TedEval is a novel evaluation protocol for scene text detectors that performs instance-level matching followed by character-level scoring to provide fairer quality assessment across difficulty levels.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
TedEval: A Fair Evaluation Metric for Scene Text Detectors
TedEval is a novel evaluation protocol for scene text detectors that performs instance-level matching followed by character-level scoring to provide fairer quality assessment across difficulty levels.