Abstract
This study proposes a font recognition algorithm based on a deep convolution neural network and a font substitution algorithm based on texture and grayscale features. The experiments show that the proposed font recognition method can effectively extract font features with a high recognition rate, without the prior knowledge of the text content and with good versatility. The substitution effect of the proposed font replacement method can better satisfy the subjective visual perception of the human eyes and easily expand. The research results can be used to improve the publication quality; ensure the best presentation effect when presented in different platforms; facilitate font retrieval and effectively protect font copyright.
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
Liu, Y.P.: The development and research of word document format-checking plug-in based on VSTO. Comput. Knowl. Technol. (2016)
Si, G., Ning, L., Lin, Z.: Method for bibliographic reference format normativity checking. J. Beijing Inf. Sci. Technol. Univ. 32(1), 44–49 (2017)
Yang, Y.: Check the Document Style Method and System, CN 104346319 B (2017)
Wang, Z., Yang, J., Jin, H., et al.: DeepFont: a system for font recognition and similarity. In: ACM International Conference on Multimedia, pp. 813–814. ACM (2015)
Wang, Z., Yang, J., Jin, H., et al.: DeepFont: identify your font from an image, pp. 451–459 (2015)
Tao, D., Lin, X., Jin, L.: Principal component 2-D long short-term memory for font recognition on single chinese characters. IEEE Trans. Cybern. 46(3), 756–765 (2016)
Huang, S.P., Zhong, Z.Y., Jin, L.W., Zhang, S.Y., et al.: DropRegion training of inception font network for high-performance Chinese font recognition. Pattern Recognit. 77 (2018)
Wang, Y., Lian, Z., Tang, Y., et al.: Font recognition in natural images via transfer learning. MultiMedia Model. (2018)
Ling, X., Guo, S., Gao, F.: Chinese character font recognition based on multi-scale wavelet analysis. Comput. Appl. 26(b06), 21–23 (2006)
Hou, Y., Zhou, S., Lei, L., Zhao, L.: Invariant feature with multi-characteristic scales using Gabor filter bank. Acta Electron. Sin. 41(06), 1146–1152 (2013)
Li, K., Yin, J., Li, Y.: Local statistical analysis of Gabor coefficients and adaptive feature extraction for face description and recognition. J. Comput. Res. Dev. 9(2), 611–648 (2012)
Wang, X.: Optical font recognition of Chinese based on the stroke tip similarity. Acta Scientiarum Naturalium Universitatis Pekinensis 49(1), 54–60 (2013)
Acknowledgements
The authors acknowledge the National Natural Science Foundation of China (Grant: 61672105), National Key R&D Program of China (Grant: 2018YFB1004100) and the Opening Foundation of State Key Laboratory of Digital Publishing Technology.
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
Li, N., Zhao, H., Liu, X. (2021). Machine Learning-Based Font Recognition and Substitution Method for Electronic Publishing. In: Stephanidis, C., Antona, M., Ntoa, S. (eds) HCI International 2021 - Late Breaking Posters. HCII 2021. Communications in Computer and Information Science, vol 1498. Springer, Cham. https://doi.org/10.1007/978-3-030-90176-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-90176-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90175-2
Online ISBN: 978-3-030-90176-9
eBook Packages: Computer ScienceComputer Science (R0)