This paper presents a robust and efficient method for license plate detection with the purpose of accurately localizing vehicle license plates from complex scenes in real time. A simple yet effective image downscaling method is first proposed to substantially accelerate license plate localization without sacrificing detection performance compared with that achieved using the original image. Furthermore, a novel line density filter approach is proposed to extract candidate regions, thereby significantly reducing the area to be analyzed for license plate localization. Moreover, a cascaded license plate classifier based on linear support vector machines using color saliency features is introduced to identify the true license plate from among the candidate regions. For performance evaluation, a data set consisting of 3977 images captured from diverse scenes under different conditions is also presented. Extensive experiments on the widely used Caltech license plate data set and our newly introduced data set demonstrate that the proposed approach substantially outperforms state-of-the-art methods in terms of both detection accuracy and run-time efficiency, increasing the detection ratio from 91.09% to 96.62% while decreasing the run time from 672 to 42 ms for processing an image with a resolution of 1082×728 . The executable code and our collected data set are publicly available.
Color Histogram based on HSV and Color Moments are widely used in image retrieval. In this paper, we focus on the research about the image retrieval and propose a new color feature, called Cascade Color Moments. By dividing the image into blocks, we add spatial information of the image into the color features. Cascade Color Moments feature is formed by cascading the color Moments of each block. The experimental results show that Cascade Color Moments is better than HSV Color Histogram and Color Moments when taking the retrieval precision into consideration. Meanwhile, a preprocessing procedure of the clothing image is proposed which mainly includes histogram equalization, foreground extraction and finally normalizing the size of the clothing area of the image into 64*128. And the preprocessing can greatly remove effect of the background, illumination and size of the image.
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.