Korean License Plate Recognition System Using Combined Neural Networks

초록

We developed a deep learning application to detect and recognize Korean cars' license plates from images. It is an advanced application that targets to provide deep learning solution that can be applied in many areas including Intelligent Transportation System, Internet of Things and Smart City. Despite, there have been many approaches and studies on license plate localization, character segmentation and recognition, there have not been highly demanded results particularly using deep neural networks. Traditional approaches on license plate detection have achieved quite a high accuracy in detection and recognition, in which mostly Optical Character Recognition (OCR) is used. Nevertheless, in this research, we developed our own method that is a combination of scene text recognition technique with Geometrical Image Transformation (GIT) to recognize number plates for combined neural networks and achieving 99.8% and 95.7% of detection and recognition accuracy respectively.

키워드