Automatic License Plate Detection System for Myanmar Vehicle License Plates

Abstract

License Plate Detection is an intelligent system to find the exact license plate by analyzing image/video data for automatic license plate recognition (ALPR) system. The proposed system used image data. There is much early research has been done for ALPR purposes, however, it was still challenging tasks for accurately detect license plates in the open environment. The main difficulties lie in the diversity of plates such as language, font, color, and type of the number plates that differ across nations and conditional variations such as various background scenes and illumination when captured. The fundamental ALPR system consists of three processes: license plate detection, character segmentation, and character recognition. Proposed system focused on license plate detection based on image processing technology that is a crucial step for the whole ALPR system. A Myanmar License plate has a white boundary for every different color of plates, thus the proposed system applied an edge-based approach for any color of plates, and the plate region will remain because of its white boundary. After edge detection, morphological operation has been applied as it can add or remove pixels from/to the objects in an image. Thus the license plate can be extracted accurately. Finally, the bounding box technology was applied to extract only the number plate region properly.