Image Retrieval Based on the Energy and Entropy of Multiwavelets Transform

A new retrieval algorithm based on the energy and entropy of multiwavelets is presented. Firstly, the retrieval image is decomposed by the multiwavelets transform. Secondly, the 0/1 quantization is used to deal with the energy matrix of sub image of multiwavelets decomposition. The multiwavelets entropy and energy of image is computed as the texture feature of image. The Gaussian model is used to normalize the sub-characters of different images. Finally, the texture similarity of the querying image and other images is computed by the L1-norm distance. Experiments indicate that this method gives better performance in texture image retrieval than FWHT and MWHT.