Artificial Neural Networks enables solving many problems in which classical computing is not up to task. Neural Networks and Deep Learning currently provide the best solutions to problems in image recognition, speech recognition and natural language processing. In this paper a Neural Network, more specific - Convolutional Neural Network solution for the purpose of recognizing and classifying road traffic signs is proposed. Such solution could be used in autonomous vehicle production, and also similar solutions could easily be implemented in any other application that requires image object recognition.

Keywords: Неуралне мреже, конволуционе неуралне мреже, класификација, саобраћајни знакови.
Published on website: 16.7.2018