Deep Classifiers-Based License Plate Detection, Localization and Recognition on GPU-Powered Mobile Platform

Abstract

The realization of a deep neural architecture on a mobile platform is challenging, but can open up a number of possibilities for visual analysis applications. A neural network can be realized on a mobile platform by exploiting the computational power of the embedded GPU and simplifying the flow of a neural architecture trained on the desktop workstation or a GPU server. This paper presents an embedded platform-based Italian license plate detection and recognition system using deep neural classifiers. In this work, trained parameters of a highly precise automatic license plate recognition (ALPR) system are imported and used to replicate the same neural classifiers on a Nvidia Shield K1 tablet. A CUDA-based framework is used to realize these neural networks. The flow of the trained architecture is simplified to perform the license plate recognition in real-time. Results show that the tasks of plate and character detection and localization can be performed in real-time on a mobile platform by simplifying the flow of the trained architecture. However, the accuracy of the simplified architecture would be decreased accordingly.

A Vision-Based Machine Learning Method for Barrier Access Control Using Vehicle License Plate Authentication

“…Another deep learning method based on the AlexNet [46] was introduced by Lee et al [47] for AVLPR, where they re-trained the AlexNet to perform their task on their database and achieved 95.24% correct recognition. Rizvi et al [5] also proposed a deep learning based approach for Italian vehicle license plate recognition on a mobile platform. They utilized two deep learning models, one to detect and localize the license plate and the characters present, and another as a character classifier.…”

“…In this paper, we focus on the algorithmic aspects of an AVLPR system, which includes the localization of a vehicle license plate, character extraction and character recognition. For the process of license plate localization, researchers have proposed various methods including, connected component analysis (CCA) [1], morphological analysis with edge statistics [2], edge point analysis [3], color processing [4], and deep learning [5]. The rate of accuracy for these localization methods varies from 80.00% to 99.80% [3,6,7].…”

Recognition of License Plates Symbols of Different Formats

“…In [11] detection of a license plate and its recognition is performed using convolutional neural networks without a separate segmentation step. Also, possible simplifications of the created neural networks for use on mobile platforms are indicated.…”

“…Recognition is performed using correlation analysis. During the research it was found that such method of detecting a license plates № 1 (11), 2018 ТЕХНІЧНІ НАУКИ ТА ТЕХНОЛОГІЇ TECHNICAL SCIENCES AND TECHNOLOGIES 107 works well under the some special conditions and is completely inappropriate for others. Segmentation of this method obviously will not work in case of dirty plates, and as a result the license plate can not be correctly recognized.…”

License Plate Recognition for Parking Management System using UAV Vision

“…Since LPR is applied to almost all traffic control systems besides PMS, other studies are also being actively studied. For example, there are many research articles such as * Corresponding Author LPR using Convolutional Neural Network and LPR in mobile system environment [3], [4]. This study proposed a new PMS which improves LPR performance of drones by using existing parking system.…”