This paper presents a vision system that provides a robust identification and localization of 2-D objects in industrial scenes. A symbolic image description based on the polygonal approximation of the object silhouette is extracted in video real time by the use of dedicated hardware. A two-stage matching algorithm is proposed. At the first stage hypotheses for assignments of image to model polygons are generated together with hypotheses for the object's pose. Corresponding continuous measures of similarity are derived from the turning functions of the curves. At the second stage compatible matches of polygons are collected by using a voting scheme in transformation space. Experimental results reveal the fault tolerance of the vision system with regard to noisy and broken image contours, as well as partial occlusion of objects. The robustness and easy adaptability of the vision system make it well suited for a wide variety of applications.