EraseNet : End-to-End Text Removal in the Wild

Scene text removal has attracted increasing research interests owing to its valuable applications in privacy protection, camera-based virtual reality translation, and image editing. However, existing approaches, which fall short on real applications, are mainly because they were evaluated on synthet...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2020) vom: 28. Aug.
Auteur principal: Liu, Chongyu (Auteur)
Autres auteurs: Liu, Yuliang, Jin, Lianwen, Zhang, Shuaitao, Luo, Canjie, Wang, Yongpan
Format: Article en ligne
Langue:English
Publié: 2020
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM314308970
003 DE-627
005 20250227212825.0
007 cr uuu---uuuuu
008 231225s2020 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2020.3018859  |2 doi 
028 5 2 |a pubmed25n1047.xml 
035 |a (DE-627)NLM314308970 
035 |a (NLM)32857697 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liu, Chongyu  |e verfasserin  |4 aut 
245 1 0 |a EraseNet  |b End-to-End Text Removal in the Wild 
264 1 |c 2020 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 22.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Scene text removal has attracted increasing research interests owing to its valuable applications in privacy protection, camera-based virtual reality translation, and image editing. However, existing approaches, which fall short on real applications, are mainly because they were evaluated on synthetic or unrepresentative datasets. To fill this gap and facilitate this research direction, this paper proposes a real-world dataset called SCUT-EnsText that consists of 3,562 diverse images selected from public scene text reading benchmarks, and each image is scrupulously annotated to provide visually plausible erasure targets. With SCUT-EnsText, we design a novel GANbased model termed EraseNet that can automatically remove text located on the natural images. The model is a two-stage network that consists of a coarse-erasure sub-network and a refinement sub-network. The refinement sub-network targets improvement in the feature representation and refinement of the coarse outputs to enhance the removal performance. Additionally, EraseNet contains a segmentation head for text perception and a local-global SN-Patch-GAN with spectral normalization (SN) on both the generator and discriminator for maintaining the training stability and the congruity of the erased regions. A sufficient number of experiments are conducted on both the previous public dataset and the brand-new SCUT-EnsText. Our EraseNet significantly outperforms the existing state-of-the-art methods in terms of all metrics, with remarkably superior higherquality results. The dataset and code will be made available at https://github.com/HCIILAB/SCUT-EnsText 
650 4 |a Journal Article 
700 1 |a Liu, Yuliang  |e verfasserin  |4 aut 
700 1 |a Jin, Lianwen  |e verfasserin  |4 aut 
700 1 |a Zhang, Shuaitao  |e verfasserin  |4 aut 
700 1 |a Luo, Canjie  |e verfasserin  |4 aut 
700 1 |a Wang, Yongpan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2020) vom: 28. Aug.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:PP  |g year:2020  |g day:28  |g month:08 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2020.3018859  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2020  |b 28  |c 08