | |
| Abstract | Many businesses, cafes, and outdoor spaces provide trash, recycling, and composting bins, requiring consumers to decipher instructional text, icons, or images in order to sort their waste accurately. It can be confusing to know what pieces of waste go in which bin. Moreover, different areas may have different rules for how to separate waste, and people often inadvertently throw their trash in the wrong bin. Machine learning solutions can help us more quickly and accurately choose the proper receptacle for our waste by classifying a photograph of the waste. This paper presents a novel image classification model that categorizes the types of waste produced after eating a meal, which can be used in mobile applications to encourage users to correctly sort waste. Building on recent work in deep learning and waste classification, we introduce CompostNet, a convolutional neural network that classifies images according to how they should be appropriately discarded. We provide details about the design and development of CompostNet, along with an evaluation of its effectiveness in classifying images of waste. Further, we discuss two different approaches to the design of our system, one using a custom model and the other augmenting a pre-trained image classification model (MobileNet) through transfer learning, and and how we achieved greater success with the transfer learning approach. To the best of our knowledge, CompostNet is the first waste classification system that uses a deep learning network to identify compostable, recyclable, and landfill materials. CompostNet is an application of machine learning for social good, and supports United Nations Sustainable Development Goal 12: Responsible Consumption and Production [1]. |
Similar Articles
| ID | Score | Article |
|---|---|---|
15841
|
Nnamoko, N; Barrowclough, J; Procter, J Solid Waste Image Classification Using Deep Convolutional Neural Network(2022)Infrastructures, 7, 4 | |
| 44275
|
Khan, HA; Naqvi, SS; Alharbi, AAK; Alotaibi, S; Alkhathami, M Enhancing trash classification in smart cities using federated deep learning(2024)Scientific Reports, 14, 1 | |
| 9686
|
Chand, P; Assaf, M An Empirical Study on Lightweight CNN Models for Efficient Classification of Used Electronic Parts(2024)Sustainability, 16.0, 17 | |
| 43656
|
Oguz, A; Ertugrul, OF Determining the fullness of garbage containers by deep learning(2023) | |
| 40504
|
Malik, M; Prabha, C; Soni, P; Arya, V; Alhalabi, WA; Gupta, BB; Albeshri, AA; Almomani, A Machine Learning-Based Automatic Litter Detection and Classification Using Neural Networks in Smart Cities(2023)International Journal On Semantic Web And Information Systems, 19, 1 | |
| 29681
|
Pellegrini, L; Maltoni, D; Graffieti, G; Lomonaco, V; Mazzini, L; Mondardini, M; Zappoli, M A weakly supervised approach for recycling code recognition(2023) | |
| 21734
|
Alonso, SLN; Forradellas, RFR; Morell, OP; Jorge-Vazquez, J Digitalization, Circular Economy and Environmental Sustainability: The Application of Artificial Intelligence in the Efficient Self-Management of Waste(2021)Sustainability, 13.0, 4 | |
| 25794
|
Waltner, G; Jaschik, M; Rinnhofer, A; Possegger, H; Bischof, H An Intelligent Scanning Vehicle for Waste Collection Monitoring(2022) | |
| 18866
|
Lu, WS; Chen, JJ Computer vision for solid waste sorting: A critical review of academic research(2022) | |
| 16303
|
Chen, CY; Yu, TT Towards a circular economy: Recapturing battery, metal, and plastic from soil-size and gravel-size municipal solid waste incineration bottom ash using convolutional neural networks(2023) |