Using texture and shape features to retrieve sets of similar medical images

In this paper, a novel scheme has been proposed for image retrieval task using the feature extracted directly from a compressed or uncompressed image. The texture information is first extracted by exploiting the multiresolution nature of wavelet decomposition, which represent the horizontal, vertical and diagonal frequency distribution of an image. We then calculate the mean and standard deviation of wavelet coefficients of each sub-band as texture features. In additions, we also extract shape feature by using the fixed-resolution block representation, which divides the image into isometric blocks and calculate the overlapped degree of each block with binary codes. The experimental results show that the retrieval efficiency is considerably improved by the proposed approach.