EXPLOITABLE EDGE ANALYSIS FOR FREE FLOW VEHICLE PLATE LOCALIZATION

• Main Authors: Abbas Salimi Zaini, Siti Norul Huda Sheikh Abdullah, Azizi Abdullah, Nelson Budin Sana, Shariffpudin Basiron
• Format: Article
• Language: English
• Published: UKM Press 2021-06-01
• Series: Asia-Pacific Journal of Information Technology and Multimedia
• Subjects: license plate localization; vertical blobs projection; edge segmentation; plate recognition
• Online Access: https://www.ukm.my/apjitm/view.php?id=200

In Malaysia, vehicle recognition system (VRS) such as vehicle plate recognition and counting, is rapidly growing and applied in many areas such as to identify vehicle identities for the law enforcement by authorities and electronic toll collection by highway agencies. Uncovering the region of interest in chaotic illumination environment at free flow road makes localizing license plate is critical process of VRS. Available edge vertical projection claimed to be robust to illumination, however, it tends to create false edges and sensitive to noises that can hinder the recognition performance. Thus, this research aims to propose a license plate localization method that based on exploitable edge analysis.comprising four main steps, namely pre-processing, rectangular blob searching, analysis and the vertical rectangular blobs projection. It calculates total and exploit edge information at y axis of the image. The proposed method is then tested on the European number plate datasets i.e. Baza Slika which contains about 167 vehicle images and Ondrej which contains about 97 vehicle images. The experimental results show that the proposed method outperforms the Ondrej method by obtaining accuracy of 95% on Baza Slika dataset and slightly lower by an accuracy of 91% on the Ondrej dataset. Then, the proposed method tested on the Malaysia vehicle dataset namely Tol Sungai Long data set which contains about 584 images of different illumination conditions, i.e. 297 images in the morning, 140 images in the afternoon and 147 images in the night. The proposed method outperforms other approaches with accuracy of 91.24%, 93.57% and 75.51% in the morning, evening and night respectively.