Road sign recognition with Convolutional Neural Network

Extracting the contents of a digital image has been proven a hard problem for computers. Since for them, an image is only a matrix of values, knowing what structures a human would recognize in this image, is a nontrivial problem. In this paper, we have implemented and tested a system of detection of road signs. The approach taken in this work consists of using convolutional neural network where this network is supposed to distinguish between different classes of signs (stop, attention etc.) and the final model will then be integrated to the autonomous cars. Tests carried out on the dataset GTSRB (The German Traffic Sign Recognition Benchmark) shows the performance of the system currently being developed.

[1]  Max Q.-H. Meng,et al.  An efficient neural network approach to dynamic robot motion planning , 2000, Neural Networks.

[2]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[3]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[6]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[7]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[8]  Lior Shamir,et al.  Pattern Recognition Software and Techniques for Biological Image Analysis , 2010, PLoS Comput. Biol..

[9]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[10]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

[13]  Yann LeCun,et al.  Traffic sign recognition with multi-scale Convolutional Networks , 2011, The 2011 International Joint Conference on Neural Networks.