TY - GEN
T1 - A committee of neural networks for traffic sign classification
AU - Cireşan, Dan
AU - Meier, Ueli
AU - Schmidhuber, Jürgen
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 2011/10/24
Y1 - 2011/10/24
N2 - We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance. © 2011 IEEE.
AB - We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance. © 2011 IEEE.
UR - http://ieeexplore.ieee.org/document/6033458/
UR - http://www.scopus.com/inward/record.url?scp=80054740693&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2011.6033458
DO - 10.1109/IJCNN.2011.6033458
M3 - Conference contribution
SN - 9781457710865
SP - 1918
EP - 1921
BT - Proceedings of the International Joint Conference on Neural Networks
ER -