As a significant feature of vehicle, the color feature plays an important role in the intelligent transportation systems. However, the color feature is easily affected by the variations of the lighting condition. In this paper, we present a new method for vehicle color recognition, which is based on license plate color. The color of license plate is recognized by the prior knowledge and the recognition result of the license plate, which is not sensitive to the variations of lighting condition. We select the vehicle ROI (region of interest) near the license plate, and convert the color space of the plate image and the vehicle ROI image from RGB to HSV. The vehicle color is identified by the relative location of the ROI color and the plate color in the spectrum. We verify the feasibility of our approach through a comparison experiment. Experiment results show that the color of license plate is helpful to recognize the vehicle color.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.