%0 Journal Article
%T Multi-column deep neural network for traffic sign classification
%J Neural networks
%D 2012
%A Cireşan, Dan
%A Meier, Ueli
%A Masci, Jonathan
%A Schmidhuber, Jürgen
%V 32
%N 
%P 333-338
%X We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination.<p /> <p>Language: en</p>
%G en
%I Elsevier Publishing
%@ 0893-6080
%U http://dx.doi.org/10.1016/j.neunet.2012.02.023