Multiple License Plate Extraction Based on Mathematical Morphology and Component Filtering in Indian Traffic Conditions

In a vehicle license plate identification system, locating the license plate in the image or video of a vehicle is an important step before final recognition. In the proposed method care has been taken up to extract license plate of motorcycle (size of plate is small and double row plate), car (single as well as double row type), transport vehicle such as bus, truck, dirty plates as well as multiple license plates present in an image frame under consideration. This paper presents a multiple license plate detection algorithm based on mathematical morphology and component filtering. The proposed algorithm consists of three main stages. The three stages involve pre-processing followed by morphological operations and connected component analysis. The algorithm is able to detect single as well as multiple license plates accurately. The algorithm is tested on set of 750 samples containing the vehicle images from India as well as other countries. The success rate is 98.8% for single license plate extraction and 95% for multiple extraction case.