Novel similarity measures for object recognition and image matching are proposed, which are inherently robust against occlusion, clutter, and nonlinear illumination changes. They can be extended to be robust to global as well as local contrast reversals. The similarity measures are based on representing the model of the object to be found and the image in which the model should be found as a set of points and associated direction vectors. They are used in an object recognition system for industrial inspection that recognizes objects under Euclidean transformations in real time.
展开▼
