Vehicle Logo Recognition Based on Optimized Dictionary and Robust Collaborative Representation

Abstract

Recently, with the increase of the car ownership, transportation network becomes more and more complex, the traffic management system is facing a serious challenge. Therefore, vehicle recognition plays a decisive role. The vehicle logo contains information of a vehicle, so vehicle logo can be used to identify vehicle models. Considering the problem of the high calculation cost of the vehicle recognition based on sparse representation, a vehicle logo recognition method based on optimized dictionary and robust collaborative representation is proposed. This method not only has a high recognition rate but also reduces the computation time. In our method, HOG feature is selected to represent the vehicle logo image. HOG features are extracted from training samples and testing samples respectively, and then dictionary learning method based on Fisher discrimination criterion is adopted to optimize the train samples. Finally, robust collaborative representation is used to recognize the vehicle models. The experimental results show that our method achieves a high recognition rate 98.2% and reduces the computation time.