Recognition of colorful objects in variant backgrounds and illumination conditions

This paper presents a fuzzy based method for recognizing color objects in a complex background under varying illumination. Fuzzy rules are generated using a fuzzy associative memory training method to cope with chromatic distortion. The color model used is the hue-saturation-value color model. In this paper, the proposed method is applied to stop sign recognition in real-world scenes that may have incorrect video camera focus and/or other color distortions. The results of this research can help the GPSVan/sup TM/ system generate maps automatically.