This Article 
 Bibliographic References 
 Add to: 
An Approach to Novelty Detection Applied to the Classification of Image Regions
April 2004 (vol. 16 no. 4)
pp. 396-407

Abstract—In this paper, we present a new framework for novelty detection. The framework evaluates neural networks as adaptive classifiers that are capable of novelty detection and retraining on the basis of newly discovered information. We apply our newly developed model to the application area of object recognition in video. This paper details the tools and methods needed for novelty detection such that data from unknown classes can be reliably rejected without any a priori knowledge of its characteristics. The rejected data is postprocessed to determine which samples can be manually labeled of a new type and used for retraining. In this paper, we compare the proposed framework with other novelty detection methods and discuss the results of adaptive retraining of neural network to recognize further unseen data containing the newly added objects.

[1] S. Albrecht, J. Busch, M. Kloppenburg, F. Metze, and P. Tavan, Generalised Radial Basis Function Networks for Classification and Novelty Detection: Self-Organisation of Optimal Bayesian Decision Neural Networks, vol. 13, pp. 1075-1093, 2000.
[2] J. Bezdek, R. Ehrlich, and W. Full, FCM: The Fuzzy c-Means Clustering Algorithm Computers and Geosciences, vol. 10, no. 2, pp. 191-203, 1984.
[3] M.L. Bushnell and S.W. Director, “VLSI CAD Tool Integration Using the Ulysses Environment,” Proc. ACM/IEEE Design Automation Conf., ACM, New York, 1986, pp. 55-61.
[4] T. Brotherton, T. Johnson, and G. Chadderdon, Classification and Novelty Detection Using Linear Models and a Class Dependent- Elliptical Basis Function Neural Network Proc. Int'l Joint Conf. Neural Networks, May 1998.
[5] C. Campbell and K.P. Bennett, A Linear Programming Approach to Novelty Detection Advances in Neural Information Processing Systems, vol. 14, 2001.
[6] C.K. Chow, "On Optimum Recognition Error and Reject TradeOff," IEEE Trans. Information Theory, vol. 16, no. 1, pp. 41-46, 1970.
[7] P. Crook and G. Hayes, A Robot Implementation of a Biologically Inspired Method for Novelty Detection Proc. Towards Intelligent Mobile Robots Conf., 2001.
[8] D. Dasgupta and F.A. Gonzalez, An Immunogenetic Approach to Intrusion Detection Dept. of Computer Science, Univ. of Memphis, Report No. CS-01-001, May 2001.
[9] M.J. Desforges, P.J. Jacob, and J.E. Cooper, Application of Probability Density Estimation to the Detection of Abnormal Conditions in Engineering Proc. Inst. of Mechanical Eng., vol. 212, pp. 687-703, 1998.
[10] R.O. Duda, R.E. Hart, and D.G. Stork, Pattern Classification, second ed. Wiley, 2001.
[11] S.E. Fahlman and C. Lebiere, The Cascade-Correlation Learning Architecture Advances in Neural Information Processing Systems, D.S. Touretzky, ed., vol. 2, pp. 524-532, 1990.
[12] P. Foggia, C. Sansone, F. Tortorella, and M. Vento, Multiclassification: Reject Criteria for the Bayesian Combiner Pattern Recognition, vol. 32, pp. 1435-1447, 1999.
[13] G. Fumera, F. Roli, and G. Giacinto, Reject Option with Multiple Thresholds Pattern Recognition, vol. 33, pp. 2099-2101, 2000.
[14] L.K. Hansen, C. Liisberg, and P. Salamon, The Error-Reject Tradeoff Open Systems and Information Dynamics, vol. 4, pp. 159-184, 1997.
[15] T. Harris, Neural Network in Machine Health Monitoring Professional Eng., 1993.
[16] J. Huang, S.R. Kumar, M. Mitra, W. Zhu, and R. Zabih, Image Indexing Using Color Correlograms Proc. Computer Vision and Pattern Recognition, pp. 762-768, 1997.
[17] N. Japkowicz, C. Myers, and M. Gluck, A Novelty Detection Approach to Classification Proc. 14th Int'l Joint Conf. Artificial Intelligence, pp. 518-523, 1995.
