M-Band Wavelet Based Texture Features for Content Based Image Retrieval.
Manesh Kokare, Biswanath N. Chatterji, Prabir Kumar Biswas · 2002
Biorthonormal M-band wavelet transform is used to decompose the image into M × M sub-bands for constructing the feature database in content-based image retrieval of 1856 Brodatz texture images. Texture features are obtained by computing the measure of energy, standard deviation and its combination on each band. Results are far superior and impressive than conventional two-band wavelet decomposition. Keywords: M-band wavelet, 2-band wavelet, Content-based image retrieval, image database, feature database, similarity, query image, texture analysis. 1.Introduction: Worldwide networking allows us to communicate, share, and learn information in the