Synthesizing data for text recognition with style transfer
Sign Up to like & getrecommendations! Published in 2018 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-6656-3
Abstract: Most of the existing datasets for scene text recognition merely consist of a few thousand training samples with a very limited vocabulary, which cannot meet the requirement of the state-of-the-art deep learning based text recognition… read more here.
Keywords: text recognition; synthesizing data; style transfer; transfer ... See more keywords