Carpet Back Sizing Quality Assessment by Measuring the Amount of Resin Using Image Processing and Machine Learning Approaches

Mohammad Ehsan Momeni Heravi; Mohammad Hossein Moattar

doi:10.14502/tekstilec.66.2023053

Authors

Mohammad Ehsan Momeni Heravi Department of Textile and Fashion Design, Mashhad Branch, Islamic Azad University, Mashhad, Iran Author
Mohammad Hossein Moattar Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran Author https://orcid.org/0000-0002-8968-6744

DOI:

https://doi.org/10.14502/tekstilec.66.2023053

Keywords:

carpet quality assessment, carpet back sizing, digital image processing, machine learning, edge detection

Abstract

The mechanical properties of the carpet, such as dimensional stability, bending stiffness, handle and creeping on the surface during use, have a direct relationship with the amount of resin applied to the back of the carpet in the sizing process. In today’s factories, the optimal amount of resin and the mechanical quality of the carpet are controlled by the operator touching the carpet on the machine carpet finishing line or manually while rolling the carpet. Proposed in this paper is an automatic method based on the evaluation of the bending stiffness of the sized carpet that uses digital image processing and machine learning to measure the optimal amount of size concentration and control this index. For this purpose, during the final stage of carpet production, the carpet is folded in the middle, and two edges of the carpet are placed on top of each other. A side view image is then taken of the carpet. Using edge detection methods, the edges of the carpet are identified, and different features, such as the average, maximum and minimum statistics for the curve and contour angles, are then extracted. Different conventional machine learning approaches, such as KNN, CART and SVM, are applied. To evaluate the proposed method, a dataset containing 220 different images is used in a 10-fold cross-validation scheme. Different performance measures resulting from the evaluations demonstrate the effectiveness and applicability of the method.

Downloads

Download data is not yet available.

References

ÖNDER, Emel, BERKALP, Ömer Berk. Effects of different structural parameters on carpet physical properties. Textile Research Journal, 2001, 71(6), 549–555, doi: 10.1177/004051750107100613. DOI: https://doi.org/10.1177/004051750107100613

DAYIARY, M., SHAIKHZADEH NAJAR, S., SHAMSI, M. A new theoretical approach to cut-pile carpet compression based on elastic-stored bending energy. The Journal of the Textile Institute, 2009, 100(8), 688–694, doi: 10.1080/00405000802170242. DOI: https://doi.org/10.1080/00405000802170242

DAYIARY, M., SHAIKHZADEH, NAJAR S., SHAMSI, M. An experimental verification of cut-pile carpet compression behavior. The Journal of the Textile Institute, 2010, 101(6), 488–494, doi: 10.1080/00405000802542242. DOI: https://doi.org/10.1080/00405000802542242

GENTRY, David R. Dimensional stability of carpets in installation: part I: stability to mechanical actions. Textile Research Journal, 1977, 47(7), 459–463, doi: 10.1177/004051757704700703. DOI: https://doi.org/10.1177/004051757704700703

ERDOĞAN, Ümit Halis. Effect of pile fiber cross section shape on compression properties of polypropylene carpets. The Journal of the Textile Institute, 2012, 103(12), 1369–1375, doi: 10.1080/00405000.2012.685558. DOI: https://doi.org/10.1080/00405000.2012.685558

TAYLAN, Osman, DARRAB, Ibrahim A. Fuzzy control charts for process quality improvement and product assessment in tip shear carpet industry. Journal of Manufacturing Technology Management, 2012, 23(3), 402–420, doi: 10.1108/17410381211217434. DOI: https://doi.org/10.1108/17410381211217434

STUART, I.M., BAIRD, K. A new test for bending length. Textile Research Journal, 1966, 36(1), 91–93, doi: 10.1177/004051756603600112. DOI: https://doi.org/10.1177/004051756603600112

ZHOU, Naiyue, GHOSH, Tushar K. On-line measurement of fabric bending behavior: part I: theoretical study of static fabric loops. Textile Research Journal, 1997, 67(10), 712–719, doi: 10.1177/004051759706701003. DOI: https://doi.org/10.1177/004051759706701003

