EXTRACTING SALIENT CONTOURS FOR TARGET RECOGNITION - ALGORITHM AND PERFORMANCE EVALUATION

To achieve robust and efficient object recognition, particularly from real outdoor images, we must develop methods to reduce clutter and ext ract salient information of objects. Toward this end, we present a tec hnique to rank and extract salient contours from a 2-D image acquired by a passive sensor. The goal is to find important contours correspond ing to possible objects. Our method starts with edge pixels, or edgels , from an edge detector and assigns a saliency measure to linked edgel s (contours) based on length, smoothness, and contrast. For length we use the number of edgels in the contour, for smoothness we use average change of curvature, and for contrast we use the edge magnitude. Cont ours are ranked by saliency, and the more salient contours are selecte d. We test this method on several real outdoor images of objects in cl uttered and occluded conditions and obtain excellent results. We evalu ate the performance of this technique in the context of a recognition system that matches 2-D image corners with 3-D model vertices. We pres ent graphs, using corners on the object of interest and clutter, to de monstrate the appropriateness of saliency ranking. We plot curves disp laying the percentage of object corners to all image corners for the t op few salient contours. We conclude by observing that extracting the more salient contours increases the ratio of image corners on the obje ct to all image corners, reducing the search space for the corner matc hing step in recognition.