Efficient Image Retrieval in Fashion: Leveraging Clustering and Principal Component Analysis for Search Space Reduction

Year 2024, Volume: 17 Issue: 3, 638 - 649, 31.12.2024

Başak Esin Köktürk Güzel

https://doi.org/10.18185/erzifbed.1500279

Abstract

In this study, a novel approach using clustering techniques and Principal Component Analysis (PCA) for reducing the search space in fashion image retrieval systems is introduced. The study focuses on extracting high-dimensional feature vectors from images of clothing items and finding the same or the most similar product using these feature vectors, thereby narrowing the search space. The proposed method employs unsupervised learning algorithms to analyze high-dimensional fashion image feature vectors, grouping them into meaningful clusters. This enhances search efficiency and improves user experience. By reducing the dimensionality of feature vectors with PCA, computational costs are minimized. Experimental results demonstrate that the proposed method significantly accelerates computation time while maintaining an acceptable level of accuracy.

Keywords

Fashion search, fashion image retrieval, clustering, principal component analysis, Resnet50, VGG19

Supporting Institution

KOSGEB

Project Number

68KIB

Thanks

This project is supported by the KOSGEB’s R&D, Product Development, and Innovation Support Program grant number 68KIB.

References

• [1] S. Shirkhani, H. Mokayed, R. Saini, and H. Y. Chai, “Study of AI-Driven Fashion Recommender Systems,” SN Comput Sci, vol. 4, no. 5, p. 514, 2023, doi: 10.1007/s42979-023-01932-9.
• [2] X. Li, X. Wang, X. He, L. Chen, J. Xiao, and T.-S. Chua, “Hierarchical fashion graph network for personalized outfit recommendation,” in Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, 2020, pp. 159–168.
• [3] A. Dagan, I. Guy, and S. Novgorodov, “Shop by image: characterizing visual search in e-commerce,” Information Retrieval Journal, vol. 26, no. 1, p. 2, 2023, doi: 10.1007/s10791-023-09418-1.
• [4] M. Hadi Kiapour, X. Han, S. Lazebnik, A. C. Berg, and T. L. Berg, “Where to buy it: Matching street clothing photos in online shops,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 3343–3351.
• [5] Z. Liu, P. Luo, S. Qiu, X. Wang, and X. Tang, “Deepfashion: Powering robust clothes recognition and retrieval with rich annotations,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1096–1104.
• [6] M. Jia et al., “Fashionpedia: Ontology, segmentation, and an attribute localization dataset,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16, 2020, pp. 316–332.
• [7] B. Kolisnik, I. Hogan, and F. Zulkernine, “Condition-CNN: A hierarchical multi-label fashion image classification model,” Expert Syst Appl, vol. 182, p. 115195, 2021.
• [8] Z.-Q. Cheng, X. Wu, Y. Liu, and X.-S. Hua, “Video2shop: Exact matching clothes in videos to online shopping images,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4048–4056.
• [9] N. Garcia and G. Vogiatzis, “Dress like a star: Retrieving fashion products from videos,” in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 2293–2299.
• [10] J. Huang, R. S. Feris, Q. Chen, and S. Yan, “Cross-domain image retrieval with a dual attribute-aware ranking network,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1062–1070.
• [11] M. Hadi Kiapour, X. Han, S. Lazebnik, A. C. Berg, and T. L. Berg, “Where to buy it: Matching street clothing photos in online shops,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 3343–3351.
• [12] L. Richardson, “Beautiful soup documentation,” 2007, April.
• [13] Y. Wu, A. Kirillov, F. Massa, W. Y. Lo, and R. Girshick, “Detectron2 [www document],” URL https://github. com/facebookresearch/detectron2 (accessed 12.12. 23), 2019.
• [14] S. Guo et al., “The imaterialist fashion attribute dataset,” in Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019, p. 0.
• [15] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
• [16] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.