Toward an optimal convolutional neural network for traffic sign recognition

Hamed Habibi Aghdam; Elnaz Jahani Heravi; Domenec Puig

doi:10.1117/12.2228582

8 December 2015 Toward an optimal convolutional neural network for traffic sign recognition

Hamed Habibi Aghdam, Elnaz Jahani Heravi, Domenec Puig

Proceedings Volume 9875, Eighth International Conference on Machine Vision (ICMV 2015); 98750K (2015) https://doi.org/10.1117/12.2228582
Event: Eighth International Conference on Machine Vision, 2015, Barcelona, Spain

Abstract

Convolutional Neural Networks (CNN) beat the human performance on German Traffic Sign Benchmark competition. Both the winner and the runner-up teams trained CNNs to recognize 43 traffic signs. However, both networks are not computationally efficient since they have many free parameters and they use highly computational activation functions. In this paper, we propose a new architecture that reduces the number of the parameters 27% and 22% compared with the two networks. Furthermore, our network uses Leaky Rectified Linear Units (ReLU) as the activation function that only needs a few operations to produce the result. Specifically, compared with the hyperbolic tangent and rectified sigmoid activation functions utilized in the two networks, Leaky ReLU needs only one multiplication operation which makes it computationally much more efficient than the two other functions. Our experiments on the Gertman Traffic Sign Benchmark dataset shows 0:6% improvement on the best reported classification accuracy while it reduces the overall number of parameters 85% compared with the winner network in the competition.

Citation Download Citation

Hamed Habibi Aghdam, Elnaz Jahani Heravi, and Domenec Puig "Toward an optimal convolutional neural network for traffic sign recognition", Proc. SPIE 9875, Eighth International Conference on Machine Vision (ICMV 2015), 98750K (8 December 2015); https://doi.org/10.1117/12.2228582

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available