Video-Based License Plate Recognition Using Single Shot Detector and Recurrent Neural Network

Each vehicle has its own identity, in other words, the vehicle number plate. This identity often uses in parking processing, security development, and toll systems. It is necessary to develop an automated system that can be used and supported by vehicle number plates known as License Plate Recognition (LPR). This paper proposed the LPR system based on video data CCTV using the Single Shot Detector to localize the license plate, the Connected Component Labeling to do the character segmentation, and Recurrent Neural Network to recognize the characters on the license plate. This study shows our proposed method works well based on the experimental result, with an average accuracy of 94.01 % for license plate localization, 84.08% for character segmentation, and 93.53% for character recognition.