Mattingly "AI & Prompt Design: Named Entity Recognition"
templates.pptx
1. Real Time Defect Identification of White Fabric in Textile Industry
using Computer Vision
2. Name of Student Muhammad Arslan Ansari
Regd. No. 2019-uam-2751
Supervisory Committee
i. Dr. Ayesha Hakim : (Supervisor)
ii. Dr. Aamir Hussain : (Member)
iii. Dr. Nasir Nadeem : (Member)
5. Introduction
• The quality assurance of fabrics is a major problem in the textile
manufacturing industry. Automatic detection of defects is the most
important and challenging tasks. In order to guarantee fabric quality,
automatic detection of defects is the most challenging task. In Pakistan,
many industries have to bear the cost of defective products. Traditional
manual inspection is a labour-intensive process. Manual inspection of
fabric defects is unreliable that is seriously affected by factors including
varying light intensity, fatigue, and the experience-level of the
inspector.
7. Objectives
• To Identify the following defects in white fabric:
o Horizontal or vertical stripes.
o Yarn missing
o Bunching up
o Stains
• Comparative analysis of machine learning techniques for defect
identification
8. Dataset
• The data is collecting from local textile industry manually by
capturing an image from HD camera that captures the image in
such a clear way that looks like a human eye see the images. The
captured image has features that defect images. The defects can
be in multiple forms either by yarn missing in figure 1.1 , stains in
figure 1.2, bunching up in figure1.3, vertical stripes in figure 1.4.
12. References
• Arivazhagan, S., Ganesan, L., and Bama, S. 2006. Fault segmentation in fabric images using
Gabor wavelet transform. Machine Vision and Applications, 16(6), 356.
• Bumrungkun, P. 2019, April. Defect detection in textile fabrics with snake active contour and
support vector machines. In Journal of Physics: Conference Series (Vol. 1195, No. 1, p.
012006). IOP Publishing.
• Çelik, H. İ., Dülger, L. C., and Topalbekiroğlu, M. 2014. Development of a machine vision
system: real-time fabric defect detection and classification with neural networks. The
Journal of The Textile Institute, 105(6), 575-585.
• Jing, J. F., Ma, H., and Zhang, H. H. 2019. Automatic fabric defect detection using a deep
convolutional neural network. Coloration Technology, 135(3), 213-223.
• Li, Y., Zhang, D., and Lee, D. J. 2019. Automatic fabric defect detection with a wide-
andcompact network. Neurocomputing, 329, 329-338.
• Lizarraga-Morales, R. A., Correa-Tome, F. E., Sanchez-Yanez, R. E., and Cepeda-Negrete, J.
2019. On the use of binary features in a rule-based approach for defect detection on
patterned textiles. IEEE Access, 7, 18042-18049.