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

Summary

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.

doi: 10.1109/ijcnn.2011.6033458

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