CNN MODEL FOR TRAFFIC SIGN RECOGNITION

The traffic sign recognition framework (TSRS) is an important component of intelligent transportation systems (ITS). Accurately identifying traffic signs can improve driving safety. This research provides a traffic sign recognition approach based on profound learning. It primarily focuses on the location and order of roundabout signs. First, a photograph undergoes pre-processing to highlight important facts. Hough Transform is used to distinguish and find regions. Finally, the unique street traffic signs are analyzed for further understanding. This paper proposes a photo handling-based traffic sign discovery and distinguishing proof technique that is combined with convolutional brain organization (CNN) to sort traffic signs. CNN is useful for recognizing many PC vision tasks due to its high recognition rate. TensorFlow is used to implement CNN. We have a recognition accuracy of over 98.2% for the roundabout image in the German informative collections. KEYWORDS——traffic sign recognition, traffic sign detection, deep learning, convolutional neural network