Abstract
The retrieval of incomplete and fuzzy shoe prints is a difficult problem in shoe print retrieval algorithm. In order to solve this problem. We improve the feature extraction network by using a new module called Dilated-MBConv on efficientV2. The new module is constructed by introducing multi-scale dilated convolution, and the original MBConv is replaced by Dilated-MBConv in stage 5–7 of the network; At the same time, in order to make the feature extraction network pay attention to the location information of shoe prints, this paper uses coordinate attention to replace the original squeeze and excitation module of the network. The improved network has achieved a better retrieve results in CSS-200 and CS-Database.
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
Similar content being viewed by others
References
Wang, X., et al.: Automatic shoeprint retrieval algorithm for real crime scenes. Springer International Publishing. Springer International Publishing (2014)
Richetelli, N., Lee, M.C., Lasky, C.A., et al.: Classification of footwear outsole patterns using Fourier transform and local interest points. Forensic Sci. Int. 275, 102–109 (2017)
Peng, F.: Local Semantic Patch and Manifold Ranking Based Shoeprint Retrieval, pp. 11–18. Dalian Maritime University, Dalian (2019)
Zhou, S.Y.: Local Semantic Filter Bank Based Low Quality Shoeprint Image Retrieval, pp. 15–39. Dalian Maritime University, Dalian (2020)
Kong, B., et al.: Cross-domain image matching with deep feature maps. Int. J. Comput. Vision 127(3), 1738–1750 (2018)
Shi, W.T., Tang, Y.Q.: Research on forensic shoeprint retrieval algorithm by fine-tuning VGG-16. Journal of People’s Public Security University of China (Science and Technology) 26(03), 22–29 (2020)
Shi, W.T., Tang, Y.Q.: Shoeprints retrieval algorithm based on selective convolutional descriptor aggregation. Science Technology and Engineering 21(16), 6772–6779 (2021)
Tan, M.X., Quoc, V.L.: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. (28 May 2019). [2021.11.25]. https://arxiv.org/abs/1905.11946
Tan, M.X., Quoc, V.L.: EfficientNetV2: Smaller Models and Faster Training (1 April 2021). [2021.6.23]. https://doi.org/10.48550/arXiv.2104.00298
Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 472–480 (2017)
Wang, P., et al. Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 1451–1460 (2018)
Sanghyun, W., Park, J.C., Lee, J.Y., Kweon, I.S.: Convolutional Block Attention Module. In: Proceedings of ECCV 2018, September 8–14, pp. 36–39. Munich, Germany (2018)
Hou, Q.B., Zhou, D.Q., Feng, J.S.: Coordinate attention for efficient mobile network design. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13708–13717 (2021)
Wu, Y.J., Wang, X.N., Zhang, T.: Crime scene shoeprint retrieval using hybrid features and neighboring images. Information 10(02), 45–60 (2019)
Touvron, H., et al.: Training data-efficient image transformers & distillation through attention (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xin, Y., Tang, Y., Yang, Z. (2022). Shoe Print Retrieval Algorithm Based on Improved EfficientnetV2. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)