Defect detection in textiles using back propagation neural classifier

Subrata Das; Amitabh Wahi; Suresh Jayaram

doi:10.5937/zasmat2303308D

Autori

Subrata Das Bannari Amman Institute of Technology, Department of Fashion Technology, Sathyamangalam, Erode Dist., Tamil Nadu, India Autor
Amitabh Wahi Bhagwant University, Department of Computer Science & Engineering, Ajmer, Rajasthan, India Autor
Suresh Jayaram Sky Cotex India Private Limited, Tirupur, Tamil Nadu, India Autor

DOI:

https://doi.org/10.5937/zasmat2303308D

Ključne reči:

klasifikacija defekata, rupe, debela mesta, veštačka neuronska mreža, karakteristike, pletenine

Apstrakt

Tekstilni proizvodi su pogođeni defektima tokom procesa proizvodnje. To je, takođe, rasipanje resursa koji se koriste za proizvodnju i zauzvrat utiče na poslovanje. Ručna inspekcija u otkrivanju kvarova se danas ne podstiče u proizvodnom procesu. Kompjuterski vid sa algoritmima mašinskog učenja u automatizovanom sistemu kontrole kvaliteta igra važnu ulogu u otkrivanju nedostataka u proizvodnom procesu, kao i analizi kvaliteta proizvoda. Klasifikacija nedostataka pletene tkanine je aktivna oblast istraživanja širom sveta. Ovaj rad predstavlja metod klasifikacije za otkrivanje nedostataka kao što su rupe i debela mesta na pletenini primenom algoritma veštačke neuronske mreže. Algoritmi veštačke neuronske mreže uče iz ulaznih podataka nakon uspešnog procesa obuke, predviđa prirodu nepoznatih uzoraka na veoma brz i precizan način. Predloženi radovi se odvijaju u dve faze. U prvoj fazi su slike neispravnih uzoraka dve klase prikupljene kamerom visoke rezolucije. Slike uzoraka u boji su pretvorene u slike u sivoj skali. Karakteristike su izvučene iz svake slike u sivoj skali i uskladištene u bazi podataka. U drugoj fazi je obučen neuronski klasifikator sa algoritmom neuronske mreže sa povratnom propagacijom (BPNN) na skupu podataka za obuku. Nakon uspešne obuke neuronske mreže na skupu podataka o vozu, performanse obučene neuronske mreže su procenjene na test skupu podataka. Različiti eksperimenti su sprovedeni povećanjem broja uzoraka podataka za obuku; utvrđeno je da je najbolji učinak ocenjivanja dobijen sa 83,3%.

Reference

Ben, S., Nasri, S. (2010) Automatic recognition of woven fabrics based on texture and using SVM: Signal, image and video processing. Springer-Verlag London, 4: 429-463

https://doi.org/10.1007/s11760-009-0132-5

Bishop, C.M. (1995) Neural network for pattern recognition. Oxford: Oxford University Press

https://doi.org/10.1093/oso/9780198538493.001.0001

Ch, L., Li, J., Li, Y., He, L., Fu, X., Chen, J. (2021) Fabric defect detection in textile manufacturing: A survey of the state of the art.Security and Communication Network, ID 9948808

https://doi.org/10.1155/2021/9948808

Choonjong, K., Ventura, J.A., Tofang-Sazi, K. (2000) A neural network approach for defect identifcation and classifcation on leather fabric.Journal of Intelligent Manufacturing, 11: 485-499

https://doi.org/10.1023/A:1008974314490

Das, S., Wahi, A., Keerthika, S., Thulasiramand, N., Sundaramurthy, S. (2019) Automated defect detection of woven fabric using Artificial Neural Network.Man Made Textiles in India, 47 (4), 113-115

Denuth, H., Mark, H. (2002) The Matlab version 7.5: User guide. USA: The Math Works Inc

