Color-texture analysis by mutual information for multispectral image classification

TitleColor-texture analysis by mutual information for multispectral image classification
Publication TypeMiscellaneous
Year of Publication2009
AuthorsH. Maia, E., Hammouch A., & Aboutajdine D.
Keywordsco-occurrence matrix, feature extraction, forest areas, hybrid color texture space, image analysis, image classification, Image color analysis, image colour analysis, Image databases, image texture, Information analysis, Morocco, multispectral image classification, Multispectral imaging, mutual information, Rabat, RGB color space, Spatial databases, SPOT HRV (XS), Support vector machine classification, support vector machines, support vectors machine (citation), VisTex database
Abstract

In this paper, we propose a new approach for the construction of a hybrid color-texture space by using mutual information. Feature extraction is done by the co-occurrence matrix with SVM (support vectors machine) as a classifier. We apply our approach to the VisTex database and to the classification of a SPOT HRV (XS) image representing two forest areas in the region of Rabat in Morocco. We compare the result of classification obtained in this hybrid space with the one in the RGB color space.