This Article 
 Bibliographic References 
 Add to: 
A Neural Network-Based Novelty Detector for Image Sequence Analysis
October 2006 (vol. 28 no. 10)
pp. 1664-1677
This paper proposes a new model of "novelty detection” for image sequence analysis using neural networks. This model uses the concept of artificially generated negative data to form closed decision boundaries using a multilayer perceptron. The neural network output is novelty filtered by thresholding the output of multiple networks (one per known class) to which the sample is input and clustered for determining which clusters represent novel classes. After labeling these novel clusters, new networks are trained on this data. We perform experiments with video-based image sequence data containing a number of novel classes. The performance of the novelty filter is evaluated using two performance metrics and we compare our proposed model on the basis of these with five baseline novelty detectors. We also discuss the results of retraining each model after novelty detection. On the basis of Chi-square performance metric, we prove at 5 percent significance level that our optimized novelty detector performs at the same level as an ideal novelty detector that does not make any mistakes.

[1] J. Bezdek, R. Ehrlich, and W. Full, “FCM: The Fuzzy C-Means Clustering Algorithm,” Computer Geographic Science, vol. 10, no. 2, pp. 191-203, 1984.
[2] C. Bishop, “Novelty Detection and Neural Network Validation,” Proc. IEE Conf. Vision and Image Signal Processing, pp. 217-222, 1994.
[3] C. Bishop, Neural Networks for Pattern Recognition. Oxford Univ. Press, 1995.
[4] H. Byungho and C. Sungzoon, “Characteristics of Auto-Associative MLP as a Novelty Detector,” Proc. IEEE Int'l Joint Conf. Neural Networks, vol. 5, pp. 3086-3091, 1999.
[5] D. Dasgupta and S. Forrest, “Novelty-Detection in Time Series Data Using Ideas from Immunology,” Proc. Int'l Conf. Intelligent Systems, 1996.
[6] D. Dasgupta and F. Nino, “A Comparison of Negative and Positive Selection Algorithms in Novel Pattern Detection,” Proc. IEEE Conf. Systems, Man, and Cybernetics, vol. 1, pp. 125-130, 2000.
[7] D.L. Davies and D.W. Bouldin, “A Cluster Separation Measure,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 1, no. 2, pp. 224-227, 1979.
[8] I. Diaz and J. Hollmen, “Residual Generation and Visualization for Understanding Novel Process Conditions,” Proc. IEEE Int'l Joint Conf. Neural Networks, pp. 2070-2075, 2002.
[9] R.O. Duda, R.E. Hart, and D.G. Stork, Pattern Classification, second ed. Wiley, 2001.
[10] J.C. Dunn, “A Fuzzy Relative of The ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters,” J. Cybernetics, vol. 3, pp. 32-57, 1973.
[11] S.E. Fahlman and C. Lebiere, “The Cascade-Correlation Learning Architecture,” Advances in Neural Information Processing Systems, D.S. Touretzk, ed., vol. 2, pp. 524-532, 1990.
[12] M.M. Fleck, D.A. Forsyth, and C. Bregler, “Finding Naked People,” Proc. European Conf. Computer Vision, 592-602, 1996.
[13] A. Ford and A. Roberts, “Color Space Conversions,” technical report, Westminster Univ., 1998.
[14] R.S. Guh, F Zorriassatine, and J.D.T. Tannock, “On-Line Control Chart Pattern Detection and Discrimination— A Neural Network Approach,” AI in Eng., vol. 13, pp. 413-425, 1999.
[15] J. Huang, S. Kumar, M. Mitra, W.J. Zhu, and R. Zabih, “Image Indexing Using Color Correlogram,” Proc. IEEE Computer Visions and Pattern Recognition Conf., pp. 762-768, 1997.
[16] A. Jain and A. Zongker, “Feature Selection: Evaluation, Application, and Small Sample Performance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, pp. 153-158, 1997.
[17] S.P. King, D.M. King, P. Anuzis, K. Astley, L. Tarassenko, P. Hayton, and S. Utete, “The Use of Novelty Detection Techniques for Monitoring High-Integrity Plant,” Proc. Int'l Conf. Control Applications, vol. 1, pp. 221-226, 2002.
[18] H. Ko and G. Jacyna, “Dynamical Behavior of Autoassociative Memory Performing Novelty Filtering,” IEEE Trans. Neural Networks, vol. 11, pp. 1152-1161, 2000.
[19] T. Kohonen, Self-Organisation and Associative Memory. Springer-Verlag, 1988.
[20] T. Kohonen, Self-Organising Maps. Springer, 2001.
[21] T. Kwok and D. Yeung, “Objective Functions for Training New Hidden Units in Constructive Neural Networks,” IEEE Trans. Neural Networks, vol. 8, pp. 1131-1148, 1999.
[22] K.L. Laws, “Texture Image Segmentation,” Technical Report 940, Univ. of Southern California, 1980.
[23] Y. LeCun et al., ”Handwritten Digit Recognition with a Back-Propagation Network,” Advances in Neural Information Processing Systems, vol. 2, pp. 396-404, 1990.
