A License Plate Recognition System Based on HSV Space in Natural Lighting
In recent years, with the development of modern traffic demand, the automobile license plate recognition technology has obtained more and more attentions. In this paper, the license plate in the vehicle image is located by extracting the color feature in HSV color space. And after binarizing the license plate image, the vertical scanning procedure is used to segment the license plate characters, and the template matching procedure are used to recognize the characters according to the similar degrees. Experimental results show that the system designed in this paper can effectively recognize the license plate in natural lighting, with the accuracy up to 95% for the Chinese characters, 90.4% for the numbers, 84.4% for the letters, and the time consumption being second level.
Z. B. Zhang et al., "A License Plate Recognition System Based on HSV Space in Natural Lighting", Advanced Materials Research, Vol. 590, pp. 421-426, 2012