Research On Method Of Vehicle-logo Identification

Vehicle-logo identification system is a practical technology which through computer vision, image processing and pattern recognition methods to extract the information of vehicle-logo from vehicle images to determine the vehicle's brand information. Vehicle-logo identification technology is one of the important parts to achieve intelligent traffic management. Vehicle-logo recognition technology has important practical value in this filed.Vehicle-logo recognition is an important research topic in Intelligent Transportation, and it includes two key parts: vehicle-logo location and vehicle-loge recognition. In this paper, we did research into Vehicle-logo recognition based on extensive literature and propose two Vehicle-logo recognition methods.A method for vehicle-logo recognition based on independent component analysis and support vector machine is proposed. First, we do some preprocessing to all the vehicle's images. Then we extract vehicle-logo image's feature base on independent component analysis technology. Last, we apply support vector machine to design the classifier for recognizing vehicle-logos. Experimental results show that the proposed method in this paper has higher accuracy, quicker speed than other methods for vehicle-logo recognition.A method for vehicle-logo recognition based on Independent component analysis and fuzzy support vector machine is proposed. The kernel of this method extracting vehicle-logo image's feature base on independent component analysis technique and Taking fuzzy support vector machine as classifier to recognize the vehicle-logos. Experimental results show that the proposed method is a way which has quicker speed, higher accuracy and stronger robustness than other traditions methods for vehicle-logo recognition.