This Article 
 Bibliographic References 
 Add to: 
Addressing the Problems of Bayesian Network Classification of Video Using High-Dimensional Features
February 2004 (vol. 16 no. 2)
pp. 230-244

Abstract—Bayesian theory is of great interest in pattern classification. In this paper, we present an approach to aid in the effective application of Bayesian networks in tasks like video classification, where descriptors originate from varied sources and are large in number. In order to extend the application of conventional Bayesian theory to the case of continuous and nonparametric descriptor space, dimension partitioning into attributes by minimizing the discrete Bayes error is proposed. The partitioning output goes to the dimensionality reduction module. A new algorithm for dimensionality reduction for improving the classification accuracy is proposed based on the class pair discriminative capacity of the dimensions. It is also shown how attributes can be weighed automatically in a single-label assignment based on comparing the class pairs. A computationally efficient method to assign multiple labels on the samples is also presented. Comparison with standard classification tools on video data of more than 4,000 segments shows the potential of our approach in pattern classification.

[1] D.W. Aha and R.L. Bankert, Feature Selection for Case-Based Classification of Cloud Types: An Empirical Comparison Proc. Am. Association for Artificial Intelligence Conf., pp. 106-112, 1994.
[2] H. Almuallim and T.G. Dietterich, Learning Boolean Concepts in the Presence of Many Irrelevant Features Artificial Intelligence, vol. 69, pp. 279-305, 1994.
[3] P. Antal, Construction of a Classifier with Prior Domain Knowledge Formalized as Bayesian Network Proc. IEEE Conf. Industrial Electronics Soc., pp. 2527-2531, 1998.
[4] Y.A. Aslandogan and C.T. Yu, Techniques and Systems for Image and Video Retrieval IEEE Trans. Knowledge and Data Eng., vol. 11, pp. 56-63, Jan./Feb. 1999.
[5] M.B. Bassat, Use of Distance Measures, Information Measures and Error Bounds in Feature Evaluation Handbook of Statistics, Krishnaiah and Kanal, eds., pp. 773-791, 1982.
[6] P.S. Bradley and O.L. Mangasarian, Feature Selection via Concave Minimization and SVMS Proc. Int'l Conf. Machine Learning, pp. 82-90, 1998.
[7] M. L. Cascia and E. Ardizzone, JACOB: Just a Content-Based Query System for Video Databases Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, pp. 1216-1219, 1996.
[8] E.J. Clarke and B.A. Barton, Entropy and MDL Discretization of Continuous Variables for Bayesian Belief Networks Int'l J. Intelligent Systems, vol. 15, pp. 61-92, 2000.
[9] R. Collobert and S. Bengio, SVMTorch: Support Vector Machines for Large-Scale Regression Problems J. Machine Learning Research, vol. 1, pp. 143-160, 2001.
[10] G.F. Cooper, Probabilistic Inference Using Belief Networks is NP-Hard Technical Report KSL-87-27, Stanford Univ., 1987.
[11] J. Demsar and F. Solina, Using Machine Learning for Content-Based Image Retrieval Proc. Int'l Conf. Pattern Recognition, vol. 3, pp. 138-142, 1996.
[12] P.J. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach. Prentice Hall, 1982.
[13] N.D. Doulamis, A.D. Doulamis, and S.D. Kollias, A Neural Network Approach to Interactive Content-Based Retrieval of Video Databases Proc. Int'l Conf. Image Processing, vol. 2, pp. 116-120, 1999.
[14] P.A. Estevez, M. Fernandez, R.J. Alcock, and M.S. Packianather, Selection of Features for the Classification of Wood Board Defects Proc. Int'l Conf. Artificial Neural Networks, pp. 347-352, 1999.
[15] J. Bach, et al., The Virage Search Engine: An Open Framework for Image Search Engine Proc. SPIE Conf. Storage and Retrieval of Image and Video Databases, pp. 76-87, 1996.
[16] M. Flickner, H. Sawhney, W. Niblack, J. Ashley, Q. Huang, B. Dom, M. Gorkani, J. Hafner, D. Lee, D. Petkovic, D. Steele, and P. Yanker, “Query by Image and Video Content: The QBIC System,” IEEE Computer, 1995.
[17] K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press 1990.
