A novel fusion mixture of active experts algorithm for traffic signs recognition

Abstract

Traffic sign recognition is an important problem in today’s applications. In this paper, by combining ensemble and active learning methods, a novel fusion mixture of active experts algorithm is proposed for this problem. The active learning algorithm is a popular method for reducing the number of samples. The primary goal of active learning is diminishing complexity, increasing the convergence rate, speeding up training process, and decreasing the cost of samples labeling. The active learning, hence, chooses informative samples to train. In addition, ensemble methods are a combination of simple classifiers for improving accuracy. Each classifier tries to learn a region of dataset better than other regions that all opinions are considered on ensemble methods as an ultimate decision. The mixture of experts is one of the most modern hybrid methods in which the training process takes a relatively long time, and it is a problem for large datasets. Our proposed Mixture of Active Experts tries to solve this problem. It decreases the training time process and increases the speed of convergence for finding optimal weights by selecting only informative samples in active learning phase. It is also applicable for online situations, in which the model should be trained continuously. The results of different experiments on German Traffic Sign Recognition Benchmark dataset demonstrate that the proposed method shows 96.69% accuracy and achieved the 6th rank among all the state of the art algorithms using smaller number (only 60%) of training samples.