A Fast Adaptive Content-based Retrieval System of Satellite Images Database using Relevance Feedback

In this paper, we present a system for content-based retrieval of large database of classified satellite images, based on user's relevance feedback (RF).Through our proposed system, we divide each satellite image scene into small subimages, which stored in the database. The modified radial basis functions neural network has important role in clustering the subimages of database according to the Euclidean distance between the query feature vector and the other subimages feature vectors. The advantage of using RF technique in such queries is demonstrated by analyzing the database retrieval results.

Authors:

• Hanan Mahmoud Ezzat Mahmoud
• Alaa Abd El Fatah Hefnawy

Keywords:

• content-based image retrieval
• large database of image
• RBF neural net
• relevance feedback

References:

[1] John A. Richards and Xiuping Jia, "Remote Sensing Digital Image
Analysis: an introduction" third edition pp 1-73 2000.
[2] Milan Sonka, Vaclav Hlavac, Roger Boyle "Image Processing Analysis
and Machine Vision" second edition pp 290-361, 1999.
[3] Floyd F. Sabins, "Remote Sensing, principles and interpretation: land
use and land cover" third edition pp387-416, 1999.
[4] Adeli,H., and Hung, S., John Wily, "Machine Learning- Neural
Networks, Genetic Algorithms, and Fuzzy Systems" 1995.
[5] Bose, N.K., and Liang, P.,"Neural Networks Fundamentals with Graphs,
Algorithms, and Application", Mc-GrawHill,NY.1996.
[6] Lipmann,R.P."An introduction to computing with Neural Networks"
IEEE ASSP Magazine.1991.
[7] Benediktsson,J.A., Swain, P.H., and Erosy, O. "Neural
netrorkApproaches versus Statistical methods in classification of
Multisource Remote sensing Data", IEEE Trans. Geoscience and
Remote sensing,vol. 28,no.4,pp540-552.
[8] Paul L. Rosin and Freddy Fierens."Improving Neural Network
Grnralization" In Proceedings of IGARSS'95, 1995.
[9] Krishna Mohan Buddhiraju "Contextual Refinement of neural network
classification using Relaxation Labelling Algorithms"22nd Asian
Conference on Remote sensing.November 2001.
[10] Chen, D.,D. Stow, and P Gong, "Examining the effect of spatial
resolution on classification accuracy : an urban environmental case "
International Journal of Remote Sensing 25(00):1-16, 2004.
[11] Chen, D.,D. Stow, and P Gong, "Strategies for integrating information
from multiple spatial resolutions into land use/land cover classification
routines" Photogrammetric Engineering & Remote Sensing
,69(11):1279-1287,2003.
[12] Chen, D.,D. Stow, and P Gong, "the effect of training strategies on
supervised classification at different spatial resolutions Photogrammetric
Engineering & Remote Sensing ,68(11):1155-1162.
[13] Foody, G.M.,"Status of land cover classification accuracy assessment"
Remote Sensing of Environmental 80 pp.185-201.
[14] Mc Cullac and Pits "Artificial Neural Networks :An Introduction -
Radial Basis Function Neural Network" Chapter7, pp 236-284,1995.
[15] T.Bretschneider,O.Kao, "A Retrieval System For Remotely sensed
Imagery" NASA EPSCoR, 2000.
[16] Koki Iwao, Taizo Yamamoto,Ryosuke, Shiro Ochi, and Mitsuharu
Tokunaga "Automatic Database Development Methods for a very large
number of satellite images " spatial information science, Tokyo
University, 2001.
[17] Y. Rui, T.S.Huang, "A novel relevance feedback technique in image
retrieval" in Proceedings ACM Multimedia'99 (Part2), Orlando, FL,
USA, pp.67-70, 1999.
[18] Z. Jin, I. King, X.Q. Li, " Content-Based image retrieval by relevance
feedback" in Proceedings of the fouth international Conference on visual
information systems, Lecture notes in computer science, Vol.1929,
Lyon, France, November 2-4 Springer, Berlin, 2000.