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.