Scene Text Detection
Scene Text Detection is a computer vision task that involves automatically identifying and localizing text within natural images or videos. The goal of scene text detection is to develop algorithms that can robustly detect and and label text with bounding boxes in uncontrolled and complex environments, such as street signs, billboards, or license plates.
Source: ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
Papers
Showing 1–10 of 213 papers
All datasetsICDAR 2015Total-TextMSRA-TD500SCUT-CTW1500ICDAR 2013ICDAR 2017 MLTCOCO-TextIC19-ArtIC19-ReCTs
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MixNet | F-Measure | 89.4 | — | Unverified |
| 2 | FAST-B-736 | F-Measure | 87.3 | — | Unverified |
| 3 | DBNet++ (ResNet-50) (736) | F-Measure | 87.2 | — | Unverified |
| 4 | FAST-S-736 | F-Measure | 86.4 | — | Unverified |
| 5 | DBNet++ (ResNet-18) (736) | F-Measure | 85.1 | — | Unverified |
| 6 | DB-ResNet-50 (736) | F-Measure | 84.9 | — | Unverified |
| 7 | FAST-T-736 | F-Measure | 84.9 | — | Unverified |
| 8 | FAST-T-512 | F-Measure | 84.5 | — | Unverified |
| 9 | PAN | F-Measure | 84.1 | — | Unverified |
| 10 | CRAFT | F-Measure | 82.9 | — | Unverified |