Optimisation of Gaussian mixture model for satellite image classification
Optimisation of Gaussian mixture model for satellite image classification
- Author(s): X. Zhou and X. Wang
- DOI: 10.1049/ip-vis:20045126
For access to this article, please select a purchase option:
Buy article PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): X. Zhou 1 and X. Wang 2
-
-
View affiliations
-
Affiliations:
1: Department of Electrical Engineering, Texas A&M University, College Station, USA
2: Department of Electrical Engineering, Columbia University, New York, USA
-
Affiliations:
1: Department of Electrical Engineering, Texas A&M University, College Station, USA
- Source:
Volume 153, Issue 3,
June 2006,
p.
349 – 356
DOI: 10.1049/ip-vis:20045126 , Print ISSN 1350-245X, Online ISSN 1359-7108
A new methodology for classifying multidimensional satellite remote-sensing data is proposed. This technique is based on the Gaussian mixture modelling of the feature vectors extracted from the satellite image and the Bayesian approach to pattern recognition. The key contribution is the optimisation of the Gaussian mixture model for each class based on the training data. An array of techniques are employed for this purpose, including attribute learning vector quantisation, minimum description length model selection, semi-tied covariance matrices, minimum-classification-error learning, fusion of classifiers and the genetic algorithm. Contextual analysis is also developed for recognition. Experimental results on thematic mapper satellite image data demonstrate that the proposed technique outperforms various existing methods for pattern learning and classification.
Inspec keywords: Bayes methods; covariance matrices; geophysical signal processing; genetic algorithms; learning (artificial intelligence); remote sensing; image classification; multidimensional signal processing
Other keywords:
Subjects: Knowledge engineering techniques; Other topics in statistics; Computer vision and image processing techniques; Other topics in statistics; Algebra, set theory, and graph theory; Algebra; Algebra; Optimisation techniques; Probability theory, stochastic processes, and statistics; Geography and cartography computing; Geophysical techniques and equipment; Optimisation techniques; Data and information; acquisition, processing, storage and dissemination in geophysics; Optical, image and video signal processing
References
-
-
1)
- Lanterman, A., Achwarz, A., Wallace, L., Rissanen, L.: `Intertwining themes in the theories of model order estimation', Research Report, 1991.
-
2)
- T. Kohonen . The self-organizing map. Proc. IEEE , 9 , 1464 - 1480
-
3)
- R. Haralick , K. Shanmugam , I. Dinstein . Textural features for image classification. IEEE Trans. Syst. Man Cybern. , 610 - 621
-
4)
- A.J. Smola , B. Scholkopf , K. Müller . The connection between regularization operators and support vector kernels. Neural Netw. , 637 - 649
-
5)
- M.J. Gales . Semi-tied covariance matrixes for hidden Markov models. IEEE Trans. Speech Audio Process. , 3 , 272 - 281
-
6)
- M.F. Augustteijin , L.E. Clemens , K.A. Shaw . Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier. IEEE Trans. Geosci. Remote Sens. , 2 , 1044 - 1063
-
7)
- G.G. Wilkinson . Results and implications of a study of fifteen years of satellite image classification experiments. IEEE Trans. Geosci. Remote Sens. , 3 , 433 - 440
-
8)
- G.J. McLachlan , T. Krishnan . (1997) The EM algorithm and extensions.
-
9)
- J.S. Weszka , C.R. Dyer , A. Rosenfeld . A comparative study of texture measures of terrain classification. IEEE Trans. Syst. Man Cybern. , 269 - 285
-
10)
- A. Lobo . Image segmentation and discriminant analysis for the identification of land cover units in ecology. IEEE Trans. Geosci. Remote Sens. , 5 , 1136 - 1145
-
11)
- R.T. Frankot , A. Chellappa . Lognormal random-field models and their applications to radar image synthesis. IEEE Trans. Geosci. Remote Sens. , 2 , 195 - 207
-
12)
- B. Solaiman , E. Pierce , F.T. Ulaby . Multisensor data fusion using fuzzy concepts: application to land-cover classification using ERS-1/JERS-1 SAR composites. IEEE Trans. Geosci. Remote Sens. , 3 , 1316 - 1326
-
13)
- H. Li , N. Abe . Generalizing case frames using a thesaurus and the MDL principle. Comput. Linguist. , 2 , 217 - 244
-
14)
- Palaniappan, K., Zhu, F., Zhuang, X., Zhao, Y., Blanchard, A.: `Enhanced binary tree genetic algorithm for automatic cover classification', IEEE Int. Geosci. Remote Sensing Symposium (IGARSS), Honolulu, HI, p. 24–28.
