Neural network enhanced automatic garment measurement system

• Autorzy: Kowaleczko Paweł , Rokita Przemysław , Szczuka Marcin

Identyfikatory

DOI

10.15439/2022F8

• Konferencja: 17th Conference on Computer Science and Intelligence Systems
• Języki publikacji: EN

Abstrakty

EN

The measurement of garments is most often a verylaborious task. Automatic garment measurement systems may be thus a great convenience in fashion e-commerce cataloguing issues. In this paper, we propose an automatic garment measurement system that uses classical computer vision algorithms, as well as an error correction neural network, which reduces the overall error. We make use of data collected by our partner, which contains photographs of garments with ArUco markers. Using such data, we estimate the coordinates of feature points, which are used to calculate a specific size of a garment. We apply the error correction neural network to this measured size to minimize the error. The conducted experiments show, that our method is a useful tool that meets the requirements of practicality and its results are comparable with the current state of the art methods. Additionally, our error correction neural network is a novelty in the field of automatic garment measurement and there is no need for the garments templates, which are used in the previous solutions.

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 32
• Strony: 33--38
• Opis fizyczny: Bibliogr. 9 poz., rys., tab.

Twórcy

autor

Kowaleczko Paweł

• Institute of Computer Science, Warsaw University of Technology ul. Nowowiejska 15/19, 00-665 Warsaw, Poland
• QED Software sp. z o.o. ul.Miedziana 3A/18, 00-814 Warsaw, Poland

autor

Rokita Przemysław

• Institute of Computer Science, Warsaw University of Technology ul. Nowowiejska 15/19, 00-665 Warsaw, Poland

autor

Szczuka Marcin

• Institute of Informatics, University of Warsaw Banacha 2, 02-097 Warsaw, Poland
• BAKERS sp. z o.o. ul. Branickiego 11/154, 02-972 Warsaw, Poland

Bibliografia

• 1. S. Chevalier, Retail e-commerce sales worldwide from 2014 to 2024. URL https://www.statista.com/statistics/379046/worldwide-retail-e-commerce-sales/
• 2. A. Rosebrock, Detecting ArUco markers with OpenCV and Python - an online tutorial. URL https://www.pyimagesearch.com/2020/12/21/detecting-aruco-markers-with-opencv-and-python/
• 3. J. Juvonen, Study of the automatic garment measurement, report prepared for ROBOCOAST EU network by Aarila Dots Oy. (2019). URL https://new.robocoast.eu/wp-content/uploads/2020/09/Feasibility-study-Automatic-garment-measurement_Aarila-Dots.pdf
• 4. L. Cao, Y. Jiang, M. Jiang, Automatic measurement of garment dimensions using machine vision, in: 2010 International Conference on Computer Application and System Modeling (ICCASM 2010), Vol. 9, 2010, pp. V9-30-V9-33. http://dx.doi.org/10.1109/ICCASM.2010.5623093.
• 5. K. Chen, Image analysis technology in the automatic measurement of garment dimensions., Asian Journal of Information Technology 4 (9) (2005) 832-834. URL https://medwelljournals.com/abstract/?doi=ajit.2005.832.834
• 6. C. Li, Y. Xu, Y. Xiao, H. Liu, M. Feng, D. Zhang, Automatic measurement of garment sizes using image recognition, in: Proceedings of the International Conference on Graphics and Signal Processing, ACM, 2017, pp. 30-34. http://dx.doi.org/10.1145/3121360.3121382.
• 7. G. Bradski, A. Kaehler, The OpenCV Library, Dr. Dobb’s Journal of Software Tools 3 (2000).
• 8. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, Pytorch: An imperative style, high-performance deep learning library, in: H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, R. Garnett (Eds.), Advances in Neural Information Processing Systems (NeurIPS 2019), Vol. 32, Curran Associates, Inc., 2019. http://dx.doi.org/10.48550/arXiv.1912.01703. URL https://arxiv.org/abs/1912.01703
• 9. W. Falcon, et al., PyTorch Lightning, gitHub repository. (2019). URL https://github.com/PyTorchLightning/pytorch-lightning

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).