A Scalable and Efficient Multi-Label CNN-Based License Plate Recognition on Spark
Authors:
- Weishan ZhangWZWeishan Zhang
- Bing XueBXBing Xue
- Jiehan ZhouJZJiehan Zhou
- Xin LiuXLXin Liu
- Hao LvHLHao Lv
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1738-1744
Abstract
Surveillance cameras are being rapidly deployed for facilitating smart transportation. Recognizing the vehicle license plate from massive videos becomes a challenge in context of system scalability and efficiency. This paper proposes a novel algorithm for scalable and efficient license plate recognition (SELPR). The SELPR algorithm first locates the license plate using a YOLO (You Look Only Once) network and recognizes the license plate using multi-label convolutional neural network (Multi-label CNN). We deploy the SELPR algorithm to the Apache Spark framework to evaluate its scalability and efficiency in parallel processing. The results demonstrates that SELPR can achieve synthesized performance with 95% recognition accuracy, better processing efficiency and scalability on a Spark cluster.Keywords
This publication has 10 references indexed in Scilit:
- A Deep-Intelligence Framework for Online Video ProcessingIEEE Software, 2016
- A smart camera for the surveillance of vehicles in intelligent transportation systemsMultimedia Tools and Applications, 2015
- An Improved Template Matching Algorithm for Car License Plate RecognitionInternational Journal of Computer Applications, 2015
- Vehicle license plate recognition using visual attention model and deep learningJournal of Electronic Imaging, 2015
- An Iranian License Plate Recognition System Based on Color FeaturesIEEE Transactions on Intelligent Transportation Systems, 2014
- Extensible Video Processing Framework in Apache Hadoop2013
- Vertical-Edge-Based Car-License-Plate Detection MethodIEEE Transactions on Vehicular Technology, 2012
- Automatic License Plate Recognition (ALPR): A State-of-the-Art ReviewIEEE Transactions on Circuits and Systems for Video Technology, 2012
- Automatic Number Plate Recognition System for Vehicle Identification Using Optical Character Recognition2009
- MapReduceCommunications of the ACM, 2008