Abstract
Mongolian is a language spoken in Inner Mongolian, China. Traditional Mongolian script standard compliance testing is very important and fundamental work. This paper proposes a classification network for traditional Mongolian script standard compliance testing. The network uses the spatial pyramid pooling mechanism, it can accept images of different sizes in the convolutional neural network. It can effectively solve multi-scale problems of traditional Mongolian words. Experimental results show the SSP-ResNet-18-Single can effectively recognize traditional Mongolian images, and the recognition average accuracy can reach 98.60%. This network achieves good performance in Mongolian word recognition compare with the current mainstream word recognition network. The dataset has been publicly available.
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
Choijinzhab.: Mongolian Encoding, 1st edn. Inner Mongolia University Press, Hohhot (2000). https://www.babelstone.co.uk/Mongolian/MGWBM.html (in Chinese)
Wang, Y.: Research of font standard compliance detection technology. Master’s thesis. Inner Mongolia University, Hohhot (2012). (in Chinese)
Zhao, Y.: The design and implementation of Mongolian information processing products standards compliance testing system. Master’s Thesis. Inner Mongolia University, Hohhot (2013). (in Chinese)
He, Z., Wang, X., Chen, H.: Research and design of standard conformance test of Mongolian software. Inf. Technol. Standard. z1(14), 47–49 (2015). (in Chinese)
Huslee, S., Bai, C.: Standard conformance test of Mongolian complex text layout engine. J. Guangxi Acad. Sci. 34(01), 63–67 (2018). (in Chinese)
Zhou, C.: Design of Mongolian standard compliance detection system based on deep learning. Master’s thesis. Inner Mongolia University, Hohhot (2019). (in Chinese)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (2012)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Howard, A., et al.: Searching for mobilenetv3. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–1324 (2019)
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
Zhou, C., Wu, L., Guo, W., Cao, D. (2022). Traditional Mongolian Script Standard Compliance Testing Based on Deep Residual Network and Spatial Pyramid Pooling. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13536. Springer, Cham. https://doi.org/10.1007/978-3-031-18913-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-18913-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18912-8
Online ISBN: 978-3-031-18913-5
eBook Packages: Computer ScienceComputer Science (R0)