STM Journals Peer-reviewed research from Consortium e-Learning Network

Recent Trends in Electronics Communication Systems

Traffic Sign Detection and Recognition Using Deep learning based- Convolutional Neural Network Algorithm

  1. Avani Goel
  2. Vandana Dubey

Abstract

The concept of Deep Convolutional Neural Organizations (CNNs) is a quickly arising new zone for Automatic traffic sign detection and recognition among the few master frameworks, such as independent driving and driver assistance. Here, in this paper, for traffic sign detection, we have utilized another methodology that uses a newly developed identification calculation and an RGB-based tone thresholding procedure. Results of the proposed identification and acknowledgement approaches are assessed on German Traffic Sign Detection dataset. Moreover, this work incorporates execution and examination of Deep Learning based designs for the grouping of 43 unique kinds of traffic signs. Also, well known Convolutional Neural Network based structures were assessed with respect to the accuracy of classification and prediction speed. Finally, we have also suggested an effective CNN method that gives high accuracy and precision as well in the light of the results achieved.

Keywords

Support