A Scalable and Efficient Multi-Label CNN-Based License Plate Recognition on Spark

Authors:
  • WZWeishan Zhang
    Weishan Zhang
  • BXBing Xue
    Bing Xue
  • JZJiehan Zhou
    Jiehan Zhou
  • XLXin Liu
    Xin Liu
  • HLHao Lv
    Hao Lv

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.

This publication has 10 references indexed in Scilit: