publication . Conference object . Other literature type . 2011

A committee of neural networks for traffic sign classification

Jürgen Schmidhuber; Jonathan Masci; Ueli Meier; Dan Ciresan;
Open Access
  • Published: 01 Jul 2011
  • Publisher: IEEE
Abstract
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.
Subjects
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: Convolutional neural network, Time delay neural network, Neocognitron, Artificial neural network, Deep learning, Speech recognition, Traffic sign classification, Computer science, Artificial intelligence, business.industry, business, Traffic sign recognition
Related Organizations
Any information missing or wrong?Report an Issue