Automatic car license plate recognition

Abstract

In most traffic applications, someone gathers information manually at the scene or watching the video of a scene. With automatic car license plate recognition using image processing techniques, new ways of capturing traffic data are evolved. It works by processing a sequence of images captured by a video camera and identifying the vehicle’s license plate. Locating the car license plate in an image or video frame of a car is an important step in car license plate recognition/identification applications. In this thesis, we propose a morphology based method for license plate extraction from car images. The algorithm uses morphological operations on the preprocessed, edge images of the vehicles. Characteristic features such as license plate width and height, character height and spacing are considered for defining structural elements for morphological operations. The localised license plates are segmented into individual character images by connected component labeling algorithm and the segmented characters of license plate are recognized by template matching approach. Entire system is implemented in Matlab and is tested over a large database of car images of various countries.