| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Predicting Performance of Object Recognition
September 2000 (vol. 22 no. 9)
pp. 956-969
Abstract—We present a method for predicting fundamental performance of object recognition. We assume that both scene data and model objects are represented by 2D point features and a data/model match is evaluated using a vote-based criterion. The proposed method considers data distortion factors such as uncertainty, occlusion, and clutter, in addition to model similarity. This is unlike previous approaches, which consider only a subset of these factors. Performance is predicted in two stages. In the first stage, the similarity between every pair of model objects is captured by comparing their structures as a function of the relative transformation between them. In the second stage, the similarity information is used along with statistical models of the data-distortion factors to determine an upper bound on the probability of recognition error. This bound is directly used to determine a lower bound on the probability of correct recognition. The validity of the method is experimentally demonstrated using real synthetic aperture radar (SAR) data.
[1] 956 T.D. Alter and W.E.L. Grimson, “Verifying Model-Based Alignments in the Presence of Uncertainty,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 344-349, 1997.[2] T.D. Alter and D.W. Jacobs, “Uncertainty Propagation in Model-Based Recognition,” Int'l J. of Computer Vision, vol. 27, no. 2, pp. 127-159, 1998.[3] A. Amir and M. Lindenbaum, “Grouping-Based Nonadditive Verification,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 186-192, Feb. 1998.[4] B. Bhanu and G. JonesIII, “Recognizing MSTAR Target Variants and Articulations,” Proc. SPIE Conf. Algorithms for Synthetic Aperture Radar Imagery VI, vol. 3,721, pp. 507-519, 1999.[5] M. Boshra and B. Bhanu, “Bounding SAR ATR Performance Based on Model Similarity,” Proc. SPIE Conf. Algorithms for Synthetic Aperture Radar Imagery VI, vol. 3,721, pp. 716-729, 1999.[6] Y. Boykov and D. Huttenlocher, A New Bayesian Framework for Object Recognition Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. II, pp. 517-523, 1999.[7] T.M. Breuel, "Higher-Order Statistics in Visual Object Recognition," Technical Report 93-02, IDIAP, June 1993.[8] M. Dhome, M. Richetin, J.T. Lapreste, and G. Rives, “Determination of the Attitude of 3D Objects from a Single Perspective View,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 12, pp. 1,265-1,278, Dec. 1989.[9] O.D. Faugeras and M. Hebert,“The representation, recognition, and locating of 3D objects,” Int’l J. of Robotics Research, vol. 5, no. 3, pp. 27-52, Fall 1986.[10] W.E.L. Grimson and D.P. Huttenlocher, “On the Verification of Hypothesized Matches in Model-Based Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 12, pp. 1201-1213, 1991.[11] W.E.L. Grimson and T. Lozano-Perez, “Localizing Overlapping Parts by Searching the Interpretation Tree,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, Apr. 1987.[12] D.P. Huttenlocher and S. Ullman, “Recognizing Solid Objects by Alignment with an Image,” Int'l J. Computer Vision, vol. 5, no. 2, pp. 195-212, 1990.[13] G. Jones and B. Bhanu, “Recognition of Articulated and Occluded Objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 7, pp. 603-613, July 1999.[14] W.M. WellsIII, “Statistical Approaches to Feature-Based Object Recognition,” Int'l J. of Computer Vision, vol. 21, no. 1, pp. 63-98, 1997.[15] S.Z. Li, Markov Random Field Modeling in Computer Vision. New York: Springer-Verlag, 1995.[16] M. Lindenbaum, “Bounds on Shape Recognition Performance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 666-680, July 1995.[17] M. Lindenbaum, "An Integrated Model for Evaluating the Amount of Data Required for Reliable Recognition," Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 11, pp. 1,251-1,264, Nov. 1997.[18] J. Mao, P.J. Flynn, and A.K. Jain, “Integration of Multiple Feature Groups and Multiple Views into a 3D Object Recognition System,” Computer Vision and Image Understanding, vol. 62, no. 3, pp. 309-325, 1995.[19] A.R. Pope and D.G. Lowe, “Learning Appearance Models for Object Recognition,” Proc. Int'l Workshop Object Representation for Computer Vision, pp. 201-219, 1996.[20] T. Ross, S. Worrell, V. Velten, J. Mossing, and M. Bryant, “Standard SAR ATR Evaluation Experiments Using the MSTAR Public Release Data Set,” Proc. SPIE Conf. Algorithms for Synthetic Aperture Radar Imagery V, vol. 3,370, pp. 566-573, 1998.[21] K.B. Sarachik, “The Effect of Gaussian Error in Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 289-301, Apr. 1997.[22] G. Stockman, "Object Recognition and Localization via Pose Clustering," Computer Vision, Graphics,&Image Processing, Vol. 40, 1987, pp. 361-387.
Index Terms:
Bounds on recognition performance, model-based real-world object recognition, modeling data distortion, performance validation, synthetic aperture radar images, theory of performance prediction.
Citation:
Michael Boshra, Bir Bhanu, "Predicting Performance of Object Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 9, pp. 956-969, Sept. 2000, doi:10.1109/34.877519