ZHOU, Naiyue, GHOSH, Tushar K. On-line measurement of fabric-bending behavior: background, need and potential solutions. International Journal of Clothing Science and Technology, 1998, 10(2), 143–156, doi: 10.1108/09556229810213845. DOI: https://doi.org/10.1108/09556229810213845

CASSIDY, T., CASSIDY, C., CASSIE, S., ARKISON, M. The stiffness of knitted fabrics: a new approach to the measurement of bending: part 1: development. International Journal of Clothing Science and Technology, 1991, 3(5), 14–19, doi: 10.1108/eb002982. DOI: https://doi.org/10.1108/eb002982

XU, B. Assessing carpet appearance retention by image analysis. Textile Research Journal, 1994, 64(12), 697–709, doi: 10.1177/004051759406401201. DOI: https://doi.org/10.1177/004051759406401201

QUINONES, Rolando, ORJUELA, Sergio A., ORTIZ-JARAMILLO, Benhur, VAN LANGENHOVE, Lieva, PHILIPS, Wilfried. Quantifying appearance retention in carpets using geometrical local binary patterns. In Advanced Concepts for Intelligent Vision Systems. ACIVS 2011. Lecture Notes in Computer Science, vol 6915. Edited by Jacques Blanc-Talon, Richard Kleihorst, Wilfried Philips, Dan Popescu and Paul Scheunders. Berlin, Heidelberg : Springer, 2011, doi: 10.1007/978-3-642-23687-7_30. DOI: https://doi.org/10.1007/978-3-642-23687-7_30

SHADY, Ebraheem, QASHQARY, Khadijah, HASSAN, Mounir, MILITKY, Jiri. Image processing based method evaluating fabric structure characteristics. Fibres & Textiles in Eastern Europe, 2012, 6A(95), 86–90.

HOSSEINI, Sayedeh Marjaneh, MOHHAMAD-DJAFARI, Ali, MOHAMMADPOUR, Adel, MOHAMMADPOUR, Sobhan, NADI, Mohammad. Carpets color and pattern detection based on their images. Proceedings, 2019, 33(1), 1–7, doi: 10.3390/proceedings2019033028. DOI: https://doi.org/10.3390/proceedings2019033028

SERRANO, Ana, MEIJER, Suzan, VAN RIJN, Rick R., COBAN, Sophia Bethany, REISSLAND, Birgit, HERMENS, Erma, BATENBURG, Kees Joost, VAN BOMMEL, Maarten. A non-invasive imaging approach for improved assessments on the construction and the condition of historical knotted-pile carpets. Journal of Cultural Heritage, 2021, 47, 79–88, doi: 10.1016/j.culher.2020.09.012. DOI: https://doi.org/10.1016/j.culher.2020.09.012

GÜRBÜZ, Feyza, EYI, Sabiha Unal. New carpet pattern design with deep learning. Journal of Engineering Research, 2023, online first, doi: 10.36909/jer.16781. DOI: https://doi.org/10.36909/jer.16781

LI, Ming, HAM, Chan, WANG, Ying. Similarity inspection and optimal arrangement of carpet images using deep learning and genetic algorithms. In IEEE 2020 SoutheastCon Proceedings. Raleigh : IEEE, 2020, 1–2, doi: 10.1109/SoutheastCon44009.2020.9249722. DOI: https://doi.org/10.1109/SoutheastCon44009.2020.9249722

RUSS, John C. The image processing handbook. Boca Raton : CRC Press, Taylor & Francis, 2007.

GOLABI, Sasan, SAADAT, Saiid, HELFROUSH, Mohammad Sadegh, TASHK, Ashkan. A novel thinning algorithm with fingerprint minutiae extraction capability. International Journal of Computer Theory and Engineering, 2012, 4(4), 514–517, doi: 10.7763/IJCTE.2012.V4.522. DOI: https://doi.org/10.7763/IJCTE.2012.V4.522