Neural network approach to classify defect types in cotton yarns

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.