Real Scene Text Image Super-Resolution Based on Multi-Scale and Attention Fusion


Xinhua Lu, Haihai Wei, Li Ma, Qingji Xue, and Yonghui Fu, Journal of Information Processing Systems Vol. 19, No. 4, pp. 427-438, Aug. 2023  

10.3745/JIPS.02.0199
Keywords: Attention Mechanisms, multi-scale, Scene text recognition, Text Image Super-Resolution
Fulltext:

Abstract

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition’s (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Lu, X., Wei, H., Ma, L., Xue, Q., & Fu, a. (2023). Real Scene Text Image Super-Resolution Based on Multi-Scale and Attention Fusion. Journal of Information Processing Systems, 19(4), 427-438. DOI: 10.3745/JIPS.02.0199.

[IEEE Style]
X. Lu, H. Wei, L. Ma, Q. Xue, a. Y. Fu, "Real Scene Text Image Super-Resolution Based on Multi-Scale and Attention Fusion," Journal of Information Processing Systems, vol. 19, no. 4, pp. 427-438, 2023. DOI: 10.3745/JIPS.02.0199.

[ACM Style]
Xinhua Lu, Haihai Wei, Li Ma, Qingji Xue, and and Yonghui Fu. 2023. Real Scene Text Image Super-Resolution Based on Multi-Scale and Attention Fusion. Journal of Information Processing Systems, 19, 4, (2023), 427-438. DOI: 10.3745/JIPS.02.0199.