Deep License Plate Recognition in Ill-Conditioned Environments With Ill-Conditional Data Augmentation

Abstract

In general, the conventional LPR systems consist of the following modules: feature extraction, license plate locating, character segmentation, and character recognition. The performances of these module are strongly correlated with some low level image features, e.g., edges, colors, and textures. These low level image features can be influenced significantly by the illumination and view angle variations such that the recognition accuracy is degraded. Recently, the deep learning technologies make the conventional vision-based recognition technologies getting significant improvement in terms of feature discrimination and recognition accuracy. In this paper, we aim to develop a novel deep learning based LPR system with the ill-conditional data augmentation. Therefore, this paper is expected to the following contributions. First, we apply the WebGL technology to augment the training database for the ill-conditioned outdoor environments. Second, we apply the YOLOv2 DNN architecture to develop deep license plate recognition system in the ill-conditioned environments with recognition accuracy 98%.