Abstract
License plate detection and recognition is a crucial and difficult issue for an ITS (Intelligent Transportation System). This paper proposes a robust license plate detection method using vertical boundary pairs and geometric relationships. The proposed method first tries to find a candidate region for a license plate region or character, if a candidate if found, then it estimates the candidate region of the license plate; by detecting the vertical boundary pair from the vertical sobel edge image that is processed with noise removal. In the next step, the method verifies entire candidate region, and finds the optimal region by comparing the regions with each other. Simultaneously, we can classify the type of the license plate. This method is able to cope with varying complexities such as poor illumination, blurring and tilt. Experimental results demonstrate efficiency and robustness by detecting large number of license plates correctly.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.