A modified Census transform combined with AdaBoost cascades gives more compact and lower-error detectors for railway car numbers and digits than Haar or LBP features on the authors' dataset.
Han, and Hanseok Ko Reinforced AdaBoost Learning for Object Detection with Lo cal Pattern Representations, Scientific World Journal
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
-
Construction of efficient detectors for character information recognition
A modified Census transform combined with AdaBoost cascades gives more compact and lower-error detectors for railway car numbers and digits than Haar or LBP features on the authors' dataset.