Tools
Tools
Dhande, Kalpesh Jagdish (2022) Waste Classification system using Transfer Learning and Image Segmentation. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration manual)
Download (11MB) | Preview |
Abstract
Waste is a big issue in many regions of the world. Many countries are dealing with the issue of waste management. Every day, tons of rubbish is created, and the majority of this waste ends up in landfills. In most places, the process of classification is carried out by people, exposing them to health problems due to an unhygienic working environment, especially in developing and under-developed countries. On top relying on humans makes this entire process prone to human errors as humans experience sentiments, and have their biases and assumptions. Utilizing image classification and deep learning algorithms to separate recyclable garbage from organic waste is one strategy to address this problem. Both the health hazards are decreased and the procedure is made more effective as a result. So, in this research study, I created a model that identified garbage as recyclable or organic by employing transfer learning models such as VGG16 and DenseNet-121. I utilized image segmentation to segment the image, which was then submitted to the model to categorize. I obtained an accuracy of 87 % percent for the VGG 16 model and a 90 % accuracy for the DenseNet-121 model. Multiclass segmentation may be used to improve the image segmentation model even more in future.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TD Environmental technology. Sanitary engineering Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 24 Jan 2023 11:31 |
| Last Modified: | 06 Mar 2023 13:34 |
| URI: | https://norma.ncirl.ie/id/eprint/6108 |
Actions (login required)
 |
View Item |