A New Traffic Sign Recognition Technique Taking Shuffled Frog-Leaping Algorithm into Account

Pouya Demokri Dizji; Saba Joudaki; Hoshang Kolivand

doi:10.1007/s11277-022-09718-7

A New Traffic Sign Recognition Technique Taking Shuffled Frog-Leaping Algorithm into Account

Wirel Pers Commun. 2022;125(4):3425-3441. doi: 10.1007/s11277-022-09718-7. Epub 2022 Jun 28.

Authors

Pouya Demokri Dizji¹, Saba Joudaki¹, Hoshang Kolivand^{2

3}

Affiliations

¹ Department of Computer Engineering, Khorramabad Branch, Islamic Azad University, Khorramabad, Iran.
² School of Computer Science and Mathematics, Liverpool John Moores University, Liverpool, L3 3AF UK.
³ School of Computing and Digital Technologies, Staffordshire University, Staffordshire, UK.

Abstract

Everyday humans use cars to move faster, and the world is a chaotic place, and a little distraction or a mistake could be the reason for an accident and bring people great pain. An assistance system that can distinguish and detect signs on the roads and brings the driver's attention to road signs and make them aware of their meaning could be beneficial. The most important part of the Traffic Sign Recognition System is the algorithm. In this paper, a new way toward Traffic Sign Recognition algorithm taking the advantages of Color Segmentation, support vector machines, and histograms of oriented gradients on the GTSRB dataset is proposed. The unsupervised shuffled frog-leaping algorithm is employed for segmenting the images. The results show remarkable improvements by using meta-heuristic algorithms.

Keywords: HOG; Memeplex; SFLA; SVM; TSR; Unsupervised segmentation.