Vehicle License Plate Detection Using Image Segmentation and Morphological Image Processing

This paper presents an image segmentation technique to segment out the Region of Interest (ROI) from an image, in this study, the ROI is the vehicle license plate. In order to successfully detect the license plate an improvised Sliding Concentric Window (SCW) algorithm has been developed to perform the segmentation process. In this proposed model, vehicle images were obtained and the SCW algorithm has been performed to segment out the ROI and then Morphological Image Processing techniques named erosion and dilation have been used to locate the license plate. In order to validate our proposed model, we have used a dataset where the images of the vehicles have been taken from a different angle that contains natural background and different lighting conditions. It has been observed that the proposed model exhibits 86.5% accuracy rate for our tested dataset. In addition to that, a comparative study has been carried out between two different techniques (Improved SCW and Modified Bernsen Algorithm) of ROI detection to illustrate their accuracy rate. It has been found that the accuracy rate of the proposed model of VLP detection is higher than some other traditional algorithms.