Abstract
Clothing helps to enhance the wearer’s appearance, so many people pay attention to choosing clothes to suit the events they attend. Nowadays, e-commerce websites are growing strongly, while products are also increasingly diverse and abundant in all areas of life, especially apparel, and clothes with many different types and brands. Therefore, finding appropriate clothes with only an image is challenging. This collected ordinary clothes types in Vietnam, then fine-tuned the model of You Only Look Once (YOLO) version of 5l to provide better accuracy with smaller image size in clothes recognition in the image compared to the original one YOLOv5l with default values of hyper-parameters, and previous YOLO versions. As a result, the method obtains an accuracy of 0.933 in clothes detection on over 10,000 images of 18 clothes types, including popular clothes in Vietnam. The work is expected to provide an image-based useful search for e-commerce systems.
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
References
Hsiao, W.L., Grauman, K.: From culture to clothing: discovering the world events behind a century of fashion images (2021). https://doi.org/10.48550/ARXIV.2102.01690
Jocher, G.E.A.: Ultralytics/yolov5: v7.0 - yolov5 sota realtime instance segmentation (2022). https://doi.org/10.5281/ZENODO.3908559, https://zenodo.org/record/3908559
Jouanneau, W., Bugeau, A., Palyart, M., Papadakis, N., Vezard, L.: Where are my clothes? a multi-level approach for evaluating deep instance segmentation architectures on fashion images. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE (2021). https://doi.org/10.1109/cvprw53098.2021.00443
Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014). abs/1405.0312
Shajini, M., Ramanan, A.: An improved landmark-driven and spatial–channel attentive convolutional neural network for fashion clothes classification. Vis. Comput. 37(6), 1517–1526 (2020). https://doi.org/10.1007/s00371-020-01885-7
Tian, Q., Chanda, S., Kumar, K.C.A., Gray, D.: Improving apparel detection with category grouping and multi-grained branches (2021). https://doi.org/10.48550/ARXIV.2101.06770
Xu, S., Li, X., Wang, J., Cheng, G., Tong, Y., Tao, D.: Fashionformer: A simple, effective and unified baseline for human fashion segmentation and recognition. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 545–563. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19836-6_31
Yang, X.S.: Nature-inspired optimization algorithms: challenges and open problems. J. Comput. Sci. 46, 101104 (2020). https://doi.org/10.1016/j.jocs.2020.101104
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, H.T., Nguyen, K.K., T.-N.-Diem, P., T.-Dien, T. (2023). Clothing Detection and Classification with Fine-Tuned YOLO-Based Models. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds) Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023. Lecture Notes in Computer Science(), vol 13925. Springer, Cham. https://doi.org/10.1007/978-3-031-36819-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-36819-6_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36818-9
Online ISBN: 978-3-031-36819-6
eBook Packages: Computer ScienceComputer Science (R0)