Deep learning for fabric defect detection

Defects occur in the fabric production process due to machine-related errors or system faults. Deep learning solutions can be employed to increase the frequency and accuracy of detection, while reducing the time, cost and labour involved in textile manufacturing. While traditional models like convol...

Full description

Saved in:
Bibliographic Details
Main Author: Nangia, Saniya
Other Authors: Zheng Jianmin
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175318
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175318
record_format dspace
spelling sg-ntu-dr.10356-1753182024-04-26T15:42:34Z Deep learning for fabric defect detection Nangia, Saniya Zheng Jianmin School of Computer Science and Engineering ASJMZheng@ntu.edu.sg Computer and Information Science Deep learning Ensemble models Computer vision Defect detection Defects occur in the fabric production process due to machine-related errors or system faults. Deep learning solutions can be employed to increase the frequency and accuracy of detection, while reducing the time, cost and labour involved in textile manufacturing. While traditional models like convolutional neural networks can identify larger defects on solid-coloured fabrics, they are unable to accurately identify smaller defects, especially on a variety of patterned and textured fabrics. Single-stage models and transformer-based object detection models have resulted in vast improvements in model accuracy and efficiency. In this study, a modified StackBox ensemble method is implemented. The base models, YOLOv8 and RT-DETR, are fine-tuned on a dataset of patterned fabric defects to find the optimal model configurations. Their confidence scores are adjusted to reflect single or dual votes for predicted bounding boxes. Finally, a Support Vector Machine Regression meta-model is chosen to combine the predictions of both models, attaining a higher average precision and average recall than baseline models and other ensemble methods. A comparison is provided with Non-Maximum Suppression (NMS), Soft-NMS and Weighted Boxes Fusion ensemble techniques. The performance of models such as Cascade R-CNN, Faster R-CNN and RetinaNet is also analysed in comparison to the base models and modified StackBox method. Bachelor's degree 2024-04-23T06:24:31Z 2024-04-23T06:24:31Z 2024 Final Year Project (FYP) Nangia, S. (2024). Deep learning for fabric defect detection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175318 https://hdl.handle.net/10356/175318 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Deep learning
Ensemble models
Computer vision
Defect detection
spellingShingle Computer and Information Science
Deep learning
Ensemble models
Computer vision
Defect detection
Nangia, Saniya
Deep learning for fabric defect detection
description Defects occur in the fabric production process due to machine-related errors or system faults. Deep learning solutions can be employed to increase the frequency and accuracy of detection, while reducing the time, cost and labour involved in textile manufacturing. While traditional models like convolutional neural networks can identify larger defects on solid-coloured fabrics, they are unable to accurately identify smaller defects, especially on a variety of patterned and textured fabrics. Single-stage models and transformer-based object detection models have resulted in vast improvements in model accuracy and efficiency. In this study, a modified StackBox ensemble method is implemented. The base models, YOLOv8 and RT-DETR, are fine-tuned on a dataset of patterned fabric defects to find the optimal model configurations. Their confidence scores are adjusted to reflect single or dual votes for predicted bounding boxes. Finally, a Support Vector Machine Regression meta-model is chosen to combine the predictions of both models, attaining a higher average precision and average recall than baseline models and other ensemble methods. A comparison is provided with Non-Maximum Suppression (NMS), Soft-NMS and Weighted Boxes Fusion ensemble techniques. The performance of models such as Cascade R-CNN, Faster R-CNN and RetinaNet is also analysed in comparison to the base models and modified StackBox method.
author2 Zheng Jianmin
author_facet Zheng Jianmin
Nangia, Saniya
format Final Year Project
author Nangia, Saniya
author_sort Nangia, Saniya
title Deep learning for fabric defect detection
title_short Deep learning for fabric defect detection
title_full Deep learning for fabric defect detection
title_fullStr Deep learning for fabric defect detection
title_full_unstemmed Deep learning for fabric defect detection
title_sort deep learning for fabric defect detection
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/175318
_version_ 1814047304688074752