Abstract | ||
---|---|---|
Text removal algorithms have been proposed for uni-lingual scripts with regular shapes and layouts. However, to the best of our knowledge, a generic text removal method which is able to remove all or user-specified text regions regardless of font, script, language or shape is not available. Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting. To fill this gap, we propose a mask-based text removal network (MTRNet). MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask. The introduced auxiliary mask not only makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes. What's more, MTRNet achieves state-of-the-art results on several real-world datasets including ICDAR 2013, ICDAR 2017 MLT, and CTW1500, without being explicitly trained on this data, outperforming previous state-of-the-art methods trained directly on these datasets. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICDAR.2019.00016 | 2019 International Conference on Document Analysis and Recognition (ICDAR) |
Keywords | Field | DocType |
Text Removal,Inpainting,Image Translation,Mask | Image translation,Convergence (routing),Computer vision,Pattern recognition,Computer science,Font,Inpainting,Artificial intelligence,Generative grammar,Text detection,Scripting language | Conference |
Volume | ISSN | ISBN |
abs/1903.04092 | 1520-5363 | 978-1-7281-3015-6 |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Osman Tursun | 1 | 3 | 2.47 |
rui zeng | 2 | 21 | 4.18 |
Simon Denman | 3 | 509 | 56.72 |
Sabesan Sivapalan | 4 | 54 | 3.36 |
Sridha Sridharan | 5 | 2092 | 222.69 |
Clinton Fookes | 6 | 743 | 97.41 |