Brazilian vehicle identification using a new embedded plate recognition system Edson Cavalcanti Neto a , Samuel Luz Gomes a , Pedro Pedrosa Rebouças Filho a , Victor Hugo C. de Albuquerque b,⇑ a Programa de Pós-Graduação em Energias Renováveis, Instituto Federal de Educação, Ciência e Tecnologia do Ceará, Maracanau, CE, Brazil b Programa de Pós-Graduação em Informática Aplicada, Universidade de Fortaleza, Fortaleza, Ceará, Brazil article info Article history: Received 5 January 2015 Received in revised form 11 February 2015 Accepted 20 March 2015 Available online 4 April 2015 Keywords: Expert system Vehicle access control Brazilian vehicle license plates Hough transform Edge canny detector Neural Network abstract Expert systems for parking lot access control are developed in vehicle management through tracking and number recognition. These systems commonly use cameras to iden- tify a vehicle through its license plates based on intelligent and optical character recogni- tion techniques. This paper presents a new system to detect and recognize Brazilian vehicle license plates, in which the registered users have permission to enter the location. For this, techniques of Digital Image Processing were used, such as Hough Transform, Morphology, Threshold and Canny Edge Detector to extract characters, as well as Least Squares, Least Mean Squares, Extreme Learning Machine, and Neural Network Multilayer Perceptron to identify the numbers and letters. The system was tested with 700 videos with a resolution of 640  480 pixels and AVI format, granting access only when the plate was registered, getting a 98.5% success rate on the tested cases. The movement detection step is linked to the system, becoming faster and more accurate in real time. Thus, can be concluded that the proposed system is a promising tool with high potential which can be applied commercially. Ó 2015 Elsevier Ltd. All rights reserved. 1. Introduction Developing countries have high rates of violence and insecurity in their societies, and Brazil is no different. However, access control to private locations is important, and in many cases is required. In the past few years, intelligent traffic controls have been used for tool booths, real-time monitoring and park- ing systems [1]. These systems can use cameras to identify vehicles and license plates using Character Recognition [2]. Al-Ghaili et al. [3] presents a fast vertical edge detection algorithm (VEDA) based on adaptative threshold, which enhances the speed of the car-license-plate detection method. Al-Ghaili et al. [3] also compares the VEDA to the Sobel operator in terms of accuracy, algorithm com- plexity, and processing time. Mashuk et al. [4] locates the plate by applying an empirical crop, then it applies a med- ian filter to reduce the noise and uses morphology to seg- ment the characters. For the recognition, Mashuk et al. [4] uses a four layered Backpropagation neural network and uses 128 features, which are the pixels from the binarized image. Qing-kun et al. [5] presents license plate recognition based on mathematical morphology that uses edge ero- sion, connected component analysis and geometry find http://dx.doi.org/10.1016/j.measurement.2015.03.039 0263-2241/Ó 2015 Elsevier Ltd. All rights reserved. ⇑ Corresponding author. E-mail addresses: edsoncavalcanti@hotmail.com (E.C. Neto), samuel. luz@gmail.com (S.L. Gomes), pedrosarf@ifce.edu.br (P.P. Rebouças Filho), victor.albuquerque@unifor.br (V.H.C. de Albuquerque). Measurement 70 (2015) 36–46 Contents lists available at ScienceDirect Measurement journal homepage: www.elsevier.com/locate/measurement