A Data-Driven Texture Analysis of Textile Surfaces for Adaptive Control of Handling Processes
DOI:
https://doi.org/10.52825/th-wildau-ensp.v3i.3519Keywords:
Texture Analysis, Intelligent Material Handling, Robot-Assisted Assembly Processes, Image RecognitionAbstract
This paper introduces a modular AI-based gripper system featuring automated texture analysis of textile surfaces for adaptive handling in clothing automation. A dataset of 55 textile classes was captured with a high-resolution industrial camera, preprocessed into 256×256px-patches via Laplacian variance, and augmented to 1400 balanced images. Classical texture features (LBP, GLCM, HOG, DCT, Wavelet, Gabor) and ResNet18 CNN embeddings were extracted and evaluated using stratified 5-fold cross-validation with SVM, Random Forest, Decision Tree, and MLP classifiers. Hybrid approaches combine handcrafted and deep features for robust material identification, enabling dynamic grip parameterization and seamless integration into robotic processes.
Downloads
References
[1] T. Ojala, M. Pietikainen und T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on pattern analysis and machine intelligence, Jg. 24, Nr. 7, S. 971–987, 2002.
[2] R. M. Haralick, K. Shanmugam und I. H. Dinstein, “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, Nr. 6, S. 610–621, 2007.
[3] A. Ramola, A. K. Shakya und D. Van Pham, “Study of statistical methods for texture
analysis and their modern evolutions,” Engineering Reports, Jg. 2, Nr. 4, e12149, 2020.
[4] J. Trommnau, A. Frommknecht, J. Siegert, J.W¨osner und T. Bauernhansl, “Design for automatic assembly: A new approach to classify limp components,” Procedia CIRP, Jg. 91, S. 49–54, 2020.
[5] J. Reiff-Stephan, “Automatisierte Handhabung biegeschlaffer Materialien,” TH Wildau-Wissenschaftliche Beiträge, S. 72–76, 2013.
[6] S. Herz und A.-M. Schmidt, “Materialcharakterisierung für die Simulation der Handhabung von Textilien,” 2024.
[7] L. Liu, L. Zhao, Y. Long, G. Kuang und P. Fieguth, “Extended local binary patterns for
texture classification,” Image and Vision Computing, Jg. 30, Nr. 2, S. 86–99, 2012.
[8] L. Zhang, J. Jing und H. Zhang, “Fabric defect classification based on LBP and GLCM,”Journal of Fiber Bioengineering and Informatics, Jg. 8, Nr. 1, S. 81–89, 2015.
[9] A. G. Zuniga, J. B. Florindo und O. M. Bruno, “Gabor wavelets combined with volumetric fractal dimension applied to texture analysis,” Pattern Recognition Letters, Jg. 36, S. 135–143, 2014.
[10] J. Zhou u. a., “The Effects of GLCM parameters on LAI estimation using texture values from Quickbird Satellite Imagery,” Scientific Reports, Jg. 7, Nr. 1, S. 7366, 2017.
[11] D. Belila, B. Khaldi und O. Aiadi, “Wavelet texture descriptor for steel surface defect classification,” Materials, Jg. 17, Nr. 23, S. 5873, 2024.
[12] T. J. Offor, I. I. Ayogu, J. N. Odii, N. Macdonald, K. K. A. Oparauwah und E. O. Mbah,
“Texture analysis in corrosion management: A scoping review,” 2025.
[13] A. Bodnarova, M. Bennamoun und S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern recognition, Jg. 35, Nr. 12, S. 2973–2991, 2002.
[14] G. Sorwar und A. Abraham, “DCT based texture classification using soft computing approach,” arXiv preprint cs/0405013, 2004.
[15] N. Dalal und B. Triggs, “Histograms of oriented gradients for human detection,” in 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), Ieee, Bd. 1, 2005, S. 886–893.
[16] F. Mirzapour u. a., “Fast GLCM and Gabor filters for texture classification of very high resolution remote sensing images,” 2015.
[17] S. T. M. Ataky, D. Saqui, J. de Matos, A. de Souza Britto Junior und A. Lameiras Koerich, “Multiscale analysis for improving texture classification,” Applied Sciences, Jg. 13, Nr. 3, S. 1291, 2023.
[18] P. Simon und V. Uma, “Deep learning based feature extraction for texture classification,” Procedia Computer Science, Jg. 171, S. 1680–1687, 2020.
