Demo Program

 

Spatial AdaBoost: Example used in

″Supervised Image Classification by Contextual AdaBoost Based on Posteriors in Neighborhoods"
by R. Nishii and S. Eguchi (2005)
IEEE Transactions on Geoscience and Remote Sensing, 43(11), 2547-2554.


Matlab source code and the simulated data sets for supervised image classification are available from this point. Download the following six files.

Multispectral images with variance = 1
Multispectral images with variance = 4
Subroutine for tuning the coefficient
Subroutine for deriving neighborhood information
Spatial AdaBoost soruce file for DataGen20.mat
Spatial AdaBoost soruce file for DataGen23.mat

Put six files in the same directory, and execute Matlab. Then read the source file BoostLogPost20.m or BoostLogPost23.m.

 

Color figures

″A Markov random field-based approach to decision level fusion
for remote sensing image classification,"
by R. Nishii (2003)
in IEEE Transactions on Geoscience and Remote Sensing, vol. 41 (10), pp. 2316 - 2319.

Color figures

″Contextual image fusion based on Markov random fields
and its applications to geo-spatial image enhancement"
by R. Nishii and Y. Morisaki (2002)
in Advances in Statistics, Combinatorics and Related Areas, 2002
Gulati et al. (Eds.), World Scientific, New Jersey, pp. 167 - 179.

 

C-programs for Accuracy Assessment of Error Matrices

This program is used in the paper
"Accuracy and inaccuracy assessments in land-cover classification",
by R. Nishii and S. Tanaka (1999)
in IEEE Transactions on Geoscience and Remote Sensing, vol. 37(1), pp. 491 - 498.

 

For further info, send email to  

nishii@math.kyushu-u.ac.jp

mailto:nishii@math.kyushu-u.ac.jp