TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting
Most existing text spotting methods either focus on horizontal/oriented texts or perform arbitrary shaped text spotting with character-level annotations. In this paper, we propose a novel text spotting framework to detect and recognize text of arbitrary shapes in an end-to-end manner, using only word/line-level annotations for training. Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon. In TextDragon, a text detector is designed to describe the shape of text with a series of quadrangles, which can handle text of arbitrary shapes. To extract arbitrary text regions from feature maps, we propose a new differentiable operator named RoISlide, which is the key to connect arbitrary shaped text detection and recognition. Based on the extracted features through RoISlide, a CNN and CTC based text recognizer is introduced to make the framework free from labeling the location of characters. The proposed method achieves state-of-the-art performance on two curved text benchmarks CTW1500 and Total-Text, and competitive results on the ICDAR 2015 Dataset.
PDF AbstractTasks
Datasets
Total-Text
SCUT-CTW1500
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Text Spotting | ICDAR 2015 | TextDragon | F-measure (%) - Strong Lexicon | 82.5 | # 14 | |
| F-measure (%) - Weak Lexicon | 78.3 | # 11 | ||||
| F-measure (%) - Generic Lexicon | 65.2 | # 15 | ||||
| Text Spotting | SCUT-CTW1500 | TextDragon | F-measure (%) - No Lexicon | 39.7 | # 11 | |
| F-Measure (%) - Full Lexicon | 72.4 | # 10 |