[18] T. Kwok and D. Yeung, Objective Functions for Training New Hidden Units in Constructive Neural Networks IEEE Trans. Neural Networks, vol. 8 no. 5, pp. 1131-1148, 1999.
[19] J. Lamirel, M. Crehange, and J. Dulcoy, NOMAD: A Documentary Database Interrogation System Using Multiple Neural Topographies and Novelty Detection Advances in Knowledge Organisation, vol. 4, pp. 334-341, 1994.
[20] M.A. Lewis and L.S. Simo, Certain Principles of Biomorphic Robots Autonomous Robots, 2001.
[21] Y. Li, M.J. Pont, and N.B. Jones, Improving the Performance of the Radial Basis Function Classifiers in Condition Monitoring and Fault Diagnosis Applications where‘Unknown’Faults May Occur Pattern Recognition Letters, vol. 23, pp. 569-577, 2002.
[22] S. Marsland, U. Nehmzow, and J. Shapiro, A Model of Habituation Applied to Mobile Robots Proc. Towards Intelligent Mobile Robots Conf., 1999.
[23] S. Marsland, U. Nehmzow, and J. Shapiro, A Real-Time Novelty Detector for a Mobile Robot Proc. European Advanced Robotics Systems Conf., 2000a.
[24] S. Marsland, U. Nehmzow, and J. Shapiro, Novelty Detection for Robot Neotaxis Proc. Second Int'l ICSC Symp. Neural Computation, pp. 554-559, 2000b.
[25] S. Marsland, U. Nehmzow, and J. Shapiro, Detecting Novel Features of an Environment Using Habituation Proc. Simulation of Adaptive Behaviour, 2000c.
[26] S. Marsland, U. Nehmzow, and J. Shapiro, Novelty Detection in Large Environments Proc. Towards Intelligent Mobile Robots Conf., 2001.
[27] F. Mindru, T. Moons, and L. VanGool, Colour-Based Moment Invariants for Viewpoint and Illumination Independent Recognition of Colour Patterns Proc. Int'l Conf. Pattern Recognition (ICPR '98), pp. 113-124, 1998.
[28] A.F. Murray, Novelty Detection Using Products of Simple Experts A Potential Architecture for Embedded Systems Neural Networks, vol. 14, pp. 1257-1264, 2001.
[29] A. Nairac, T. Corbett-Clark, R. Ripley, N. Townsend, and L. Tarassenko, Choosing an Appropriate Model for Novelty Detection Proc. Fifth Int'l Conf. Artificial Neural Networks, pp. 227-232, 1997.
[30] A. Nairac, N. Townsend, R. Carr, S. King, P. Cowley, and L. Tarassenko, A System for the Analysis of Jet Engine Vibration Data Integrated Computer Aided Eng., vol. 6, pp. 53-65, 1999.
[31] J.A. Parikh, A Comparative Study of Cloud Classification Strategies Remote Sensing of the Environment, vol. 6, pp. 67-81, 1977.
[32] L. Parra, G. Deco, and S. Miesbach, Statistical Independence and Novelty Detection with Information Preserving Non-Linear Maps Neural Computation, vol. 8, pp. 260-269, 1995.
[33] N.J. Pizzi, R.A. Vivanco, and R.L. Somorjai, EvIdent: A Functional Magnetic Resonance Image Analysis System Artificial Intelligence in Medicine, vol. 21, pp. 263-269, 2001.
[34] K.N. Plataniotis and A.N. Venetsanopoulos, Color Image Processing and Applications. Springer-Verlag, 2000.
[35] S.J. Roberts and W. Penny, Novelty, Confidence and Errors in Connectionist Systems Proc. IEE Colloquium Intelligent Sensors and Fault Detection, no. 1996/261, 1996.
[36] S.J. Roberts, Novelty Detection Using Extreme Value Statistics IEE Proc. Vision, Image and Signal Processing, vol. 146, issue 3, pp. 124-129, 1999.
[37] R. Ruotolo, C. Surace, and K. Worden, Application of Two Damage Detection Techniques to an Off-Shore Platform Proc. SPIE, vol. 3727, pp. 882-888, 1999.
