Introduces B-MOD dataset of 19,728 mobile device photos of documents with precise text line annotations and a neural baseline showing high error rates on harder images.
Icdar2017 robust reading challenge on coco-text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Brno Mobile OCR Dataset
Introduces B-MOD dataset of 19,728 mobile device photos of documents with precise text line annotations and a neural baseline showing high error rates on harder images.