Abstract
Image processing applications can provide a safer and less exhausting driving experience for drivers. In this paper, a real time traffic sign identification based on color thresholding, regional color density and recognition via principle component analysis algorithm is implemented. Also problems which may cause traffic signs not to be recognized are studied and necessary improvements are made
Highlights
Traffic accidents may cause serious injuries, financial damage and death
True and false traffic sign recognition rates are calculated in regard to detected traffic sign number
In this study we implemented a real time traffic sign identification based on HSV color thresholding, regional color density and Eigenface algorithm
Summary
Traffic accidents may cause serious injuries, financial damage and death. Preventive laws and public service ads are in use in recent years they're not enough to prevent accidents by their own. There are three prevalent approaches in traffic sign recognition: color based, shape based and learning based [2]. Kuo and Lin used thresholding in HSI (Hue Saturation Intensity) color space to detect red pixels [4]. Paclik et al and Fang et al used thresholding in HSV (Hue Saturation Value) and similarity measurement in HSI to detect any color respectively [5,6]. Despite being the simplest method, solely color based approach can result in unreliable outcomes because colors tend to be different
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.