Published Paper Details:

This study describes the design and implementation of a convolutional neural network (CNN)-based traffic sign detection and identification system. The number of accidents caused by failure to observe traffic signs and follow traffic laws has been steadily growing. The use of synthesized training data generated from road traffic sign pictures enables for the resolution of difficulties with traffic sign detection databases that differ between nations and regions. This technology is used to create a library of synthesized images for detecting traffic signs under varied lighting situations. With this data set and a perfect CNN, a data driven can develop, traffic sign recognition detection system that performs well throughout training and recognition operations and has a high detection accuracy. This reduces the likelihood of accidents and allows the driver to focus on driving rather than studying every traffic sign. The goal of this work is to present a practical approach for detecting and recognizing traffic signs in India. The proposed system comprises two main stages that is traffic sign detection and traffic sign recognition. In the detection stage, the system utilizes a CNN to identify regions of interest (ROIs) that potentially contain traffic signs. The recognition stage involves the classification of the detected ROIs using a CNN based classifier. The proposed system was trained and tested using a publicly available traffic sign dataset, achieving high accuracy rates in both detection and recognition stages. The system's performance was evaluated using various metrics, including accuracy, precision, recall and F1 score, demonstrating its effectiveness and robustness for traffic sign detection and recognition tasks. The results demonstrate the effectiveness and efficiency of the proposed system, which can be used for various real world applications, such as advanced driver assistance systems (ADAS), autonomous driving and traffic management.