[19] E. d. S. Puls, M. V. Todescato und J. L. Carbonera, “An evaluation of pre-trained models for feature extraction in image classification,” arXiv preprint arXiv:2310.02037, 2023.
[20] M. A. Khawaja u. a., “Beyond relighting: RTI for clustering fragmented heritage textiles using deep learning,” npj Heritage Science, Jg. 14, Nr. 1, S. 95, 2026.
[21] S. R. Arshad und M. K. Shahzad, “Deep learning based fabric defect detection,” Research Reports on Computer Science, S. 1–11, 2024.
[22] J.-F. Jing, H. Ma und H.-H. Zhang, “Automatic fabric defect detection using a deep convolutional neural network,” Coloration Technology, Jg. 135, Nr. 3, S. 213–223, 2019.
[23] L. Tan, Q. Fu und J. Li, “An improved neural network model based on DenseNet for fabric texture recognition,” Sensors, Jg. 24, Nr. 23, S. 7758, 2024.
[24] S. Zhong, M. Ribul, Y. Cho und M. Obrist, “TextileNet: a material taxonomy-based fashion textile dataset,” arXiv preprint arXiv:2301.06160, 2023.
[25] P. K. Khandappa und M. S. Haladappa, “Deepsoilnet: A CNN-Based Framework With
Gabor And LBP Feature Fusion For Automated Soil Texture Classification From Field
Images 2025,” International Journal of Environmental Sciences, S. 1608–1616, Juli 2025.
[26] Y. Zhu, J. Huang, T. Wu und X. Ren, “Identification method of cashmere and wool based on texture features of GLCM and Gabor,” Journal of Engineered Fibers and Fabrics, Jg. 16, S. 1 558 925 021 989 179, 2021.
[27] T. El Ghayed, C. Falk, S. Wilbers, R. van de Sand und J. Reiff-Stephan, “Modellansatz
zur Prozessoptimierung beim hydroadhäsiven Greifen,” 2023.
[28] E. Hecht, Optics, 1. Aufl. Pearson, 2016, ISBN: 978-0133977226.
[29] M. Hohner, Optical Formulas, English, Accessed: 2026-02-26, Michael Hohner Photography, Juni 2023. besucht am 26. Feb. 2026. Adresse: https://www.mhohner.de/formulas.php.
[30] K. Schindler, “Mathematical foundations of photogrammetry,” Springer Books, S. 3087–3103, 2015.
[31] J. C. M. Edward M Mikhail James S. Bethel, Introduction To Modern hotogrammetry,
1. Aufl. WILEY, 2012, ISBN: 978-8126539987.
[32] C. Xu, Y. Tao, X. Guo und H. He, “High-fidelity and efficient particle microscopy via regional focus search and adaptive focus stacking,” Scientific Reports, 2026.
[33] F. Memon, M. A. Unar und S. Memon, “Image quality assessment for performance evaluation of focus measure operators,” Mehran University Research Journal of Engineering & Technology, Jg. 34, Nr. 4, S. 379–386, 2015.
[34] H. Dogan, R. O. Dogan, I. Ay und S. F. Sezen, “Dl-edof: Novel multi-focus image data set and deep learning-based approach for more accurate and specimen-free extended depth of focus,” Journal of Imaging Informatics in Medicine, Jg. 37, Nr. 4, S. 1991–2013, 2024.
[35] L. Perez und J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” arXiv preprint arXiv:1712.04621, 2017.
[36] S. van der Walt u. a., “scikit-image: image processing in Python,” PeerJ Computer
Science, Jg. 2, e453, 2014.
[37] H. J. Weerts, A. C. Mueller und J. Vanschoren, “Importance of tuning hyperparameters of machine learning algorithms,” arXiv preprint arXiv:2007.07588, 2020.
[38] M. Bhagat und B. Bakariya, “A comprehensive review of cross-validation techniques in machine learning,” IJSAT-International Journal on Science and Technology, Jg. 16, Nr. 1, 2025.
[39] M. Sokolova und G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information processing & management, Jg. 45, Nr. 4, S. 427–437, 2009.
[40] J. Erbani, P.-E. Portier, E. Egyed-Zsigmond, S. B. Mokhtar und D. Nurbakova, “On the
Normalization of Confusion Matrices: Methods and Geometric Interpretations,” arXiv preprint arXiv:2509.04959, 2025.
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Constantin Falk, Andreas Krispin, Janine Breithecker, Saide Kanal, Norman Günther, Jörg Reiff-Stephan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Funding data
-
Bundesministerium für Wirtschaft und Energie
Grant numbers 01IF23426N