Show simple item record

dc.contributor.author Amarathunga, S
dc.contributor.author Vidushka, K
dc.contributor.author Niles, SN
dc.contributor.author Abesooriya, RP
dc.contributor.editor Niles, SN
dc.contributor.editor Nandasiri, GK
dc.contributor.editor Pathirana, M
dc.contributor.editor Madhurangi, C
dc.date.accessioned 2023-11-22T09:14:06Z
dc.date.available 2023-11-22T09:14:06Z
dc.date.issued 2023-08-31
dc.identifier.citation Amarathunga, S., Vidushka, K., Niles, S.N., & Abesooriya, R.P. (2023). Neural network approach to classify defect types in cotton yarns. In S.N. Niles, G. K. Nandasiri, M. Pathirana, & C. Madhurangi (Eds.), Proceedings of the Textile Engineering Research Symposium 2023 (pp. 20-21). Department of Textile and Apparel Engineering, University of Moratuwa. http://dl.lib.uom.lk/handle/123/21695
dc.identifier.uri http://dl.lib.uom.lk/handle/123/21695
dc.description.abstract Accurate identification and classification of defects in cotton yarns are crucial for ensuring the quality and consistency of textile products. Defects can lead to compromised fabric quality, reduced durability, and increased production costs.[ 1] Machine learning techniques like neural networks and support vector machines have been traditionally used for defect detection [2,3], but they struggle with the complex patterns in yarn defects. Recent advances in image processing and deep learning, specifically convolutional neural networks (CNNs), offer promising results for image classification tasks [4], making them suitable for defect identification in cotton yarns. Existing studies have been limited in scope, focusing on specific defects and datasets, hindering the development of a comprehensive defect classification model. This research project aims to address this gap by creating a diverse dataset of various yarn defects, leveraging image processing to improve image quality. The proposed approach utilizes CNNs and transfer learning to build an efficient defect classification model, and its effectiveness will be evaluated against ground truth labels and industry standards. Accordingly, this study presents a solution with potential contributions to the textile industry's quality assurance processes, enhancing product quality and reducing production-related challenges.
dc.language.iso en en_US
dc.publisher Department of Textile and Apparel Engineering en_US
dc.subject CNN en_US
dc.subject Yarn defects en_US
dc.subject Textile quality en_US
dc.subject machine learning en_US
dc.subject Transfer learning en_US
dc.title Neural network approach to classify defect types in cotton yarns en_US
dc.type Conference-Extended-Abstract en_US
dc.identifier.faculty Engineering en_US
dc.identifier.department Department of Textile and Apparel Engineering en_US
dc.identifier.year 2023 en_US
dc.identifier.conference Textile Engineering Research Symposium 2023 en_US
dc.identifier.place Moratuwa en_US
dc.identifier.pgnos pp. 20-21 en_US
dc.identifier.proceeding Proceedings of the Textile Engineering Research Symposium 2023 (TERS2023) en_US
dc.identifier.email sanjithahashan@gmail.com en_US
dc.identifier.email krishalviduska97@gmail.com en_US
dc.identifier.email niles@uom.lk en_US
dc.identifier.email rangaa@uom.lk en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record