Analysis and training of a traffic sign recognition neural network model

Abstract

Objective. The purpose of the research is to develop and train a neural network model based on convolutional neural networks for effective recognition of road signs in images.

Method. Deep learning methods were used, namely convolutional neural networks, which allow you to automatically extract image characteristics and train on a large data set. The research methodology included the following steps: collecting and preparing a variety of road sign data, creating and training a neural network model based on convolutional layers, applying data augmentation methods to improve model performance, and evaluating the model’s effectiveness on a test data set.

Result. A neural network model is developed that can classify various types of road signs based on input images with high accuracy. The model was trained on diverse and high-quality data, allowing it to generalize and recognize road signs in different lighting conditions and camera angles. The use of data augmentation techniques significantly increased the model’s performance and improved its generalization ability.

Conclusion. The study highlights the importance of using diverse and high-quality data to train a model and applying data augmentation techniques to improve its performance. The study confirms the effectiveness of using neural networks, especially convolutional neural networks, for the task of recognizing road signs in images.