Capsule Deep Neural Network for Recognition of Historical Graffiti Handwriting

no code implementations • 11 Sep 2018 • Gordienko Nikita, Kochura Yuriy, Taran Vlad, Peng Gang, Gordienko Yuri, Stirenko Sergii

The confusion matrixes were much better for capsule network than for CNN model and gave the much lower type I (false positive) and type II (false negative) values in all three regimes of data augmentation.

Data Augmentation