[18] F. Garber and A. Djouadi, Bounds on the Bayes Classification Error Based on Pairwise Risk Functions IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, pp. 281-288, 1988.
[19] S. Haykin, Neural Network: A Comprehensive Foundation, pp. 178-210, Macmililan, 1999.
[20] L. Heutte, J.V. Moreatu, B. Plessis, J.L. Plagnaud, and Y. Lecourtier, Handwritten Numeral Recognition Based on Multiple Feature Extractors Proc. IEEE Int'l Conf. Document Analysis and Recognition, pp. 167-170, 1993.
[21] K. Kanazawa, D. Koller, and S. Russell, Stochastic Simulation Algorithms for Dynamic Probabilistic Networks Uncertainity in Artificial Intelligence, pp. 346-351, 1995.
[22] W. Al-Khatib, Y.F. Day, A. Ghafoor, and P.B. Berra, “Semantic Modeling and Knowledge Representation in Multimedia Databases,” IEEE Trans. Knowledge and Data Eng., vol. 11, no. 1, pp. 64-80, Jan./Feb. 1999.
[23] A.F. Kohn, L.G. Nakano, and M.O. Silva, A Class Discrimability Measure Based on Feature Space Partitioning Pattern Recognition, pp. 873-887, 1996.
[24] S.L. Lauritzen and D.J. Spiegelhalter, Local Computations with Probabilities on Graphical Structures and Their Applications to Expert Systems J. Royal Statistical Soc., pp. 157-224, 1988.
[25] H. Liu and R. Setiono, Dimensionality Reduction via Discretization Knowledge Based Systems, no. 9, pp. 67-72, 1996.
[26] C. Meek and D. Heckerman, Structure and Parameter Learning for Causal Independence and Causal Interaction Model Uncertainity in AI, pp. 366-375, 1997.
[27] A. Mittal and L. -F. Cheong, Achieving Semantic Coupling in the Domain of High-Dimensional Video Indexing Application Proc. SPIE Conf. Applications of Artificial Neural Networks in Image Processing VI, pp. 97-107, 2001.
[28] M. Modrzejewski, Selection Using Rough Sets Theory Proc. European Conf. Machine Learning, pp. 213-226, 1993.
[29] ISO/IEC JTC1/SC29/WG11 Coding of Moving Pictures and Audio, Overview of the MPEG-7 Standard Int'l Organization for Standarisation, Oct. 2000.
[30] M. Pazzani, An Interative Improvement Approach for the Discretization of Numeric Attributes in Bayesian Classifiers Proc. Int'l Conf. Knowledge Discovery and Data Mining, pp. 228-233, 1995.
[31] M. Pazzani, C. Merz, K. Ali, and T. Hume, Reducing Misclassification Costs Proc. Int'l Conf. Machine Learning, 1994.
[32] J. Pearl, Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, 1988.
[33] B. Pfahringer, Compression Based Discretization of Continuous Variables Proc. Int'l Conf. Machine Learning, pp. 456-463, 1995.
[34] J.R. Quinlan, C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.
[35] S. Raudys, How Good are SVMS? Neural Networks, vol. 13, pp. 17-19, 2000.
[36] V.I. Smirnov and A.M. Tikheyeva, The Connection between the Bayesian Risk and the Kolmogorov Distance and a Modification of It in Recognition Problems Eng. Cybernetics, vol. 15, pp. 147-150, 1977.
[37] K. Tumer and J. Ghosh, Estimating the Bayes Error Rate through Classifier Combining Proc. Int'l Conf. Pattern Recognition, pp. 695-699, 1996.
[38] J. Weston, S. Mukherjee, O. Chapelle, M. Pontil, V. Vapnik, and T. Poggio, Feature Selection for SVMs Neural Information Processing Systems, pp. 668-674, 2000.
[39] N. Wyse, R. Dubes, and A.K. Jain, A Critical Evaluation of Intrinsic Dimensionality Reduction Algorithms Pattern Recognition in Practise, pp. 415-425, 1980.
[40] Z. Yang and C.C.J. Kuo, A Semantic Classification and Composite Indexing Approach to Robust Image Retrieval Proc. Int'l Conf. Image Processing, vol. 1, pp. 134-138, 1999.

Index Terms:
Content-based retrieval, discrete bayes error, partitioning, dimensionality reduction, multiple labels assignment, Bayesian networks.
Ankush Mittal, Loong-Fah Cheong, "Addressing the Problems of Bayesian Network Classification of Video Using High-Dimensional Features," IEEE Transactions on Knowledge and Data Engineering, vol. 16, no. 2, pp. 230-244, Feb. 2004, doi:10.1109/TKDE.2004.1269600
Usage of this product signifies your acceptance of the Terms of Use.