Vehicle Identification Based on the Model

Abstract

Now a day's vehicle recognition has become a wide area of research. Vehicle recognition has several applications such as in automatic parking, toll gate management etc., Because of numerous applications, vehicle recognition in computer vision has become a research area in Intelligent Transport System (ITS). There are many different vehicles from different manufacturers which are increasing day by day. Analyzing the attributes of these vehicles and recognizing different vehicles is a complex task. The main objective of this project is vehicle identification. Vehicles can be identified by performing recognition of its iconic license plate but the License Plate Recognition System does not work when license plate is manipulated, missing or covered. Another important attribute of a vehicle is its logo which contains important information about the car and as it cannot be changed easily. Logo plays an important role in recognition of vehicles. Here vehicle recognition is concentrated based on logos in order to give the manufacturers name or brand. Vehicle recognition is performed by extracting logo using ROI selection. Then by using gray level co-occurrence matrix feature extraction method features are extracted and classification is performed based on probabilistic neural network.