Out of Length Text Recognition with Sub-String Matching
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 2798-2806
DOI: 10.1609/aaai.v39i3.32285 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yongkun Du und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
Scene Text Recognition (STR) methods have demonstrated robust performance in word-level text recognition. However, in real applications the text image is sometimes long due to detected with multiple horizontal words. It triggers the requirement to build long text recognition models from readily available short (i.e., word-level) text datasets, which has been less studied previously. In this paper, we term this task Out of Length (OOL) text recognition. We establish the first Long Text Benchmark (LTB) to facilitate the assessment of different methods in long text recognition. Meanwhile, we propose a novel method called OOL Text Recognition with sub-String Matching (SMTR). SMTR comprises two cross-attention-based modules: one encodes a sub-string containing multiple characters into next and previous queries, and the other employs the queries to attend to the image features, matching the sub-string and simultaneously recognizing its next and previous character. SMTR can recognize text of arbitrary length by iterating the process above. To avoid being trapped in recognizing highly similar sub-strings, we introduce a regularization training to compel SMTR to effectively discover subtle differences between similar sub-strings for precise matching. In addition, we propose an inference augmentation strategy to alleviate confusion caused by identical sub-strings in the same text and improve the overall recognition efficiency. Extensive experimental results reveal that SMTR, even when trained exclusively on short text, outperforms existing methods in public short text benchmarks and exhibits a clear advantage on LTB.
Zitieren
APA
Du, Y., Chen, Z., Jia, C., Gao, X., & Jiang, Y. (2025). Out of Length Text Recognition with Sub-String Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 2798-2806. https://doi.org/10.1609/aaai.v39i3.32285
Vancouver
Du Y, Chen Z, Jia C, Gao X, Jiang Y. Out of Length Text Recognition with Sub-String Matching. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):2798-2806. doi:10.1609/aaai.v39i3.32285
BibTeX
@article{Du2025,
author = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Gao, Xieping and Jiang, Yu-Gang},
title = {Out of Length Text Recognition with Sub-String Matching},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {3},
pages = {2798--2806},
doi = {10.1609/aaai.v39i3.32285}
}
EUVIMED