Skip to main content

Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models

Publication ,  Journal Article
Krishnapuram, B; Carin, L
Published in: Proceedings of the Joint Conference on Information Sciences
December 1, 2002

In conjunction with physics-based feature extraction, Hidden Markov Model (HMM) classifiers have been used successfully to fuse scattering data from multiple target orientations where the target-sensor orientation is generally unknown or "hidden". The use of prior knowledge concerning sensor motion is employed in modeling the sequential data, improving classification performance. However, the assumptions of first order Markovian state transitions state-dependent statistics constrain the intrinsic class of pdf structures admitted by the HMM, for use in classification. In this paper we overcome the above limitation by using the local variations in the HMMs induced by each sequence of observations as the feature vector for a support vector machine (SVM) classifier. Improved discrimination results are presented for measured acoustic scattering data.

Duke Scholars

Published In

Proceedings of the Joint Conference on Information Sciences

Publication Date

December 1, 2002

Volume

6

Start / End Page

354 / 357
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Krishnapuram, B., & Carin, L. (2002). Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models. Proceedings of the Joint Conference on Information Sciences, 6, 354–357.
Krishnapuram, B., and L. Carin. “Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models.” Proceedings of the Joint Conference on Information Sciences 6 (December 1, 2002): 354–57.
Krishnapuram B, Carin L. Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models. Proceedings of the Joint Conference on Information Sciences. 2002 Dec 1;6:354–7.
Krishnapuram, B., and L. Carin. “Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models.” Proceedings of the Joint Conference on Information Sciences, vol. 6, Dec. 2002, pp. 354–57.
Krishnapuram B, Carin L. Support vector machines for improved multiaspect target recognition using the fisher kernel scores of hidden Markov models. Proceedings of the Joint Conference on Information Sciences. 2002 Dec 1;6:354–357.

Published In

Proceedings of the Joint Conference on Information Sciences

Publication Date

December 1, 2002

Volume

6

Start / End Page

354 / 357