Comparing Classification Performances between Neural Networks and Particle Swarm Optimization for Traffic Sign Recognition

This paper compares classification performances of two techniques for traffic sign recognition, namely, neural networks and particle swarm optimization. Neural networks and particle swarm optimization are applied to the problem of identifying all types of traffic signs used in Thailand, namely, prohibitory signs (red or blue), general warning signs (yellow) and construction area warning signs (amber). The comparison indicates that the neural network technique has higher correct recognition rates than particle swarm optimization for traffic sign recognition. Moreover, neural networks require less computer processing time than particle swarm optimization in the traffic sign recognition system. Key-Words: Classification techniques, traffic sign recognition, neural networks, particle swarm optimization