Title :
Coalescing ICA and Wavelets Coefficients for Image Information Mining in Earth Observation Data Archives
Author :
Shah, Vijay P. ; Durbha, Surya S. ; Younan, Nicolas H. ; King, Roger L.
Author_Institution :
Dept. of Electr. & Comput. Eng., Mississippi State Univ., Starkville, MS
fDate :
July 31 2006-Aug. 4 2006
Abstract :
Reflectance pattern and spatial pattern characterize the geospatial data. Current semantic-enabled framework retrieval system extract primitive features based on color, texture (Spatial Gray Level Dependency - SGLD matrices), and shape from the segmented homogenous region. This system can use only three bands (true color or false color) at a time to capture color information as it converts RGB space into HSV space. Thus it fails to capture the complete reflectance pattern, an important characteristic of geospatial data. This paper describes a new method to perform image segmentation using the features obtained by coalescing of Independent Component Analysis and Wavelet transform, which are later on used for the region-based retrieval in the earth observation data archives. Experimental results show effectiveness of the proposed method for image information mining in Earth observation data archives.
Keywords :
data mining; feature extraction; geophysical signal processing; geophysical techniques; image colour analysis; image segmentation; image texture; independent component analysis; visual databases; wavelet transforms; Earth observation data archives; HSV space; ICA coefficients; RGB space; SGLD matrix; Spatial Gray Level Dependency; geospatial data; image information mining; image region color; image region shape; image region texture; image segmentation; independent component analysis; primitive feature extraction; reflectance pattern; region based retrieval; semantic enabled framework retrieval system; spatial pattern; wavelet coefficients; Data mining; Earth; Feature extraction; Image converters; Image segmentation; Independent component analysis; Matrix converters; Reflectivity; Shape; Wavelet coefficients;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006. IEEE International Conference on
Conference_Location :
Denver, CO
Print_ISBN :
0-7803-9510-7
DOI :
10.1109/IGARSS.2006.7
