Improved Automatic License Plate Recognition (ALPR) system based on single pass Connected Component Labeling (CCL) and reign property function

Abstract

This paper presents improved Automatic License Plate Recognition (ALPR) system based on Single Pass Connected Component Labeling (CCL). This research describes an ALPR system which is capable of distinguishing license plates under various conditions, such as distance from the camera, rotation angle between camera and vehicle (0° to +/-45°) and also poor illumination contrast condition (different weather condition, different lighting condition and physical tilted or damage of license plate). In our method, we apply adaptive thresholding filter to preprocessing step for image enhancement under various conditions, and then to find the location and characters of license plate at the same time we apply improved single pass Connected Component Labeling and regio property function that compared with other methods is fast and accurate. We determine the license plate characters and location according to appropriate size, aspect ratio, distance and connectivity of characters. Finally by using Optical Character Recognition (OCR) we find the characters on each license plate in an image. Image results show the accuracy and reliability of this method.