Abstract
The Directional Neighborhoods Approach (DNA) to classifying pixels and reconstructing images from remotely sensed noisy data is a newly proposed, computer intensive, Bayesian-type procedure. It uses the observational data to select an optimal, generally asymmetric, but relatively homogeneous, neighborhood for contextually classifying pixels. We provide Monte Carlo simulations for a 2-population image and compare DNA results with those from a reference Bayesian contextual classification. We show that DNA improves substantially upon the reference classification procedure.
The author is grateful for NSF travel grant NSF/INT-9016175. He is also grateful to Getachew Dagne for his help with the computer simulation work in Section 3.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Geisser, S (1964), “Posterior Odds for Multivariate Normal Classification”, Journal of the Royal Statistical Soceity, Ser. B, 26, 69–76.
Geisser, S. (1965), “Bayesian Estimation in Multivariate Analysis”, The Annals of Mathematical Statistics, 36, 150–159
Geisser, S. (1966), “Predictive Discrimination”, in Multivariate Analysis, ed. P. R. Krishnaiah, New York: Academic Press, pp. 149–163
Klein, R, and Press, SJ (1989), “Contextual Bayesian Classification of Remotely Sensed Data”, Communications in Statistics, Part A Theory and Methods, 18, 3177–3202
Klein, R., and Press, S. J. (1990a), “Bayesian Contextual Classification with Neighbors Correlated with Training Data”, in Bayesian and Likelihood Methods in Statistics and Econometrics: Essays in Honor of George A. Bernard, eds. S. Geisser, J. Hodges, S.J. Press, and A. Zellner, New York: North-Holland pp. 337–355
Klein, R., and Press, S. J. (1990b), “Bayesian Classification of Remotely Sensed Data When Training Data is Part of the Scene”, Revista Brasileira de Probabilidade e Estatistica, 4, 43–67
Klein, R., and Press, S. J. (1992), “Adaptive Bayesian Classification of Spatial Data”, Journal of the American Asssociation, Vol. 87, No. 419, pp. 844–851
Klein, R., and Press, S. J. (1993), “Adaptive Bayesian Classification with a Locally Proportional Prior”, Communications in Statistics - Theory and Methods, 22 (10), 2925–2940
Mardia, K. V. (1984), “Spatial Discrimination and Classification Maps”, Communications in Statistics–Theory and Methods, 13, 2181–2197
Press, SJ (1996), “The Directonal Neighborhood Approach To Contextual Classification of Image From Noisy Data”, Jour. Amer Stat. Assn., in press.
Switzer, P. (1980), “Extensions of Linear Discriminant Analysis for Statistical Classification of Remotely Sensed Satellite Imagery”, Mathematical Geology, 12, 367–376
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media New York
About this chapter
Cite this chapter
Press, S.J. (1996). Some Simulation Results for the Performance of DNA Classification of Noisy Image Data. In: Lee, J.C., Johnson, W.O., Zellner, A. (eds) Modelling and Prediction Honoring Seymour Geisser. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-2414-3_11
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2414-3_11
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-7529-9
Online ISBN: 978-1-4612-2414-3
eBook Packages: Springer Book Archive