Citation

Zaibi A, Ladgham A, Sakly A. Int. J. Veh. Safety 2021; 12(1): 1-14.

Copyright

(Copyright © 2021, Inderscience Publishers)

DOI

10.1504/IJVS.2021.115888

PMID

unavailable

Abstract

This paper suggests a new system for the automated detection of road signs. This driver assistance system detects traffic signs that have a red border with different shapes (circular, triangular, hexagonal). So, our approach relies on Support Vector Machines (SVM) implementation for road signs detection supported by feature extraction technique supported employment of a range of filters from Gabor that simplifies the recognition of interest's points in our database. On the other hand, our approach has been improved on the Edited Shuffled Frogs Leaping Algorithm (ESFLA) optimisation technique that helps in road signs detection and this technique is termed Gabor-ESFLA-SVM. This strategy ensures an intelligent recognition system. The obtained results show that this optimised classification provides higher results compared to the previous dual classification Gabor-SVM and other research works published in a few articles.

Keywords: road signs with red border detection; ESFLA optimisation; optimal solution; Gabor wavelets; features extraction; Gabor representation; SVM classification; fitness function.

Language: en