Do Capsule Networks Solve the Problem of Rotation Invariance for Traffic Sign Classification?

Jan Kronenberger Anselm Haselhoff

Published in: ICANN (3) (2018)

Keyphrases

rotation invariance
traffic signs
rotation invariant
pattern recognition
classification accuracy
image classification
feature extraction
feature space
feature vectors
three dimensional
multiscale
training set
image features
zernike moments
shape context