This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Robust Classifiers by Mixed Adaptation
June 1991 (vol. 13 no. 6)
pp. 552-567

The production of robust classifiers by combining supervised training with unsupervised training is discussed. A supervised training phase exploits statistically scene invariant labeled data to produce an initial classifier. This is followed by an unsupervised training phase that exploits clustering properties of unlabeled data. This two-phase process is termed mixed adaptation. A probabilistic model supporting this technique is presented along with examples illustrating mixed adaptation. These examples include the detection of unspecified dotted curves in dotted noise and the detection and classification of vehicles in cinematic sequences of infrared imagery.

[1] Y.Z. Tsypkin, "Adaptation and learning in automatic systems," inMathematics in Science and Engineering, vol. 73, New York: Academic, 1971.
[2] D.B. Cooper and P.W. Cooper, "Nonsupervised adaptive signal detection and pattern recognition,"Inform. Contr., vol. 7, no. 3, pp. 416-444, Sept. 1964.
[3] L. Kitchen and A. Rosenfeld, "Scene analysis using region-based constraint filtering,"Pattern Recog., vol. 17, no. 2, pp. 189-203, 1984.
[4] A. Rosenfeld, R.A. Hummel, and S.W. Zucker, "Scene labeling by relaxation operations,"IEEE Trans. Syst., Man, Cybern., vol. SMC-6, no. 6, pp. 420-433, June 1976.
[5] N. Ahuja and M. Tuceryan, "Extraction of early perceptual structure in dot patterns: Integrating region, boundary, and component gestalt,"Comput. Vision, Graphics, Image Processing, vol. 48, pp. 304-356, 1989.
[6] D. Gutfinger, "Mixed adaptation and robust classifiers," Machine Vision and Pattern Recognition Project, Univ. California, Irvine, Tech. Rep. TP-90-7, Aug. 1990.
[7] J. Sklansky and G. N. Wassel,Pattern Classifiers and Trainable Machines. New York: Spring-Verlag, 1981.
[8] R.O. Duda and P.E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[9] L.A. Zadeh, "Probability measures of fuzzy events,"J. Math. Applicat., vol. 10, pp. 421-427, 1968.
[10] A. K. Jain and R. C. Dubes,Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall, 1988.
[11] E.W. Forgy, "Cluster analysis of multivariate data: Efficiency versus interpretability of classifications," inAbstracts in Biometrics 21, No. 3, 768, Biometric Soc. Meetings, Riverside, CA, 1965.
[12] I. Gath and A. B. Geva, "Unsupervised optimal fuzzy clustering,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 7, pp. 773-781, July 1989.
[13] K.S. Narendra and A.M. Annaswamy,Stable Adaptive Systems. Englewood Cliffs, NJ: Prentice Hall, 1989.
[14] E. Backer and A. K. Jain, "A clustering performance measure based on fuzzy set decomposition,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-3, no. 1, pp. 66-75, Jan. 1981.
[15] K. Fukunaga,Introduction to Statistical Pattern Recognition. New York: Academic, 1972.
[16] P. Parent and S.W. Zucker. "Trace inference, curvature consistency, and curve detection,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 8, pp. 823-839, Aug. 1989.
[17] D. Gutfinger, E. Hertzberg, and J. Sklansky, "MRI tissue identification by mixed adaptation," Machine Vision and Pattern Recognition Project, Univ. California, Irvine, Tech. Rep. TP-90-5, May 1990.
[18] G.A. Roberts, L.H. Bradford, and D. Gutfinger, "Prioritization and classification of infrared detections using dynamic belief," inProc. SPIE Aerospace Pattern Recognition, vol. 1098, Orlando, FL, Mar. 1989, pp. 182-189.
[19] E. Taken, D. Friedman, A. Milton, and R. Nitzberg, "Least-mean-squared filter for IR sensors,"Appl. Opt., vol. 18, no. 24, Dec. 1979.
[20] B. Bhanu and O. Faugeras, "Segmentation of images having unimodal distributions,"IEEE Trans. Pattern Anal. Machine Intell., vol. 4, July 1982.

Index Terms:
pattern recognition; vehicle detection; learning systems; relaxation labelling; classifiers; supervised training; unsupervised training; clustering; probabilistic model; dotted curves; learning systems; pattern recognition; probability
Citation:
D. Gutfinger, J. Sklansky, "Robust Classifiers by Mixed Adaptation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 552-567, June 1991, doi:10.1109/34.87342
Usage of this product signifies your acceptance of the Terms of Use.