Traffic sign recognition plays a vital role in the intelligent transportation system, which increases traffic safety by providing safety and precautionary information about road hazards to drivers. Knowledge of how humans process the meaning of symptoms reduces the time it takes to respond to them and make decisions while driving. Although the expansion of the transportation network helps in the discussion of traffic, this expansion may not be feasible due to high financial costs, geographical and environmental constraints, as well as long-term improvements to transportation infrastructure. These limitations can be minimized with Traffic Management Systems (TMS). Efficient use of resources and waste reduction are key goals in managing a smart city, in which traffic and transportation activities have a significant impact. In smart city approaches, the use of intelligent processing methods in vehicles to increase safety is proposed without any interference in the driving process. This study addresses an innovative system that aims to assist councils in developing a road management plan and creating a framework for placing street signs and intelligent car systems using Google Images (GSV). Recent advances in machine memory detection technology have provided Google Automated Images with an automated approach to identifying and classifying street signs, allowing it to be used to produce a standalone image recognition system to improve traffic information monitoring and storage. This article reviews and compares studies and developments related to traffic signs and signs in smart cities and intelligent transportation systems. The results show a reduction in travel time, improved vehicle maintenance and transportation system logistics, better fleet utilization, reduced vehicle fuel consumption and CO2 emissions.