[38] M. Saptharishi, K. Bhat, C. Diehl, C. Oliver, M. Savvides, A. Soto, J. Dolan, and P. Khosla, Recent Advances in Distributed Collaborative Surveillance SPIE Proc. Unattended Ground Sensor Technologies and Applications (AeroSense 2000), vol. 4040, pp. 199-208, 2000.
[39] R. Saunders and J.S. Gero, The Importance of Being Emergent Proc. AI Design, 2000.
[40] B. Schölkopf, R. Williamson, A. Smola, J.S. Taylor, and J. Platt, Support Vector Method for Novelty Detection Neural Information Processing Systems, S.A. Solla et al., eds., pp. 582-588, 2000.
[41] M. Singh and S. Singh, Minerva Scene Analysis Benchmark Proc. Seventh Australian and New Zealand Intelligent Information Systems Conf., pp. 231-235, 2001.
[42] S. Singh, M. Markou, and J.F. Haddon, Detection of New Image Objects in Video Sequences UsingNeural Networks Proc. SPIE Electronic Imaging '2000, pp. 204-213, 2000.
[43] H. Sohn, K. Worden, and C.R. Farrar, Novelty Detection Using Auto-Associative Neural Network Proc. Symp. Identification of Mechanical Systems: Int'l Mechanical Eng. Congress and Exposition, 2001.
[44] R.J. Streifel, R.J. Maks, and M.A. El-Sharkawi, Detection of Shorted-Turns in the Field of Turbine-Generator Rotors Using Novelty Detectors Development and Field Tests IEEE Trans. Energy Conversation, vol. 11, no. 2, pp. 312-317, 1996.
[45] C. Surace and K. Worden, Some Aspects of Novelty Detection Methods Modern Practices in Stress and Vibration Analysis, pp. 89-94, 1997.
[46] C. Surace and K. Worden, A Novelty Detection Method to Diagnose Damage in Structures: An Application to An Offshore Platform Proc. Eighth Int'l Conf. Off-Shore and Polar Eng., vol. 4, pp. 64-70, 1998.
[47] C. Surace, K. Worden, and G. Tomlinson, A Novelty Detection Approach to Diagnose Damage in a Cracked Beam Proc. SPIE, vol. 3089, pp. 947-953, 1997.
[48] D.M.J. Tax and R.P.W. Duin, Support Vector Domain Description Pattern Recognition Letters, vol. 20, pp. 1191-1199, 1999.
[49] L. Tarassenko, Novelty Detection for the Identification of Masses in Mammograms Proc. Fourth Int'l Conf. Artificial Neural Networks, vol. 4, pp. 442-447, 1995.
[50] L. Tarassenko, A. Nairac, N. Townsend, and P. Cowley, Novelty Detection in Jet Engines Proc. IEE Colloqium Condition Monitoring, Imagery, External Structures and Health, pp. 41-45, 1999.
[51] O. Taylor, J. Tait, and J. MacIntyre, Improved Classification for a Data Fusing Kohonen Self Organising Map Using a Dynamic Thresholding Techniques Proc. 16th Int'l Joint Conf. Artificial Intelligence, vol. 2, pp. 828-832, 1999.
[52] G.C. Vasconcelos, A Bootstrap-Like Rejection Mechanism for Multilayer Perceptron Networks II Simposio Brasileiro de Redes Neurais, pp. 167-172, 1995.
[53] G.C. Vasconcelos, M.C. Fairhurst, and D.L. Bisset, Recognizing Novelty in Classification Tasks Proc. NIPS Conf. Novelty Detection, Adaptive Systems Monitoring, 1994.
[54] J. Vesanto and E. Alhoniemi, Clustering of the Self-Organising Map IEEE Trans. Neural Networks, vol. 11, no. 3, pp. 586-600, 2000.
[55] K. Worden, Structural Fault Detection Using a Novelty Measure J. Sound and Vibration, vol. 201, issue 1, pp. 85-101, 1997.

Index Terms:
Scene analysis, neural networks, adaptive classifiers, novelty detection.
Sameer Singh, Markos Markou, "An Approach to Novelty Detection Applied to the Classification of Image Regions," IEEE Transactions on Knowledge and Data Engineering, vol. 16, no. 4, pp. 396-407, April 2004, doi:10.1109/TKDE.2004.1269665
Usage of this product signifies your acceptance of the Terms of Use.