On the verification of hypothesized matches in model-based recognition
Model-based recognition methods often use ad hoc techniques to decide if a match of data to a model is correct. Generally an empirically determined threshold is placed on the fraction of model features that must be matched. We instead rigorously derive conditions under which to accept a match. We obtain an expression relating the probability of a match occurring at random to the fraction of model features accounted for by the match, as a function of the number of model features, the number of image features, and a bound on the degree of sensor noise.
Our analysis implies that a proper matching threshold must vary with the number of model and data features, and thus should be set as a function of a particular matching problem rather than using a predetermined value. We analyze some existing recognition systems and find that our method predicts thresholds similar those determined empirically, supporting the technique's validity.
Unable to display preview. Download preview PDF.
- Ayache, N. & O.D. Faugeras, 1986, “HYPER: A new approach for the recognition and positioning of two-dimensional objects,” IEEE Trans. PAMI 8(1), pp. 44–54.Google Scholar
- Besl, P.J. & R.C. Jain, 1985, “Three-dimensional object recognition,” ACM Computing Surveys 17(1), pp. 75–154.Google Scholar
- Chin, R.T. & C.R. Dyer, 1986, “Model-based recognition in robot vision,” ACM Computing Surveys 18(1), pp. 67–108.Google Scholar
- Clemens, D.T., 1986, The recognition of two-dimensional modeled objects-in images, M. Sc. Thesis, Massachusetts Institute of Technology, Electrical Engineering and Computer Science.Google Scholar
- Ettinger, G.J., 1988, “Large Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-parts,” IEEE Conf. on Comp. Vis. & Pattern Recog., pp. 32–41.Google Scholar
- Faugeras, O.D. & M. Hebert, 1986, “The representation, recognition and locating of 3-D objects,” Int. J. Robotics Research 5(3), pp. 27–52.Google Scholar
- Feller, W., 1968, An Introduction to Probability Theory and Its Applications, New York, Wiley.Google Scholar
- Fischler, M.A. & R.C. Bolles, 1981, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Commun. ACM 24, pp. 381–395.Google Scholar
- Grimson, W.E.L., 1989, “On the Recognition of Parameterized 2D Objects,” International Journal of Computer Vision 2(4), pp. 353–372.Google Scholar
- Grimson, W.E.L., 1989, “The Combinatorics of Object Recognition in Cluttered Environments Using Constrained Search,” Artificial Intelligence, to appear.Google Scholar
- Grimson, W.E.L. & D.P. Huttenlocher, 1990, “On the Sensitivity of the Hough Transform for Object Recognition,” IEEE Trans. PAMI, to appear.Google Scholar
- Grimson, W.E.L. & D.P. Huttenlocher, 1989, On the Verification of Hypothesized Matches in Model-Based Recognition, MIT AI Lab Memo 1110.Google Scholar
- Grimson, W.E.L. & T. Lozano-Pérez, 1987, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. PAMI 9(4), pp. 469–482.Google Scholar
- Huttenlocher, D.P. & S. Ullman, 1990, “Recognizing solid objects by alignment with an image,” Intl. J. of Computer Vision, to appear.Google Scholar
- Ikeuchi, K., 1987, “Generating an interpretation tree from a CAD model for 3d-object recognition in bin-picking tasks,” International Journal of Computer Vision 1(2), pp. 145–165.Google Scholar
- Murray, D.W. & D.B. Cook, 1988, “Using the orientation of fragmentary 3D edge segments for polyhedral object recognition,” Intern. Journ. Computer Vision 2(2), pp. 153–169.Google Scholar
- Stockman, G., 1987, “Object recognition and localization via pose clustering,” Comp. Vision, Graphics, Image Proc. 40, pp. 361–387.Google Scholar
- Thompson, D.W. & J.L. Mundy, 1987, “Three-dimensional model matching from an unconstrained viewpoint,” Proc. Intern. Conf. Robotics & Automation, Raleigh, NC, pp. 208–220.Google Scholar