Abstract
Identifying similar images within databases is a significant challenge in the field of image retrieval. This challenge is further compounded by escalating demands for heightened precision and speed, propelled by advancements in information technology. This study introduces a distinctive network design to address common problems associated with high-probability image retrieval, such as sluggish retrieval speeds and inadequate discrimination. The network architecture primarily employs CNNs for feature extraction. To maximize the advantages of deep learning in feature extraction, the design includes a second-order attention module and a second-order similarity loss. The incorporation of second-order information enhances the correlation among local spatial locations in the image, adjusting each local contribution to the global context. This facilitates a more comprehensive understanding of the image's structure and content, thereby improving feature extraction. Furthermore, dimension reduction techniques are applied to effectively capture the profound information within images. This aids in the elimination of superfluous features while preserving essential information necessary for the retrieval task. This method improves the model's retrieval accuracy by concentrating on the image's deep features, allowing it to disregard unnecessary information. Experimental results demonstrate that our image retrieval technique not only improves accuracy but also significantly accelerates retrieval speed across various datasets, exceeding previous benchmarks in the field.
Similar content being viewed by others
Data availability
The data supporting the findings of this study are publicly available datasets. http://doi.org/https://doi.org/10.1109/CVPR.2018.00598.
References
Latif, A., et al.: Content-based image retrieval and feature extraction: a comprehensive review. Math. Problems Eng. 2019, 1 (2019). https://doi.org/10.1155/2019/9658350
Feng, W., Yantao, W.: A review of content-based image retrieval technology. Ind. Technol. Forum 1, 66–67 (2013)
Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: IEEE International Conference on Computer Vision, pp. 1470–1470 (2003). https://doi.org/10.1109/ICCV.2003.1238663.
Jegou, H., et al.: Aggregating local image descriptors into compact codes. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1704–1716 (2012). https://doi.org/10.1109/tpami.2011.235
Sánchez, J., et al.: Image classification with the fisher vector: Theory and practice. Int. J. Comput. Vis. 105, 222–245 (2013). https://doi.org/10.1007/s11263-013-0636-x
Xueli, Z., Yanbin, Xu.: Comparative study of image retrieval technology. Lib. Sci. Res. 16, 59–62 (2017). https://doi.org/10.15941/j.cnki.issn1001-0424.2017.16.010
Zhang, H., et al.: Dynamic environments localization via dimensions reduction of deep learning features. In: Computer Vision Systems: 11th International Conference, ICVS 2017, Shenzhen, China, July 10-13, 2017, Revised Selected Papers 11, 239–253 (2017). https://doi.org/10.1007/978-3-319-68345-4_22
Hongyan, S.: Remote sensing image feature extraction method based on multi-feature fusion. Comput. Simul. 1, 334–337 (2016)
Song, Q., et al.: Learning deep features for msr-bing information retrieval challenge. In: Proceedings of the 23rd ACM international conference on Multimedia, pp. 169–172 (2015). https://doi.org/10.1145/2733373.2809928.
Erin Liong, V., et al.: Deep hashing for compact binary codes learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2475–2483 (2015). https://doi.org/10.1109/cvpr.2015.7298862.
Yue, C., et al.: Deep quantization network for efficient image retrieval. In: Proceedings of 13th AAAI Conference on Artificial Intelligence, pp. 3457–3463 (2016). https://doi.org/10.1109/CVPR.2017.104.
Cao, Y., et al.: Deep cauchy hashing for hamming space retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1229–1237 (2018). https://doi.org/10.1109/CVPR.2018.00134.
Ng, T. et al.: SOLAR: second-order loss and attention for image retrieval. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16, 253–270 (2020). https://doi.org/10.1007/978-3-030-58595-2_16
Gao, Z., Wang, L., Zhou, L., Yang, M. Infomax principle based pooling of deep convolutional activations for image retrieval. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 457–462 (2017). https://doi.org/10.1109/ICME.2017.8019321.
Shah, A., Chauhan, Y., Chaudhury, B.: Principal component analysis based construction and evaluation of cryptocurrency index. Expert Syst. Appl. 163, 116 (2021). https://doi.org/10.1016/j.eswa.2020.113796
Radenović, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655–1668 (2018). https://doi.org/10.1109/TPAMI.2018.2846566
Balntas, V., et al.: Learning local feature descriptors with triplets and shallow convolutional neural networks. BMVC 3, 1 (2016). https://doi.org/10.5244/C.30.119
Mishchuk, A., et al.: Working hard to know your neighbor’s margins: Local descriptor learning loss. Adv. Neural. Inf. Process. Syst. 30, 1 (2017). https://doi.org/10.4850/arXiv.1705.10872
Tian, Y., Fan, B., Wu, F.: L2-net: Deep learning of discriminative patch descriptor in euclidean space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 661–669 (2017). https://doi.org/10.1109/CVPR.2017.649.
Tian, Y., et al.: Sosnet: Second order similarity regularization for local descriptor learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11016–11025 (2019). https://doi.org/10.1109/CVPR.2019.01127.
Yang, M., et al.: Dolg: Single-stage image retrieval with deep orthogonal fusion of local and global features. In: Proceedings of the IEEE/CVF International conference on Computer Vision, pp. 11772–11781 (2021). https://doi.org/10.1109/ICCV48922.2021.01156.
Radenović, F., et al.: Revisiting oxford and paris: Large-scale image retrieval benchmarking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5706–5715 (2018). https://doi.org/10.1109/CVPR.2018.00598.
Cao, B., Araujo, A., Sim, J.: Unifying deep local and global features for image search. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 726–743 (2020). https://doi.org/10.1007/978-3-030-58565-5_43.
Mishkin, D., Radenovic, F., Matas, J.: Repeatability is not enough: learning affine regions via discriminability. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 284–300. https://doi.org/10.6038/cjg20160828.
Tolias, G., Avrithis, Y., Jégou, H.: Image search with selective match kernels: aggregation across single and multiple images. Int. J. Comput. Vis. 116, 247–261 (2016). https://doi.org/10.1007/s11263-015-0810-4
Revaud, J., et al.: Learning with average precision: Training image retrieval with a listwise loss. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5107–5116 (2019). https://doi.org/10.1109/ICCV.2019.00521 .
Acknowledgements
At the end of the article, I would like to thank Teacher Zhang and Teacher Liu for their guidance and help.
Funding
This study is not applicable.
Author information
Authors and Affiliations
Contributions
Fuqiang Wu: Conceptualization, Data curation, Writing-Original draft preparation. Writing- Reviewing and Editing. Dandan Liu and Kang An: Investigation, Supervision. Hui Zhang: Methodology, Supervision, Validation.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Ethical approval
This study is not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wu, F., Liu, D., An, K. et al. Image retrieval based on dimensionality reduction of second-order information. SIViP 18, 2723–2731 (2024). https://doi.org/10.1007/s11760-023-02943-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02943-y