TRAFFIC SIGN RECOGNITION USING DEEP LEARNING
Amir, Afia Binte, Nisa, Umme Habiba, Shafi, Ali Ashab, Reza, Md. Rafid-Ur · International Research Journal of Modernization in Engineering Technology and Science · 2023
In recent times, there has been a significant focus on the advancement of smart technology, such as smart cars, and its impact on society.As part of this trend, researchers have developed a novel method for recognizing road traffic signs using deep learning.This approach has the potential to greatly enhance the development of Advanced Driver Assistance Systems (ADAS) and autonomous vehicles.The system's architecture is designed to identify key features from traffic sign images and classify them into different categories.To achieve this, a modified LeNet-5 network is used to extract a deep representation of the traffic signs for recognition.This network includes a Convolutional Neural Network (CNN) that is adapted by connecting the output of all convolutional layers to a Multilayer Perceptron.The researchers trained this method using the German Traffic Sign Dataset and achieved promising results in recognizing traffic signs.