“Multi-Column Deep Neural Network for Traffic Sign Classification”, 2012-08 (; backlinks):
[retrospective; cf. DanNet] 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 parameterized 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.
[Keywords: deep neural networks, image classification, traffic signs, image preprocessing]