Elragal (2016) Neuro-Fuzzy fabric defect detection and classification for knitting machine. in: 23rd National Radio Science Conference (NRSC 2006)

https://doi.org/10.1109/NRSC.2006.386359

Guodong, S., Zhen, Z., Gao, Y., Xu, Y., Xu, L., Lin, S. (2019) A fast fabric defect detection framework for multi-layer convolutional neural network based on histogram back-projection.IEICE Trans. Inf. & Syst, E102-D (12), 2504-2514

https://doi.org/10.1587/transinf.2019EDP7092

Hanbay, K., Talu, M.F., Özgüven, Ö.F., Öztürk, D. (2019) Real-time detection of knitting fabric defects using Shearlet transform.Tekstil ve Konfeksiyon, 29(1): 3-10

https://doi.org/10.32710/tekstilvekonfeksiyon.482888

https://doi.org/10.32710/tekstilvekonfeksiyon.448737

Hoffer, M.L., Francini, F., Tiribilli, B., Longobardi, G. (1996) Neural networks for the optical recognition of defects in cloth.Opt. Eng, 35 (11), 3183-3190

https://doi.org/10.1117/1.601057

Kadir, S.A., Gürkan, Y.A. (2017) Stacked autoencoder method for fabric defect detection.Cumhuriyet University Faculty of Science, Science Journal (CSJ), 38(2): 343-354

https://doi.org/10.17776/cumuscij.300261

Kumar, A. (2003) Neural network-based detection of local textile defects.Pattern Recognition, 36, 1645-1659

https://doi.org/10.1016/S0031-3203(03)00005-0

Kumar, A., Shen, C.H. (2002) Texture inspection for defects using neural networks and support vector machines. in: IEEE international conference on ICIP, p.352-356

https://doi.org/10.1109/ICIP.2002.1038978

Lal, R.J., Sunil, K., Ankit, C. (2013) Fabric defect detection based on GLCM and Gabor filter: A comparison.Optik, 124(23): 6469-6474

https://doi.org/10.1016/j.ijleo.2013.05.004

Ngan, H.Y.T., Grantham, P.K.H., Nelson, Y.H.C. (2011) Automated fabric defect detection: A review.Image and Vision Computing, 29(7): 442-458

https://doi.org/10.1016/j.imavis.2011.02.002

Rasheed, A., Zafar, B., Rasheed, A., Nouman, A., Sajid, M., Dar, S.H., Habib, U., Shehryar, T., Mahmood, M.T. (2020) Fabric defect detection using computer vision techniques: A comprehensive review.Mathematical Problems in Engineering, 1, 24

https://doi.org/10.1155/2020/8189403

Rebhi, A., Benmhammed, I., Saberur, A., Farhat, F. (2015) Fabric defect detection using local homogeneity analysis and neural network.Journal of Photonics, ID 376163, 1-9

https://doi.org/10.1155/2015/376163

Shadika, P., Mulyana, T., Rendra, M. (2017) Optimizing woven curtain fabric defect classification using image processing with artificial neural network method at PT Buana Intan Gemilang.MATEC Web of Conferences, 135, 1-9

https://doi.org/10.1051/matecconf/201713500052

Tarck, M.H., Rokonuzzman, M. (2011) Distinguishing feature selection for fabric defect classification using neural network.Journal of multimedia, 6(5), 416-424

https://doi.org/10.4304/jmm.6.5.416-424

Tarek, M.H., Hossain, F.R., Rokonuzzaman, M., Farruk, A. (2014) Automated fabric defect inspection: A survey of classifiers.International Journal in Foundations of Computer Science & Technology (IJFCST), 4(1): 17-25

https://doi.org/10.5121/ijfcst.2014.4102

Wang, W., Deng, N.A., Xin, B. (2020) Sequential detection of image defects for patterned fabrics.IEEE Access, 8: 174751-174762

https://doi.org/10.1109/ACCESS.2020.3024695

Zhiqiang, K., Chaohui, Y., Qian, Y. (2013) The fabric defect detection technology based on wavelet transform and neural network convergence. in: Proceedings of IEEE International conference on information and automation, p.597-601

https://doi.org/10.1109/ICInfA.2013.6720367