A SCALE-SPACE FILTERING APPROACH FOR VISUAL FEATURE-EXTRACTION

This paper presents a new integrated approach for detecting visual fea tures which include CORNERs, ENDs, ARCs and LINEs. The effect of scale -space filtering on visual features is studied in detail as it forms t he theoretical basis of our work. In this approach, the outline of the object is first extracted and it is then smoothed by scale-space filt ering at different scale levels. Subsequently, the Local Extreme Curva ture Points extracted from the smoothed curve and END candidates are d etermined to guide the termination of the filtering process. Informati on about the curvature of each point at the largest scale level is use d to detect the different kinds of visual features. Several algorithms are proposed to determine CORNERs, ENDs, ARCs and LINEs. Experimental results show that our approach is robust to translation, rotation and scaling of the object as well as noise corruption. In addition, effic ient visual features can also be successfully extracted with this appr oach.