Please enter verification code
A visual mining based fame work for classification accuracy estimation
American Journal of Remote Sensing
Volume 1, Issue 2, April 2013, Pages: 47-52
Received: Apr. 12, 2013; Published: Apr. 2, 2013
Views 3116      Downloads 188
Arun, Pattathal Vijayakumar, MaulanaAzad National Institute of Technology- Bhopal, India
Article Tools
Follow on us
Classification techniques have been widely used in different remote sensing applications and correct classi-fication of mixed pixels is a tedious task. The problem is more complex with the classification of hyperspectral data and requires a thorough analysis. Traditional approaches adopt various statistical parameters, however does not facilitate effective visualisation. Data mining tools are proving very helpful in the classification process. We propose a visual mining based frame work for accuracy assessment of classification techniques using open source tools such as WEKA and PREFUSE. These tools in integration can provide an efficient approach for getting information about improvements in the classification accuracy and helps in refining training data set. We have illustrated frame work for investigating the effects of various resampling methods on classification accuracy and found that bilinear (BL) is best suited for preserving radiometric characteristics. We have also investigated the optimal number of folds required for effective analysis of LISS4 images.
Data mining, Remote sensing, Decision tree, Image classification, Visualization, WEKA, PREFUSE
To cite this article
Arun, Pattathal Vijayakumar, A visual mining based fame work for classification accuracy estimation, American Journal of Remote Sensing. Vol. 1, No. 2, 2013, pp. 47-52. doi: 10.11648/j.ajrs.20130102.15
Bouckaert R. R., Frank E., Hall M. A., Holmes G., Pfahringer B., Reutemann P., Witten I. H., 2010, "WEKA—Experiences with a Java Open-Source Project," Journal of Machine Learning Research, vol.11, pp. 2533-2541.
Durbha S.S., King R.L., 2005, "Semantics-enabled framework for knowledge discovery from Earth observation data archives," IEEE Transaction on Geoscience and Remote Sensing, vol.43, pp. 2563–2572.
Keim D.A., Panse C., Sips M., 2003, "PixelMaps: A New Visual Data Mining Approach for Analyzing Large Spatial Data Sets," Proceedings of 3rd IEEE Int’l Conf. Data Mining (ICDM 03), IEEE CS Press, pp. 565-568.
Lillesand Thomas M, Kiefer Ralph W, Chipman Jonathan W, 2004, "Remote Sensing and Image Interpretation," John Wiley & Sons (Asia), Singapore.
Liu Y, Salvendy G., 2007 "Design and evaluation of visualization support to facilitate decision trees classification," International Journal of Human- Computer Studies, vol.65, pp. 95–110.
Lu D, Weng Q, 2007, "A survey of image classification methods and techniques for improving classification performance," International Journal of Remote Sensing, vol. 28, pp. 823–870.
Nghi Dang Huu, Mai Luong Chi., "An object-oriented classification techniques for high resolution satellite imagery," GeoInformatics for Spatial-Infrastructure Development in Earth and Allied Sciences (GIS-IDEAS), pp. 230-240, 2008.
Vapnik V, "Statistical Learning Theory," Wiley Publishers Inc. New York, pp.230-240, 1998.
Wilkinson G.G., 2005, "Results and implications of a study of fifteen years of satellite image classification experiments," IEEE Transactions on Geoscience and Remote Sensing vol. 43, pp. 433–440.
Witten I.H., and Frank E, 2005, "Data Mining: Practical Machine Learning Tools and Techniques," Morgan Kaufmann, San Francisco, CA, pp.120-134.
Zhang J., Gruenwald Le, Gertz M, 2009. "VDM-RS: A visual data mining system for exploring and classifying remotely sensed images," Journal of Computers and Geosciences, pp. 1188–1192.
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
Tel: (001)347-983-5186