PROJECT TITLE :

Toward End-to-End Car License Plate Detection and Recognition With Deep Neural Networks

ABSTRACT:

In this study, we look at the topic of detecting and recognizing car license plates in natural scene photos. We present a unified deep neural network that can recognize letters and localize license plates in a single forward pass. The entire network can be trained from start to finish. Unlike prior systems that treat license plate detection and recognition as two independent problems to be solved one at a time, our method handles both objectives with a single network. It not only prevents intermediate errors from accumulating, but it also speeds up processing. Four data sets containing photographs captured from various scenes under varied conditions are tested for performance evaluation. Extensive experiments demonstrate the efficacy and efficiency of our proposed strategy.