[24] S.P. Lloyd, “Least Squares Quantization in PCM,” IEEE Trans. Information Theory, vol. 28, pp. 129-137, 1982.
[25] Y. Linde, A. Buzo, and R.M. Gray, “An Algorithm for Vector Quantizer Design,” IEEE Trans. Comm., vol. 28, no. 1, pp. 84-95, 1980.
[26] C. Manikopoulos and S. Papavassiliou, “Network Intrusion and Fault Detection: A Statistical Anomaly Approach,” IEEE Comm. Magazine, vol. 40, pp. 76-82, 2002.
[27] M. Markou and S. Singh, “Novelty Detection: A Review, Part I: Statistical Approaches,” Signal Processing, vol. 83, pp. 2481-2497, 2003.
[28] M. Markou and S. Singh, “Novelty Detection: A Review, Part II: Neural Network Based Approaches,” Signal Processing, vol. 83, pp. 2499-2521, 2003.
[29] M. Markou, “Models of Novelty Detection Based On Machine Learning,” PhD thesis, Dept. of Computer Science, Univ. of Exeter, U.K., 2005.
[30] F. Mindru, T. Moons, and L.J. VanGool, “Recognizing Color Patterns Irrespective of Viewpoint and Illumination,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 368-373, 1999.
[31] I.T. Nabney, Netlab: Algorithms for Pattern Recognition. Springer-Verlag, 2002.
[32] T. Odin and D. Addison, “Novelty Detection Using Neural Network Technology,” Proc. Condition Monitoring and Diagnostic Eng. Management Congress (COMADEN), 2000.
[33] K.N. Plataniotis and A.N. Venetsanopoulos, Color Image Processing and Applications. Springer, 2000.
[34] P. Pudil, J. Novovikova, and J. Kittler, “Floating Search Methods in Feature Selection,” Pattern Recognition Letters, vol. 15, pp. 1119-1125, 1994.
[35] J. Ryan, M.J. Lin, and R. Miikkulainen, “Intrusion Detection with Neural Networks,” Advances in Neural Information Processing Systems 10, pp. 943-949, 1998.
[36] B. Schölkopf and A. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimzation and Beyond. MIT Press, 2002.
[37] S. Singh, M. Singh, and M. Markou, “A Comparison of Feature Extraction Methods for Scene Analysis,” Proc. Workshop Artificial Neural Networks in Pattern Recognition, pp. 108-113, 2003.
[38] S. Singh and M. Markou, “An Approach to Novelty Detection Applied to the Classification of Image Regions,” IEEE Trans. Knowledge and Data Eng., vol. 16, no. 4, pp. 396-407, Apr. 2004.
[39] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision. PWS, 1999.
[40] L. Tarassenko, “Novelty Detection for The Identification of Masses in Mammograms,” Proc. Fourth IEE Int'l Conf. Artificial Neural Networks, pp. 442-447, 1995.
[41] L. Tarassenko, A. Nairac, N. Townsend, and P. Cowley, “Novelty Detection in Jet Engines,” Proc. IEE Colloquium on Condition Monitoring, Imagery, External Structure, pp. 41-45, 1999.
[42] D.M.J. Tax and R.P.W. Duin, “Outlier Detection Using Classifier Instability,” Proc. Joint IAPR Int'l Workshop Advances in Pattern Recognition, pp. 593-601, 1998.
[43] J-C. Terrillon, A. Pilpre, Y. Niwa, and K. Yamamoto, “Robust Face Detection and Japanese Sign Language Hand Posture Recognition for Human-Computer Interaction in An `Intelligent' Room,” Proc. 15th Int'l Conf. Vision Interface, pp. 369-376, 2002.
[44] B.B. Thompson, R.J. MarksII, J.J. Choi, M.A. El-Sharkawi, M. Huang, and C. Bunje, “Implicit Learning in Auto-Encoder Novelty Assessment,” Proc. Int'l Joint Conf. Neural Networks, pp. 2878-2883, 2002.
[45] S.E. Umbaugh, Computer Vision and Image Processing: A Practical Approach Using CVIPtools. Prentice Hall, 1998.
[46] M. Unser, “Local Linear Transforms for Texture Measurements,” Signal Processing, vol. 11, pp. 61-79, 1986.
[47] G.C. Vasconcelos, M.C. Fairhurst, and D.L. Bisset, “Recognizing Novelty in Classification Tasks,” Proc. NIPS Workshop Novelty Detection and Adaptive Systems Monitoring, 1994.
[48] J. Vesanto and E. Alhoniemi, “Clustering of the Self-Organising Map,” IEEE Trans. Networks, vol. 11, no. 3, pp. 586-600, 2000.

Index Terms:
Novelty detection, neural networks, video analysis, object classification, feature extraction and selection.
Markos Markou, Sameer Singh, "A Neural Network-Based Novelty Detector for Image Sequence Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 10, pp. 1664-1677, Oct. 2006, doi:10.1109/TPAMI.2006.196
Usage of this product signifies your acceptance of the Terms of Use.