This Article 
 Bibliographic References 
 Add to: 
Hierarchical Discriminant Analysis for Image Retrieval
May 1999 (vol. 21 no. 5)
pp. 386-401

Abstract—A self-organizing framework for object recognition is described. We describe a hierarchical database structure for image retrieval. The Self-Organizing Hierarchical Optimal Subspace Learning and Inference Framework (SHOSLIF) system uses the theories of optimal linear projection for automatic optimal feature derivation and a hierarchical structure to achieve a logarithmic retrieval complexity. A Space-Tessellation Tree is automatically generated using the Most Expressive Features (MEFs) and the Most Discriminating Features (MDFs) at each level of the tree. The major characteristics of the proposed hierarchical discriminant analysis include: 1) avoiding the limitation of global linear features (hyperplanes as separators) by deriving a recursively better-fitted set of features for each of the recursively subdivided sets of training samples; 2) generating a smaller tree whose cell boundaries separate the samples along the class boundaries better than the principal component analysis, thereby giving a better generalization capability (i.e., better recognition rate in a disjoint test); 3) accelerating the retrieval using a tree structure for data pruning, utilizing a different set of discriminant features at each level of the tree. We allow for perturbations in the size and position of objects in the images through learning. We demonstrate the technique on a large image database of widely varying real-world objects taken in natural settings, and show the applicability of the approach for variability in position, size, and 3D orientation. This paper concentrates on the hierarchical partitioning of the feature spaces.

