A Mask R-CNN and attention-based text spotter handles curved text by masking RoI features instead of rectifying them, and uses OCR-engine labels as extra training data to set state-of-the-art results on ICDAR15 and Total-Text.
Detecting and read- ing text in natural scenes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Unconstrained End-to-End Text Spotting
A Mask R-CNN and attention-based text spotter handles curved text by masking RoI features instead of rectifying them, and uses OCR-engine labels as extra training data to set state-of-the-art results on ICDAR15 and Total-Text.