CA-STD: Scene Text Detection in Arbitrary Shape Based on Conditional Attention

Xing Wu, Yangyang Qi, Jun Song, Junfeng Yao, Yanzhong Wang, Yang Liu, Yuexing Han, Quan Qian

Research output: Contribution to journalJournal articlepeer-review

5 Citations (Scopus)


Scene Text Detection (STD) is critical for obtaining textual information from natural scenes, serving for automated driving and security surveillance. However, existing text detection methods fall short when dealing with the variation in text curvatures, orientations, and aspect ratios in complex backgrounds. To meet the challenge, we propose a method called CA-STD to detect arbitrarily shaped text against a complicated background. Firstly, a Feature Refinement Module (FRM) is proposed to enhance feature representation. Additionally, the conditional attention mechanism is proposed not only to decouple the spatial and textual information from scene text images, but also to model the relationship among different feature vectors. Finally, the Contour Information Aggregation (CIA) is presented to enrich the feature representation of text contours by considering circular topology and semantic information simultaneously to obtain the detection curves with arbitrary shapes. The proposed CA-STD method is evaluated on different datasets with extensive experiments. On the one hand, the CA-STD outperforms state-of-the-art methods and achieves 82.9 in precision on the dataset of TotalText. On the other hand, the method has better performance than state-of-the-art methods and achieves the F1 score of 83.8 on the dataset of CTW-1500. The quantitative and qualitative analysis proves that the CA-STD can detect variably shaped scene text effectively.
Original languageEnglish
Article number565
Number of pages14
Issue number12
Publication statusPublished - 1 Dec 2022

Scopus Subject Areas

  • Information Systems

User-Defined Keywords

  • conditional attention
  • contour information aggregation
  • scene text detection


Dive into the research topics of 'CA-STD: Scene Text Detection in Arbitrary Shape Based on Conditional Attention'. Together they form a unique fingerprint.

Cite this