期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2019
卷号：2240
页码：208-211
出版社：Newswood and International Association of Engineers
摘要：Automatic license plate recognition system has been
found convenient in numerous transportation applications. The
project aims to develop an FPGA based neural network model
that can recognize numbers on vehicle license plates. License
plate character recognition becomes challenging when the images
have less lighting, or when the number plate is in a broken
condition. This would require human intervention for
recognizing a character. Hence, a fully automated Number Plate
Recognition system needs a better model. In this work, a
feedforward neural network that can recognize numbers is
implemented on Altera’s Cyclone II DE1 FPGA board. The
weights required for the system will be obtained by training an
NN model on MATLAB using a pool of handwritten digits. The
RTL design is synthesized and programmed on FPGA using
Quartus II 13.0sp1. The final FPGA model shows an accuracy of
60%.
关键词：pattern recognition; FPGA; neural network
model
