An Approach of Locating Korean Vehicle License Plate Based on Mathematical Morphology and Geometrical Features Ihsan Ullah 1 1 Division of Computer Science and Engineering, Chonbuk National University, Jeonju 561-756, South Korea Ihsanullah736@gmail.com Hyo Jong Lee 1, 2,* 1 Division of Computer Science and Engineering, 2 CAIIT, *Corresponding author Chonbuk National University, Jeonju 561-756, South Korea hlee@chonbuk.ac.kr Abstract— In a vehicle license plate identification system, plate region detection is the crucial step before the ultimate recognition. In most of the traffic-related applications such as searching of stolen vehicles, road traffic monitoring, airport gate monitoring, speed checking and parking access control. This paper is focused on license plate detection, license plate detection in this paper is based on mathematical morphology and considers features like license plate width, height, ratio, and angle. The advantage of the proposed system is that it works for all types of license plates which differ in size and shapes. The proposed system archived promising results. Keywords—license plate detection; morphology; lp localization; lpd I. INTRODUCTION Vehicles are a necessary part of our existing life. With the fast improvement of Intelligence transportation system, automatic identification of vehicles has played a vital role in many applications during the past two decades for examples, the identification system can be applied to management of parking services [1], controlling traffic flow[2], access- control systems, automatic toll collection[3], traffic analysis, vehicle tracking system[4], and [5] identification of stolen vehicle can deliver important information to police for searching the suspected vehicles and so on. Conventionally, license plates are used for identification of every vehicle. License Plate Recognition (LPR) is the process of automatically locating and extracting license plate information. In the LPR system, license plate detection is the most critical step. It is exceptionally difficult to detect license plate from a cluttered background efficiently because of the varying brightness, perspective distortion, interference characters, etc. Most of the previous license plate detection algorithms are restricted to certain working conditions, such as fixed backgrounds, known the color, or fixed size of the license plates[6-9]. Therefore, detecting license plate under various complex environments is still a challenging problem. In recent years, LPR has become popular due to its practical significance in image processing applications. Numerous improvements are suggested in the literature [10, 11] which present effective and precise systems to detect license plate and recognize the numbers and character on the license plate in complex scenes which directly affects the system’s overall performance. A large number of researches has been carried out for the development of this technology recently, and many techniques have been proposed, such as the methods base on edge extraction [12], Hough transform [13], color feature [14], and histogram analysis [15]. But most previous works have in some way limited their working environments, such as limiting them to indoor scenes, fixed background, fixed brightness, prescribed driveways or limited vehicle speeds. License plate numbers uniquely identify a specific vehicle which varies in shape and formats, because every country has particular license plate layout which differs in their sizes and colors. So there is a requisite for the authorities to develop such LPR system which is suitable for the vehicle License Plate different format. In general, the LPR system has the following parts: the obtainment of the input image, the image preprocessing, detection of the license plate, segmentation and the character recognition [16]. The basic block diagram of the system is shown in Figure 1. Fig. 1. The basic block diagram of the License Plate Recognition (LPR) System. 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 832 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 832 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836 2016 International Conference on Computational Science and Computational Intelligence 978-1-5090-5510-4/16 $31.00 © 2016 IEEE DOI 10.1109/CSCI.2016.161 836