Papers › WordSup: Exploiting Word Annotations for Character based Text Detection
WordSup: Exploiting Word Annotations for Character based Text Detection
Han Hu, Chengquan Zhang, Yuxuan Luo, Yuzhuo Wang, Junyu Han, Errui Ding
Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and convenient to construct a common text detection engine based on character detectors. However, training character detectors requires a vast of location annotated characters, which are expensive to obtain. Actually, the existing real text datasets are mostly annotated in word or line level. To remedy this dilemma, we propose a weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character detector training. When applied in scene text detection, we are thus able to train a robust character detector by exploiting word annotations in the rich large-scale real scene text datasets, e.g. ICDAR15 and COCO-text. The character detector acts as a key role in the pipeline of our text detection engine. It achieves the state-of-the-art performance on several challenging scene text detection benchmarks. We also demonstrate the flexibility of our pipeline by various scenarios, including deformed text detection and math expression recognition.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Text Detection | COCO-Text | WordSup (VGG16-synth-coco) | F-Measure | 36.8 | #5 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | WordSup (VGG16-synth-coco) | Precision | 45.2 | #5 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | WordSup (VGG16-synth-coco) | Recall | 30.9 | #5 of 6 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | WordSup (VGG16-synth-icdar) | F-Measure | 90.34% | #4 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | WordSup (VGG16-synth-icdar) | Precision | 93.34 | #4 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | WordSup (VGG16-synth-icdar) | Recall | 87.53 | #4 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | SSTD | F-Measure | 77 | #39 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | SSTD | Precision | 80 | #39 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | SSTD | Recall | 73 | #39 of 43 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections