Traffic sign recognition system (TSRS) is a significant portion of intelligent transportation system (ITS). Being able to identify traffic signs accurately and effectively can improve the driving safety. This paper brings forward a traffic sign recognition technique on the strength of deep learning, which mainly aims at the detection and classification of circular signs. Firstly, an image is preprocessed to highlight important information. Finally, the detected road traffic signs are classified based on deep learning. a traffic sign detection and identification method on account of the image processing is proposed, which is combined with convolutional neural network (CNN) to sort traffic signs is developed. On account of its high recognition rate, CNN can be used to realise various computer vision tasks and TensorFlow is used to implement CNN. Using a fully connected neural network to make an image classification requires a large number of layers and neurons in the network, which increases the number of parameters leading the network to over-fitting. This project presents a convolutional neural network implementation used for traffic signs recognition. The basic proposed network together with the different improvement operations allows us to be aware of which parts and phases that have the control on the system reliability.