TY  - JOUR
AU  - Dena Bazazian
AU  - Raul Gomez
AU  - Anguelos Nicolaou
AU  - Lluis Gomez
AU  - Dimosthenis Karatzas
AU  - Andrew Bagdanov
PY  - 2019//
TI  - Fast: Facilitated and accurate scene text proposals through fcn guided pruning
T2  - PRL
JO  - Pattern Recognition Letters
SP  - 112
EP  - 120
VL  - 119
N2  - Class-specific text proposal algorithms can efficiently reduce the search space for possible text object locations in an image. In this paper we combine the Text Proposals algorithm with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same recall level and thus gaining a significant speed up. Our experiments demonstrate that such text proposal approaches yield significantly higher recall rates than state-of-the-art text localization techniques, while also producing better-quality localizations. Our results on the ICDAR 2015 Robust Reading Competition (Challenge 4) and the COCO-text datasets show that, when combined with strong word classifiers, this recall margin leads to state-of-the-art results in end-to-end scene text recognition.
UR  - https://doi.org/10.1016/j.patrec.2017.08.030
L1  - http://refbase.cvc.uab.es/files/BGN2019.pdf
N1  - DAG; 600.084; 600.121; 600.129
ID  - Dena Bazazian2019
ER  -