Abstract
The triplet-loss function is widely used in fields of descriptor extraction in recent years and owing to its good performance in various databases. However, some recent works make less effort on the relationship of adjacent descriptors from the same sample, which leads to the instability of descriptors and results in the mismatching problem in practical applications. To solve this problem, we introduce the topological relationship with the Normal Distribution Function (NDF) into the triplet loss function. The loss function establishes the relationship of descriptors from the same sample and considers the interrelation of descriptors from different types of samples. Furthermore, to increase the calculation speed, we normalize the algorithm NDF. Finally, we propose the triplet-loss function on three databases. These results demonstrate that our algorithm obtains better performance than state-of-the-art methods.
Supported by National Natural Science Foundation of China (Grant No. 62006059), Guangdong Basic and Applied Basic Research Foundation (Grant No. 2019A1515110582), the National Key Research and Development Program of China (2020YFB2104304).
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
Djordjevic, D., Cvetkovic, S., Nikoli´c, S.V.: An accurate method´ for 3D object reconstruction from unordered sparse views. Signal Image Video Process. 11(6) 1147–1154 (2017)
Zhang, B., Gao, Y., Zhao, S., Liu, J.: Local derivative pattern versus local binary pattern: Face recognition with high-order local pattern descriptor. IEEE Trans. Image Process. Publicat. IEEE Signal Process. Soc. 19(2), 533–544 (2010)
Durrant-Whyte, H., Bailey, T.: Simultaneous localization and mapping (slam) part i. IEEE Robot. Autom. Mag. 13(2) 99–110 (2006)
Durrant-Whyte, H.: Simultaneous localization and mapping (slam) part ii. IEEE Robot. Autom. Mag. 13(3) 108–117 (2006)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: International Conference on Computer Vision, pp. 2564–2571 (2011)
David, G.L.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Bay, H., Tuytelaars, T., Van, G.: Surf: speeded up robust features. In: European Conference on Computer Vision, pp. 404–417 (2006)
Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., Moreno-Noguer, F.: Discriminative learning of deep convolutional feature point descriptors. In: International Conference on Computer Vision (ICCV), pp. 118–126 (2015)
He, K., Yan, L., Stan, S.: Local descriptors optimized for average precision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 596–605 (2018)
Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor’s margins: local descriptor learning loss. In: Neural Information Processing Systems, pp. 4829–4840 (2017)
Zhang, L., Szymon, R.: Learning local descriptors with a CDF-based dynamic soft margin. In: International Conference on Computer Vision, pp. 2969–2978 (2019)
Han, X., Leung, T., Jia, Y., Rahul, S., Alexander, C.B.: Matchnet: unifying feature and metric learning for patch-based matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3279–3286 (2015)
Vassileios, B., Edgar, R., Daniel, P., et al.: Learning local feature descriptors with triplets and shallow convolutional neural networks. In: British Machine Vision Conference, pp. 119.1–119.11 (2016)
Tian, Y., Fan, B., Wu, F.: L2-net: deep learning of discriminative patch descriptor in euclide-an space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6128–6136 (2017)
Wang, S., et al.: Better and faster: Exponential loss for image patch matching. In: International Conference on Computer Vision, pp. 4811–4820 (2019)
Brown, M., Winder, S.J.: Learning local image descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Balntas, V., Lenc, K., Vedaldi, A., et al. Hpatches: a benchmark and evaluation of handcrafted and learned local descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3852–3861 (2017)
Mishkin, D., Matas, J., Perdoch, M., Lenc, K.: Wxbs: wide baseline stereo generalizations. In: Proceedings of the British Machine Vision Conference, pp. 12.1–12.12 (2015)
Edgar, S.-S., Eduard, T., Luis, F., et al.: Francesc, discriminative learning of deep convolutional feature point descriptors. In: International Conference on Computer Vision, pp. 118–126 (2015)
Acknowledgement
This research is supported by National Natural Science Foundation of China (Grant No. 62006059), Guangdong Basic and Applied Basic Research Foundation (Grant No. 2019A1515110582), and the National Key Re-search and Development Program of China (2020YFB2104304).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yin, J., Liu, C., Jiang, J., Wen, J., Yang, L., Zhu, S. (2021). Normal Distribution Function on Descriptor Extraction. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12889. Springer, Cham. https://doi.org/10.1007/978-3-030-87358-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-87358-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87357-8
Online ISBN: 978-3-030-87358-5
eBook Packages: Computer ScienceComputer Science (R0)