Identification of Indonesian vehicle registration plate by adaptive thresholding and region labeling algorithm

Every car has a unique label to identify the car. It is called a license plate or a vehicle registration plate. A vehicle registration plate (VRP) in Indonesia consists of a series of alphanumeric. The aim of this research is to identify and crop the VRP given a frontal image of a car. Image processing is done by converting the color image from a camera into grayscale image. It is transformed into binary image by using adaptive threshold. The position of the VPR from the frontal car image has to be detected first before cropping by using region labeling, filtering techniques. Experiments are conducted and system is able to identify the VRP above 95%.