-
15)
- P.C. Smits , A. Annoni . Updating land-cover maps by using texture information from very high-resolution space-borne imagery. IEEE Trans. Geosci. Remote Sens. , 3 , 1244 - 1254
-
16)
- J.T. Chien . On-line hierarchical transformation of hidden Markov models for speech recognition. IEEE Trans. Speech Audio Process. , 6 , 656 - 667
-
17)
- J. Rissanen . (1989) Stochastic complexity in statistical inquiry.
-
18)
- J. Makhoul , S. Roucos , H. Gish . Vector quantization in speech coding. Proc. IEEE , 1551 - 1588
-
19)
- J.L. Gauvain , C.H. Lee . Maximum a posteriori estimation for multivariate Gaussian mixture observationsof Markov chains. IEEE Trans. Speech Audio Process. , 2 , 291 - 298
-
20)
- D.E. Goldberg . (1999) Genetic algorithms in search, optimization and machine learning.
-
21)
- P. Ohanian , R. Dubes . Performance evaluation for four classes of textural features. Pattern Recognit. , 8 , 819 - 833
-
22)
- L. Davis , L. Davis . (1991) Handbook of genetic algorithm.
-
23)
- J.D. Paola , R.A. Schowengerdt . A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification. IEEE Trans. Geosci. Remote Sens. , 4 , 981 - 996
-
24)
- A.H. Schistad Solberg , T. Taxt , A.H. Jain . A Markov random field model for classification of multisource satellite imagery. IEEE Trans. Geosci. Remote Sens. , 1 , 100 - 113
-
25)
- B.B. Chai , T. Huang , X. Zhuang , Y. Zhao , J. Sklansky . Piecewise linear classifiers using binary tree structure and genetic algorithm. Pattern Recognit. , 11 , 1905 - 1917
-
26)
- D.A. Reynolds . Speaker identification and verification using Gaussian mixture speaker models. Speech Commun. , 91 - 108
-
27)
- M. Pontil , A. Verri . Support vector machines for 3D object recognition. IEEE Trans. Pattern Anal. Mach. Intell. , 6 , 637 - 646
-
28)
- B.H. Juang , S. Katagiri . Discriminative learning for minimum error classification. IEEE Trans. Signal Process. , 3043 - 3054
-
29)
- Y.J. Hung , P.H. Swain . Bayesian contextual classification based on modified M-estimates and Markov random fields. IEEE Trans. Geosci. Remote Sens. , 1 , 67 - 78
-
30)
- B.-H. Juang , W. Chou , C.-H. Lee . Minimim classification error rate mothods for speech recognition. IEEE Trans. Speech Audio Process. , 3 , 257 - 265
-
31)
- C.-I. Chang , H. Ren . An experiment-based quantitative and comparative analysis of hyperspectral target detection and image classification algorithms. IEEE Trans. Geosci. Remote Sens. , 2 , 1044 - 1063
-
32)
- J. Li , A. Najmi , R.M. Gray . Image classification by a two-dimensional hidden Markov model. IEEE Trans. Signal Process. , 2 , 517 - 533
-
33)
- P.C. Smits , S.G. Dellepiane . Synthetic aperture radar image segmentation by detail observing Markov random field approach. IEEE Trans. Geosci. Remote Sens. , 4 , 844 - 857
-
34)
- Zhu, Y., Zhao, Y., Palaniappan, K., Zhou, X., Zhuang, X.: `Optimal Bayesian classifier for land cover classification using Landsat TM data', IEEE Int. Geosci. Remote Sensing Symposium (IGARSS), Honolulu, HI, p. 447–450.
-
35)
- S. Amari , S. Wu . Improving support vector machine classifiers by modifying kernel functions. Neural Netw. , 783 - 789
-
1)
Related content
