Parallel license plate recognition scheme based on image splicing for intelligent transportation system

License plate recognition (LPR) is investigated as a promising automation technique for transportation system, for instance, automatic billing system for electronic parking lots, snapshot system of traffic violation, etc. Support Vector Machine (SVM) is a typical method for pattern recognition, and it works efficiently for traditional vehicle plate recognition systems, which process the vehicle images one by one in a serial perspective. On one hand, the number of vehicles is increasing rapidly in the transportation system, and on the other hand, more cameras need to be deployed to make the transportation system more intelligent. It means that more and more images would be snapshotted and they all need to be recognized timely. In this case, to improve the efficiency of LPR system, this paper proposes a parallel license plate recognition (PLPR) scheme, which can recognize multiple images simultaneously. Simulation results show that PLPR can reduce the average recognition time compared with the traditional recognition methods.