TEXTURE FEATURES FOR BROWSING AND RETRIEVAL OF IMAGE DATA

Image content based retrieval is emerging as an important research are a with application to digital libraries and multimedia databases. The focus of this paper is on the image processing aspects and in particul ar using texture information for browsing and retrieval of large image data. We propose the use of Gabor wavelet features for texture analys is and provide a comprehensive experimental evaluation. Comparisons wi th other multiresolution texture features using the Brodatz texture da tabase indicate that the Gabor features provide the best pattern retri eval accuracy. An application to browsing large air photos is illustra ted.