This Article 
 Bibliographic References 
 Add to: 
Grouping-Based Nonadditive Verification
February 1998 (vol. 20 no. 2)
pp. 186-192

Abstract—Verification is the final decision stage in many object recognition processes. It is carried out by evaluating a score for every hypothesis and choosing the hypotheses associated with the highest score. This paper suggests a grouping-based verification paradigm, relying on the observation that a group of data features belonging to a hypothesized object instance should be a "good group." Therefore, it should support perceptual grouping information available from the image by grouping relations. The proposed score, which is the joint likelihood of these grouping cues, quantifies this observation in a probabilistic framework. Experiments with synthetic and real images show that the proposed method performs better in difficult cases.

[1] A. Amir and M. Lindenbaum, “A Generic Grouping Algorithm and Its Quantitative Analysis,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 168-185, Feb. 1998.
[2] A. Amir and M. Lindenbaum, "Grouping-Based Non-Additive Verification," Technical Report CIS-9518, Technion, Israel, Oct. 1995.
[3] A. Amir and M. Lindenbaum, "Quantitative Analysis of Grouping Processes," ECCV-96, vol. 1, pp. 371-384,Cambridge, 1996.
[4] T.M. Breuel, "Higher-Order Statistics in Visual Object Recognition," Technical Report 93-02, IDIAP, June 1993.
[5] T.M. Cover, Elements of Information Theory.New York: Wiley-Interscience, 1991.
[6] R.O. Duda and P.E. Hart, "Use of the Hough Transform to Detect Lines and Curves in Pictures," Comm. ACM, vol. 15, no. 1, pp. 11-15, 1972.
[7] 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.
[8] W.E.L. Grimson and D.P. Huttenlocher, eds., Special issues on the interpretation of 3D scenes, Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 10, Oct. 1990 and vol. 14, no. 2, Feb. 1991.
[9] D. Huttenlocher and S. Ullman, "Recognizing Solid Objects by Alignment With an Image," IJCV, vol. 5, no. 2, pp. 195-212, 1990.
[10] 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.
[11] M. Lindenbaum, “Bounds on Shape Recognition Performance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 666-680, July 1995.
[12] D.G. Lowe, Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, 1985.
[13] J. Mundy, C. Huang, J. Liu, W. Hoffman, D. Forsyth, C. Rothwell, A. Zisserman, S. Utcke, and O. Bournez, "Object Recognition System Based on Geometric Invariants," IUW-94, pp. 1,393-1,402, 1994.
[14] J.L. Mundy and A. Zisserman, Geometric Invariance in Computer Vision.Cambridge, Mass.: MIT Press, 1992.
[15] A. Papoulis, Probability, Random Variables, and Stochastic Processes.New York: McGraw-Hill, 1991.
[16] C. Rothwell, "Reasoning About Occlusions During Hypothesis Verification," ECCV-96, vol. 1, pp. 599-609,Cambridge, 1996.
[17] K.B. Sarachik and W. Grimson, "Gaussian Error Models for Object Recognition," CVPR, pp. 400-406, 1993.
[18] S. Sarkar and K.L. Boyer, “Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure,” IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382-399, 1993.
[19] A.P. Witkin and J.M. Tenenbaum, "On the Role of Structure in Vision," J. Beck, B. Hope, and A. Rosenfeld, eds., Human and Machine Vision, pp. 481-543.New York: Academic Press, 1983.
[20] H. Wolfson, "Model-Based Object Recognition by Geometric Hashing," ECCV-90, pp.526-536, 1990.

Index Terms:
Hypothesis verification, object recognition, perceptual grouping, maximum likelihood, graph clustering, Kullback Leibler distance.
Arnon Amir, Michael Lindenbaum, "Grouping-Based Nonadditive Verification," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 186-192, Feb. 1998, doi:10.1109/34.659936
Usage of this product signifies your acceptance of the Terms of Use.