Article
A DEEP NEURAL NETWORK APPROACH FOR TRAFFIC SIGN RECOGNITION
Road signs are crucial for ensuring a safe and orderly flow of traffic. Negligence in failing to read traffic signs and misinterpreting them is a significant contributor to auto accidents. The suggested system assists in identifying traffic signs and alerting the driver through speaker so that he or she may make the appropriate selections. Convolutional Neural Network (CNN) training is used in the proposed system to aid in the detection and categorization of images of traffic signs. To increase the accuracy of a given dataset, a set of classes are created and trained. We used the German Traffic Sign Benchmarks Dataset, which includes 51,900 photos of traffic signs in around 43 categories. About 98.52 percent of the execution was accurate. A voice alarm is broadcast over the speaker when the system recognizes the sign to inform the driver. The proposed system also has a component where drivers of moving vehicles are informed of nearby traffic signs so they are aware of the laws they should observe. The system's goal is to protect the driver, passengers, and pedestrians from harm.
Full Text Attachment
