Research on the Optimal Machine Learning Classifier for Traffic Signs

Now autonomous driving is a hot topic, and the identification of traffic signs also extremely important for driving. This paper mainly compares difference Support Vector Machine (SVM), Multilayer Perceptron (MLP), Logistic Regression (LR) Classifier in sign classification. The effect initial image processing on classification accuracy studied. found that sharpening significantly improved Based results various situations, author that, this paper, SVM classifier with best effect, but LR not much worse than when sharpened.