Abstract
Textile is one of the basic and important aspects in present fashion era. We cannot imagine world without textile. Fabric quality control is also a fundamental issue in the textile manufacturing industry. Automatic fabric defect detection is considered to be of great interest for detection of different kinds of defects like hole, slub, oil stains, etc. This work provides a new approach for detection of faults and defects from the given fabric samples. Textile defect detection comprises five basic steps: image acquisition where the image samples are collected from standard TILDA dataset followed by preprocessing method in which grayscale transformation is applied for removing the unwanted noise and improving the image quality, gray-level co-occurrence matrix (GLCM) is considered for feature extraction where 13 features: contrast, correlation, entropy, autocorrelation, energy, dissimilarity, correlation, homogeneity, cluster shade, maximum probability, contrast inverse difference, sum of square, and standard division DCT are used with 1000 fabric image samples for the comparative study. Proposed work outperforms with 95% using neural network and 85% using SVM. The neural network (NN) classifier is used for classification of normal and defective fabrics. Finally, defect localization and the fabric identification are implemented for identifying whether the fabric sample used is defective or normal fabric.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
S.R. Kurkute, P.S. Sonar, S.A. Shevgekar, D.B. Gosavi, DIP based automatic fabric fault detection. Int. Res. J. Eng. Technol. 4(4), 3356–3360 (2017)
W. Wang, B. Xin, N. Deng, J. Li, Objective Evaluation on Yarn Hairiness Detection Based Multi-View Imaging and Processing Method (Elsevier, 2019), vol. 148, pp. 1–8
K. Yıldız, Z. Yıldız, O. Demir, A. Buldu, Determination of yarn twist using image processing techniques. in International Conference on Image Processing, Production and Computer Science (ICIPCS'2015) Istanbul (Turkey), ICIPCS (2015), pp. 83–88
V. Kaplan, N.Y. Varan, M. Dayik, Y. Turhan, G. Durur, Detection of warp elongation in satin woven cotton fabrics using image processing. Fibres Amp. Text. Estern Europe 24(4), 62 (2016)
K. Hanbay, M.F. Talu, O.F. Ozguven, Fabric defect detection system and methods ‘A systematic literature review’. Int. J. Light Electron Optics 127(24), 11960–11973 (2016)
M. Jmali, F. Sakli, B. Zitouni, Fabrics defects detecting using image processing and neural networks & quot. IEEE Int. Conf. Appl. Res. Text. 4, 1–4 (2014)
R.D. Karnik, L.S. Admuthe, Density evaluation and weave pattern classification of fabric using image processing. Int. J. Eng. Res. Technol. 10, 452–456 (2017)
P. Singh, P. Singh, Texture analysis in fabric material for quality evaluation using GLCM matrix. Int. J. Appl. Eng. Technol. 5, 1–5 (2015)
G.V. Vasant, M.D. Patil, Cotton contaminants automatic identification techniques. Int. J. Emerg. Technol. Innovative Eng. 1(5), 63–66 (2015)
M. Garg, G. Dhiman, Deep convolution neural network approach for defect inspection of textured surface. J. Inst. Electron. Comput. (2), 28–38 (2020)
P. Anandan, R.S. Sabeenian, Fabric defect detection using discrete curvelet transform. Int. Conf. Robot. Smart Manuf. (RoSMa2018) 133, 1056–1065 (2018)
S. Mei, Y. Wang, G. Wen, Automatic fabric defect detection with a multi scale convolutional denoising auto encoder network model. MDPI J. 18(4), 1–18 (2018)
L. Weninger, M. Kopaczka, D. Merhof, Defect detection in plain weave fabrics by yarn tracking and fully convolutional network. In IEEE 2018 International instrumentation and measurement technology conference (12MTL), IEEE (2018), pp.1–6
A. Hamdi, M.S. Sayed, M.M. Fouad, M.M. Hadhoud, Unsupervised patterned fabric defect detection using texture filtering and K-means clustering. in 2018 International conference on innovative trends in computer engineering, ITCE (2018), pp.130–144
S.L. Bangare, N.B. Dhawas, V.S. Taware, S.K. Dighe, P.S. Bagmare, Implementation of fabric fault detection system using image processing. Int. J. Res. Advent Technol. 5(6), 115–119 (2017)
Y. Li, W. Zhao, J. Pan, Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Trans. Autom. Sci. Engi. 14(2), 1256–1264 (2017)
L. Tong, W.K. Wong, C.K. Kwong, Fabric defect detection for apparel industry anonlocal sparse representation approach. IEEE 5, 5947–5964 (2017)
H. Abdellah, R. Ahmed, O. Slimane, Defect detection and identification in textile fabric by SVM method. IOSR J. Eng. (IOSRJEN) 04(12), 69–77 (2014)
R.S. Mahagaonkar, S. Soma, A novel texture based skin melanoma detection using color GLCM and CS-LBP feature. Int. J. Comput. Appl. 171(5), 1–5 (2017)
G. Singh, G. Singh, M. Kaur, Performance evaluation of fabric defect detection using series of image processing algorithm and ANN operation. Int. J. Recent Trends Eng. Res. 2(5), 1–7 (2016)
Z. Xiaowei, F. Xiujuan, Fabric defect detection based on GLCM approach. in 6th International Conference on Information Engineering for Mechanics and Materials, ICIMM (2016), pp. 673–677
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Soma, S., Pooja, H. (2022). Machine Learning System for Textile Fabric Defect Detection Using GLCM Technique. In: Reddy, A.B., Kiranmayee, B., Mukkamala, R.R., Srujan Raju, K. (eds) Proceedings of Second International Conference on Advances in Computer Engineering and Communication Systems. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-16-7389-4_16
Download citation
DOI: https://doi.org/10.1007/978-981-16-7389-4_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7388-7
Online ISBN: 978-981-16-7389-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)