Recognition of blurred license plate images

In video forensics, to recognize objects in low-resolution frames is a commonly seen problem. In this paper, we propose a systematic way to recognize blurred license plate images. Our method only uses one license plate image and character segmentation is not necessary. The process involves three steps. First, using single-character templates, we identify the positions of characters on a license plate and estimate the corresponding character list. Then, the position of a special symbol on the license plate is estimated. Finally, to refine the recognition results, we expand the single-character templates to multiple-character templates. The experiment results demonstrate the efficacy of our method in recognizing characters in blurred license plate images.