Content-based color image retrieval via lifting scheme

Content-based image retrieval (CBIR) aims at querying targets by using visual contents of image itself. Although classical wavelet transform is effective in representing image feature and thus is suitable in CBIR, it still encounters problems especially in implementation, e.g. floating-point operation and decomposition speed, which may nicely be solved by lifting scheme, a novel spatial approach for constructing biorthogonal wavelet filters. Lifting scheme has such intriguing properties as convenient construction, simple structure, integer-to-integer transform, low computational complexity as well as flexible adaptivity, revealing its potentials in CBIR. In this paper, by using general lifting and its adaptive version, we decompose HSI color images into multilevel scale and wavelet coefficients, with which, we can perform image feature extraction and similarity match by means of F-norm theory. Meanwhile, we provide a progressive image filtering strategy to achieve flexible CBIR. Eventually, the retrieval performances of lifting scheme are compared with those of its classical counterpart in retrieval accuracy and speed.