Using deformable convolutional layers in the middle of a CRNN improves recognition of irregular scene text by several accuracy points on TotalText and ICDAR 2015 without image rectification.
Title resolution pending
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
-
Focus-Enhanced Scene Text Recognition with Deformable Convolutions
Using deformable convolutional layers in the middle of a CRNN improves recognition of irregular scene text by several accuracy points on TotalText and ICDAR 2015 without image rectification.