DATA AUGMENTATION METHOD TO IMPROVE THE QUALITY OF E-COMMERCE IMAGE RECOGNITION
Article Sidebar
Main Article Content
Abstract
In the rapidly evolving landscape of e-commerce, the visual representation of products plays a pivotal role in engaging consumers and driving conversion rates. This article introduces a new approach for image augmentation that includes objects segmentation, dominant color determination, background replacement and realistic shadow generation. These steps collectively contribute to the creation of augmented images that are used not only in the electronic catalogues but enrich abilities of the neural networks with various and fortified training data. Developed system allows to solve problems related to class imbalance and to enhance model generalization as well as to improve the quality of recognition.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Shorten, C., Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, (6), 60. DOI: 10.1186/s40537-019-0197-0.
Wang, J., Zhang, W., Zang, Y., Cao, Y., Pang, J., Gong, T., … Lin, D. (2021). Seesaw Loss for Long-Tailed Instance Segmentation. In 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) (9690–9699). IEEE. DOI: 10.1109/CVPR46437.2021.00957.
Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., & Feng, J. (2020). Overcoming Classifier Imbalance for Long-Tail Object Detection with Balanced Group Softmax. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (10988–10997). IEEE. DOI: 10.1109/CVPR42600.2020.01100.
Tan, J., Lu, X., Zhang, G., Yin, C., & Li, Q. (2020). Equalization Loss v2: A New Gradient Balance Approach for Longtailed Object Detection. In 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) (1685–1694). IEEE. DOI: 10.1109/CVPR46437.2021.00173.
Esposito, C., Landrum, G. A., Schneider N., Stiefl N., & Riniker, S. (2021). GHOST: Adjusting the Decision Threshold to Handle Imbalanced Data in Machine Learning. J. Chem. Inf. Model., 61(6), 2623–2640. DOI: 10.1021/acs.jcim.1c00160.
Chen, Y, Hu, V. T., Gavves, E., Mensink, T., Mettes, P., Yang, P. & Snoek C. G. M. (2020). PointMixup: Augmentation for Point Clouds. In A. Vedaldi, H. Bischof, T. Brox, & J. M. Frahm (Eds.), Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol. 12348 (330–345). Springer, Cham. DOI: 10.1007/978-3-030-58580-8_20.
Ghiasi G., Cui, Y., Srinivas, A., Qian, R., Lin, T.-Y., Cubuk, E. D., … Zoph, B. (2021). Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation. In 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) (2917–2927). IEEE. DOI: 10.1109/CVPR46437.2021.00294.
Devries, T., & Taylor, G. W. (2017). Improved Regularization of Convolutional Neural Networks with Cutout. ArXiv, (1708.04552). DOI: 10.48550/arXiv.1708.04552.
Sorokina, V., & Ablameyko, S. (2021). Neural Network Training Acceleration by Weight Standardization in Segmentation of Electronic Commerce Images. In C. van Gulijk, & E. Zaitseva (Eds.), Reliability Engineering and Computational Intelligence. Studies in Computational Intelligence: Vol. 976 (237–244). Springer, Cham. DOI: 10.1007/978-3-030-74556-1_14.
Sorokina, V., & Ablameyko, S. (2023). 2D Cast Shadow Generation in E-commerce Image Using UNet Vision Transformer. In 2023 International Conference on Information and Digital Technologies (IDT) (31–36). IEEE. DOI: 10.1109/IDT59031.2023.10194446.
Ronneberger, O., Fischer, P., Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. Wells, & A. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science. Vol. 9351 (234–241). Springer, Cham. DOI: 10.1007/978-3-319-24574-4_28.