Title: Bees algorithm and support vector machine for Malaysian license plate recognition

Authors: Nahlah M. Shatnawi

Addresses: Department of Computer Science, Yarmouk University, Irbid, Jordan

Abstract: Nowadays the increasing use of vehicles in modern life raises the problem of designing techniques that support effective traffic monitoring and vehicle identification. License plate recognition is an advanced machine vision technology used to identify vehicles by their license plates without direct human intervention. License plate recognition system major steps include image capturing, preprocessing, segmentation, feature extraction and classification. In this paper, a complete system for Malaysian license plate recognition is proposed to handle special Malaysian license plates under different conditions. In the proposed system, peak signal to noise ratio (PSNR) and bees algorithm is used in preprocessing and segmentation stages, Sobel method for edge detection, and support vector machine for classification. The proposed system is applied to dataset that is consisted of 1,216 grey scale images, and is compared with different methods in segmentation and classification. Results show the robustness of the proposed system, making them suitable for more real world applications.

Keywords: image processing; segmentation; plate recognition; bees algorithm; support vector machine; SVM.

DOI: 10.1504/IJBIS.2018.092527

International Journal of Business Information Systems, 2018 Vol.28 No.3, pp.284 - 298

Received: 29 Sep 2016
Accepted: 25 Nov 2016

Published online: 24 Jun 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article