TRAFFIC SIGN RECOGNITION USING CNN

COMPUTER SCIENCE AND ENGINEERING

Traffic sign recognition is very useful in automatic driver assistance systems. A convolutional neural network is a class of deep learning networks, used to examine and check visual imagery. It is used to train the image classification and recognition model because of its high accuracy and precision. Convolutional neural networks (CNN) execute both the feature extraction and the classification. These methods could achieve impressive results but usually on the basis of an extremely huge and complex network, since the fully-connected layers in CNN form a classical neural network classifier, which is trained by gradient descent-based implementations, the generalization ability is limited and sub-optimal. The main objective is to classify, recognize, and identify the traffic signs using convolutional neural networks which are made up of neurons that has learnable weights and biases that helps in giving the high performance in identifying the traffic signs even in its tough vulnerable conditions. The goal of the traffic sign recognition project is to build a convolutional neural network (CNN) which is used to classify traffic signs and to enhance safety, as it allows drivers to concentrate on the traffic in complicated situations. The system also helps motorists to keep to the speed limit. We should train the model so it can decode traffic signs from natural images using the dataset. The existing system approach makes sure a safe and comfortable driving experience by developing and giving an accurate road sign detection and recognition system which will forewarn the driver ahead of approaching signs on the road while driving.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.