Resampling Approach for Anomaly Detection in Multispectral Images

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 5093, Issue , 2003, Pages 230-240

  Theiler, James ^a   Cai, D Michael ^a  

^a LOS ALAMOS NATIONAL LABORATORY   (United States)

Author keywords

Anomaly detection; Machine learning; Multispectral imagery

Indexed keywords

ANOMALY DETECTION; AUTOMATED TARGET RECOGNITION (ATR); MULTISPECTRAL IMAGERY;

COMPUTER PROGRAMMING; EROSION; FILTERS (FOR FLUIDS); FUZZY SETS; LEARNING SYSTEMS; LIGHTING; OPTIMIZATION; TEXTURES; VEGETATION;

IMAGE ANALYSIS;

EID: 1642475063     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.487069     Document Type: Conference Paper

References (19)

1. N. R. Harvey, J. Theiler, S. P. Brumby, S. Perkins, J. J. Szymanski, J. J. Bloch, R. B. Porter, M. Galassi, and A. C. Young, "Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction," IEEE Trans. Geosci. and Remote Sens. 40, pp. 393-404, 2002.
2. The American Heritage Dictionary of the English Language, Fourth Edition, Houghton Mifflin Company, 2000. (www.dictionary.com).
3. d. But this level of formality does not serve our purposes.
4. Actually, it is only necessary that s(x) = h(Q(x)/P(x)) where h is a monotonic function. This looseness in the definition of optimal s(x) suggests a strategy for designing sub-optimal anomaly detectors when - as is the case - both P(x) and Q(x) are not known. One chooses s(x) to measure some quantity, like brightness, or red-ness, or smoothness, that describes a data point x and then calibrates s(x) against normal data. This provides an "anomaly" detector that is sensitive to the desired property. Of course, the problem with this approach is that the very nature of an anomalies makes the identification of their properties formally impossible. Informally, however, there may be times when this approach is useful.
5. Matlab Statistical Toolbox User's Guide, MathWorks, 2001.
6. K. Fukunaga, Introduction to Statistical Pattern Recognition, Morgan Kauffman, San Francisco, 2nd ed., 1990.
7. S. Ben-David and M. Lindenbaum, "Learning distributions by their density levels: A paradigm for learning without a teacher," J. Computer and System Sciences 55, pp. 171-182, 1997.
8. C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Mining and Knowledge Discovery 2, pp. 121-167, 1998.
9. D. Tax and R. Duin, "Data domain description by support vectors," in Proc. ESANN99, M. Verleysen, ed., pp. 251-256, D. Facto Press, (Brussels), 1999.
10. D. Tax and R. Duin, "Uniform object generation for optimizing one-class classifiers," J. Machine Learning Res. 2, pp. 155-173, 2002.
11. D. Tax and P. Juszczak, "Kernel whitening for one-class classification," in Pattern Recognition with Support Vector Machines, S.-W. Lee and A. Verri, eds., vol. 2388 of Lecture Notes in Computer Science, pp. 40-52, Springer Verlag, (Berlin), 2002.
12. B. Schölkopf, R. Williamson, A. Smola, J. Shawe-Taylor, and J. Platt, "Support vector method of novelty detection," in Advances in Neural Information Processing Systems, S. A. Solla, T. K. Leen, and K.-R. Mller, eds., vol. 12, pp. 582-588, MIT Press, 2000.
13. B. Schölkopf, J. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, "Estimating the support of a high-dimensional distribution," Neural Computation 13, pp. 1443-1471, 2001.
14. B. Schölkopf and A. J. Smola, Learning with Kernels : Support Vector Machines, Regularization, Optimization, and Beyond., MIT Press, Cambridge, MA, 2002.
15. T. Hastie, R. Tibshirani, and J. Friedman, Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer-Verlag, New York, 2001.
16. A. Cannon, J. M. Ettinger, D. Hush, and C. Scovel, "Machine learning with data dependent hypothesis classes," J. Machine Learning Res 2, pp. 335-358, 2002.
17. A. Cannon, J. Howse, D. Hush, and C. Scovel, "Simple classifiers," Submitted to: IEEE Trans. Neural Networks, 2003.
18. A. Cannon, J. Howse, D. Hush, and C. Scovel, "Simple classifiers from data dependent hypothesis classes," Submitted to: International Conference on Machine Learning, 2003.
19. C.-C. Chang and C.-J. Lin, "LIBSVM: a library for support vector machines." Software made available by the authors from http://www.csie.ntu.edu.tw/̃cjlin/libsvm/index.html.