Super-pixel segmentation followed by an ensemble of CNN text detectors improves coverage and extraction accuracy on high-entropy e-commerce images compared with standard CNN baselines.
Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut.Journal of Electronic Imaging, 26(6):061610
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
-
Semi-Bagging Based Deep Neural Architecture to Extract Text from High Entropy Images
Super-pixel segmentation followed by an ensemble of CNN text detectors improves coverage and extraction accuracy on high-entropy e-commerce images compared with standard CNN baselines.