TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

13Citations
Citations of this article
12Readers
Mendeley users who have this article in their library.

Abstract

Text irregularities pose significant challenges to scene text recognizers. Thin-Plate Spline (TPS)based rectification is widely regarded as an effective means to deal with them. Currently, the calculation of TPS transformation parameters purely depends on the quality of regressed text borders. It ignores the text content and often leads to unsatisfactory rectified results for severely distorted text. In this work, we introduce TPS++, an attention-enhanced TPS transformation that incorporates the attention mechanism to text rectification for the first time. TPS++ formulates the parameter calculation as a joint process of foreground control point regression and content-based attention score estimation, which is computed by a dedicated designed gated-attention block. TPS++ builds a more flexible content-aware rectifier, generating a natural text correction that is easier to read by the subsequent recognizer. Moreover, TPS++ shares the feature backbone with the recognizer in part and implements the rectification at feature-level rather than image-level, incurring only a small overhead in terms of parameters and inference time. Experiments on public benchmarks show that TPS++ consistently improves the recognition and achieves state-of-the-art accuracy. Meanwhile, it generalizes well on different backbones and recognizers. Code is at https://github.com/simplify23/TPS PP.

Cite

CITATION STYLE

APA

Zheng, T., Chen, Z., Bai, J., Xie, H., & Jiang, Y. G. (2023). TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 2023-August, pp. 1777–1785). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2023/197

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free