[1] K. Ikeuche and T. Kanade, "Automatic Generation of Object Recognition Programs," Proc. IEEE, vol. 76, no. 8, pp. 1,016-1,035, 1988.
[2] W.E.L. Grimson, Object Recognition by Computer. MIT Press, 1990.
[3] D.P. Huttenlocher and S. Ullman, "Object Recognition Using Alignment," Proc. Int'l Conf. Computer Vision, pp. 102-111,London, England, 1987.
[4] D.J. Kriegman and J. Ponce, "On Recognizing and Positioning Curve 3-D Objects From Image Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 1,127-1,137, Dec. 1990.
[5] F. Stein and G. Medioni, "Efficient Two-Dimensional Object Recognition," Proc. Int'l Conf. Pattern Recognition, IEEE Computer Society, 1990, pp. 596-600.
[6] J. Weng, N. Ahuja, and T.S. Huang, "Learning Recognition and Segmentation of 3D Objects from 2D Images," Proc. 1993 IEEE Int'l Conf. Computer Vision (ICCV '93), pp. 121-128, 1993.
[7] M. Turk and A. Pentland, "Eigenfaces for Recognition," J. Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[8] T. Kohonen, "Self-Organized Formation of Topologically Correct Feature Maps," Biological Cybernetics, vol. 43, pp. 59-69, 1982.
[9] T. Kohonen, "Self-Organized Network," Proc. IEEE, vol. 43, pp. 59-69, 1990.
[10] T. Poggio and F. Girosi, Networks for Approximation and Learning Proc. IEEE, vol. 78, pp. 1481-1497, 1990.
[11] E.B. Baum, "When Are k-Nearest Neighbor and Back Propagation Accurate for Feasible Sized Sets of Examples?" Proc. EURASP Workshop Neural Networks, L.B. Almeida and C.J. Wellekens, eds., Delft Univ. of Tech nology, pp. 2-25, 1990.
[12] J. Rubner and K. Schulten, "Development of Feature Detectors by Self-Organization," Biological Cybernetics., vol. 62, pp. 193-199, 1990.
[13] A. Pentland, B. Moghaddam, and Starner, "View-Based and Modular Eigenspaces for Face Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1994, pp. 84-91.
[14] C. Bregler and S.M. Omohundro, “Nonlinear Manifold Learning for Visual Speech Recognition,” Proc. Int'l Conf. Computer Vision, pp. 494-499, 1995.
[15] L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone, Classification and Regression Trees. Chapman&Hall, 1993.
[16] R. Duda, P. Hart, and D. Stork, Pattern Classification. New York: John Wiley&Sons, 2001.
[17] A.K. Jain and R.C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, N.J.: Prentice Hall, 1988.
[18] J.R. Quinlan,"Induction of decision trees," Machine Learning, vol. 1, pp. 81-106, 1986.
[19] B.D. Ripley, Pattern Recognition and Neural Networks. Cambridge Univ. Press, 1995.
[20] D.J. Hand, Discrimination and Classification.Chichester: John Wiley&Sons, 1981.
[21] S.S. Wilks, Math.l Statistics.New York: John Wiley&Sons, 1963.
[22] K. Fukunaga, Introduction to Statistical Pattern Recognition, second edition. Academic Press, 1990.
[23] G.R. Dattatreya and L.N. Kanal, "Decision Tress in Pattern Recognition," Progress in Pattern Recognition, L. Kanal and A. Rosenfeld, eds., pp. 189-239,New York: Elsevier Science, 1985.
[24] S.R. Safavian and D. Landgrebe, "A Survey of Decision Tree Classifier Methodology," IEEE Trans. Systems, Man, and Cybernetics, vol. 21, no. 3, pp. 660-674, 1991.
[25] S.K. Murthy, “Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey,” Data Mining and Knowledge Discovery, pp. 345-389, 1998.
[26] L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees.New York: Chapman&Hall, 1993.
[27] E.G. Henrichon, jr. and K.S. Fu, "A Nonparametric Multivariate Partitioning Procedure for Pattern Classification," IEEE Trans. Computers, vol. 18, pp. 614-624, July 1969.
[28] J.H. Friedman, "A Recursive Partition Decision Rule for Nonparametric Classification," IEEE Trans. Computers, vol. 26, pp. 404-408, Apr. 1977.
[29] H. Murase and S.K. Nayar, "Illumination Planning for Object Recognition in Structured Environments," Proc. IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, pp. 31-38,Seattle, Washington, June 1994.
[30] D.L. Swets, B. Punch, and J.J. Weng, "Genetic Algorithms for Object Recognition in a Complex Scene," Proc., Int'l Conf. Image Processing, pp. 595-598,Washington, D.C., Oct. 1995.
[31] D.L. Swets and J. Weng, Using Discriminant Eigenfeatures for Image Retrieval IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 8, pp. 831-836, Aug. 1996.
[32] D.L. Swets and J.J. Weng, "Efficient Content-Based Image Retrieval Using Automatic Feature Selection," Proc., Int'l Symp. Computer Vision, pp. 85-90,Coral Gables, Fla., Nov. 1995.
[33] M. Kirby and L. Sirovich,“Application of Karhunen-Loève procedure for the characterization of human faces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, Jan. 1990.
[34] I.T. Jolliffe, Principal Component Analysis.New York: Springer-Verlag, 1986.
[35] M.M. Loève, Probability Theory.Princeton, N.J.: Van Nostrand, 1955.
[36] T. Hastie and R. Tibshirani, “Discriminant Adaptive Nearest Neighbor Classification,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 607-615, June 1996.
[37] R.A. Fisher, "The Statistical Utilization of Multiple Measurements," Annals of Eugenics, vol. 8, pp. 376-386, 1938.
[38] D.L. Swets and J.J. Weng, "SHOSLIF-O: SHOSLIF for Object Recognition and Image Retrieval (phase II)," Technical Report CPS 95-39, Dept. of Computer Science, Michigan State Univ., East Lansing, Mich., Oct. 1995.
[39] A. Pentland, R.W. Picard, and S. Scarloff, "Photobook: Tools for Content-Based Manipulation of Image Databases," SPIE Storage and Retrieval Image and Video Databases II, no. 2,185, San Jose, Feb. 1994.
[40] B. Moghaddam and A. Pentland, "Maximum Likelihood Detection of Faces and Hands," Int'l Workshop Automatic Face- and Gesture-Recognition, M. Bichsel, ed., pp. 122-128, 1995.
[41] J. Weng and S. Chen, "Incremental Learning for Vision-Based Navigation," Proc. Int'l Conf. Pattern Recognition, vol. IV, pp. 45-49,Vienna, Austria, Aug. 1996.
[42] E.E. Smith, "Categorization," Thinking, D.N. Osherson and E.E. Smith, eds., pp. 33-53, MIT Press, 1990.
[43] E. Rosch, C. Mervis, D. Gray, D. Johnson, and P. Boyes-Braehm, "Basic Objects in Natural Categories," Cognitive Psychology, vol. 3, pp. 382-439, 1976.
[44] D. L. Swets, Y. Pathak, and J. J. Weng, "An Image Database System for with Support for Traditional Alphanumeric Queries and Content-Based Queries by Example," Multimedia Tools and Applications, vol. 7, no. 3, 1998.

Index Terms:
Principal component analysis, discriminant analysis, hierarchical image database, image retrieval, tessellation, partitioning, object recognition, face recognition, complexity with large image databases.
Daniel L. Swets, Juyang Weng, "Hierarchical Discriminant Analysis for Image Retrieval," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 5, pp. 386-401, May 1999, doi:10.1109/34.765652
Usage of this product signifies your acceptance of the Terms of Use.