Abstract
The process of learning good representation in deep learning may prove difficult when the data is insufficient. In this paper, we propose a Siamese similarity network for one-shot ancient character recognition based on a similarity learning method to directly learn input similarity, and then use the trained model to establish one shot classification task for recognition. Multi-scale fusion backbone structure and embedded structure are proposed in the network to improve the model's ability to extract features. we also propose the soft similarity contrast loss function for the first time. It ensures the optimization of similar images with higher similarity and different classes of images with greater differences while reducing the over-optimization of back-propagation leading to model overfitting. A large number of experiments show that our proposed method has achieved high-efficiency discriminative performance, and obtained the best performance over the methods of traditional deep learning and other classic one-shot learning.
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
Yuan, G., Jiayi, M., Alan, L.: Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples. IEEE Trans. Image process. 26(5), 2545–2560 (2017)
Bin, P., Zhenwei, S., Xia, X.: Mugnet: deep learning for hyperspectral image classification using limited samples. ISPRS J. Photogrammetry Remote Sens. 145, 108–119 (2017)
Han, A., Bharath, R., Aneesh, S.P., Vijay, P.: Low data drug discovery with one-shot learning. ACS Cent. Sci. 3(4), 283–293 (2017)
Kadam, S., Vaidya, V.: Review and analysis of zero, one and few shot learning approaches. In: Abraham, A., Cherukuri, A.K., Melin, P., Gandhi, N. (eds.) ISDA 2018 2018. AISC, vol. 940, pp. 100–112. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-16657-1_10
Gregory, K., Richard, Z., Ruslan, S.: Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, Lille, France (2015)
Yann, L., Yoshua, B., Geoffrey, H.: Deep learning. Nat. 521(7553), 436–444 (2015)
Waseem, R., Zenghui, W.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29(9), 2352–2449 (2017)
Alex, K., Ilya, S., Geoffrey, H.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Taraggy, M.G., Mahmoud, I.K., Hazem, M.A.: Comparative study on deep convolution neural networks DCNN-based offline arabic handwriting recognition. IEEE Access 8, 95465–95482 (2020)
Yikang, Z., Heng, Z. Yongge, L., Qing, Y., Chenglin, L.: Oracle character recognition by nearest neighbor classification with deep metric learning.In: International Conference on Document Analysis and Recognition, Sydney, NSW, Australia, pp. 309–314. IEEE (2019)
Oriol, V., Charles, B., Timothy, L., Koray, K., Daan, W.: Matching networks for one shot learning. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, Red Hook, NY, USA, pp. 3637–3645. Curran Associates Inc. (2016)
Jake, S., Kevin, S., Richard, S.Z.: Prototypical networks for few-shot learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4077–4087. Long Beach, CA, USA (2017)
Camilo, V., Qianni, Z., Ebroul, I.: One shot logo recognition based on siamese neural networks. In: International Conference on Multimedia Retrieval Dublin, ACM, Ireland (2020)
Christian, S., Sergey, L., Vincent, V., Alexander, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In Proceedings of the 31th AAAI Conference on Artificial Intelligence, San Francisco, California, USA. AAAI Press (2017)
Kaiming, H., Xiangyu, Z. Shaoqing, R., Jian, S.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Min, L., Qiang, C., Shuicheng, Y.: Network in Network (2014)
Geoffrey, H., Nitish, S., Alex, K., Ilya, S., Ruslan, R.S.: Improving neural networks by preventing co-adaptation of feature detectors. Comput. Sci. 3(4), 212–223 (2012)
Raia, H., Sumit, C., Yann, L.: Dimensionality reduction by learning an invariant mapping. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, pp. 1735–1742. IEEE (2006)
Simon, A.: About Omniglot (1998).https://www.omniglot.com/about.htm#langs
Xu, H.: Research and implementation of character detection and recognition of ancient Yi language. Dissertation, Southwest University (2020)
Bang, L., et al.: HWOBC-a handwriting oracle bone character recognition database. J. Phys. Conf. 1651(1), 012050 (2020)
Hartline, H.K., Wagner, H.G., Ratliff, F.: Ratliff inhibition in the eye of limulus. J. Gen. Physiol. 39, 651–673 (1956)
Karen, S., Andrew, Z.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Christian, S., et al.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Acknowledgements
This work was supported by The National Social Science Fund of China (19BYY171), China Postdoctoral Science Foundation (2015M580765), and Chongqing Postdoctoral Science Foundation (Xm2016041), the Fundamental Research Funds for the Central Universities, China (XDJK2018B020), Chongqing Natural Science Foundation (cstc2019jcyj-msxmX0130), Chongqing Key Lab of Automated Reasoning and Cognition, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences(arc202003).
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
Liu, X., Tang, X., Chen, S. (2021). Learning a Similarity Metric Discriminatively with Application to Ancient Character Recognition. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12815. Springer, Cham. https://doi.org/10.1007/978-3-030-82136-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-82136-4_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82135-7
Online ISBN: 978-3-030-82136-4
eBook Packages: Computer ScienceComputer Science (R0)