Mining regions of remote sensing images

Authors:
Jules-Raymond Tapamo;Rowan Titlestad;Serestina Viriri
Affiliations:
University of KwaZulu-Natal, School of Electrical, Electronic and Computer Engineering, Durban, South Africa;University of KwaZulu-Natal, School of Computer Science, Durban, South Africa;University of KwaZulu-Natal, School of Computer Science, Durban, South Africa
Venue:
CIMMACS '10 Proceedings of the 9th WSEAS international conference on computational intelligence, man-machine systems and cybernetics
Year:
2010

Citing 5
Cited 0

Texture discrimination by Gabor functions

Biological Cybernetics
Biologically motivated computationally intensive approaches to image pattern recognition

Future Generation Computer Systems - Special double issue: high performance computing and networking (HPCN)
Support vector machine active learning for image retrieval

MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
Mining Patterns of Change in Remote Sensing Image Databases

ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Comparison of texture features based on Gabor filters

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Large amounts of remote sensing satellite data is available but the sheer amount of information makes it difficult to find land areas based on their content rather than readily available attributes such as geographic position. A content- based image retrieval system for remote sensing images is presented in this paper as an attempt to solve the problem of finding specific land areas based on their texture. The system makes use of a bank of Gabor filters for feature extraction and a one-class support vector machine for classification. Very promising results are obtained.