Papers › TextBoxes++: A Single-Shot Oriented Scene Text Detector
TextBoxes++: A Single-Shot Oriented Scene Text Detector
Minghui Liao, Baoguang Shi, Xiang Bai
Scene text detection is an important step of scene text recognition system and also a challenging problem. Different from general object detection, the main challenges of scene text detection lie on arbitrary orientations, small sizes, and significantly variant aspect ratios of text in natural images. In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass. No post-processing other than an efficient non-maximum suppression is involved. We have evaluated the proposed TextBoxes++ on four public datasets. In all experiments, TextBoxes++ outperforms competing methods in terms of text localization accuracy and runtime. More specifically, TextBoxes++ achieves an f-measure of 0.817 at 11.6fps for 1024*1024 ICDAR 2015 Incidental text images, and an f-measure of 0.5591 at 19.8fps for 768*768 COCO-Text images. Furthermore, combined with a text recognizer, TextBoxes++ significantly outperforms the state-of-the-art approaches for word spotting and end-to-end text recognition tasks on popular benchmarks. Code is available at: https://github.com/MhLiao/TextBoxes_plusplus
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
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 | TextBoxes++_MS | F-Measure | 58.72 | #2 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | TextBoxes++_MS | Precision | 60.87 | #2 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | TextBoxes++_MS | Recall | 56.7 | #2 of 6 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | TextBoxes++_MS | F-Measure | 88%% | #8 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | TextBoxes++_MS | Precision | 91 | #8 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | TextBoxes++_MS | Recall | 84 | #8 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | Quad_MS | F-Measure | 82.9 | #31 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | Quad_MS | Precision | 87.8 | #31 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | Quad_MS | Recall | 78.5 | #31 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