Rotation invariant texture feature for content based image retrieval

An effective rotation invariant polar-wavelet texture feature for content based image retrieval is proposed. The feature extraction process involves a polar transform followed by an adaptive row shift invariant wavelet packet transform. The polar transform converts a given image into a rotation-invariant but row-shifted image, which is then passed to the adaptive row shift invariant wavelet packet transform to generate adaptively some subbands of rotation invariant wavelet coefficients with respect to an information cost function. An energy signature is computed for each sub-band of these wavelet coefficients. In order to reduce feature dimensionality, only the most dominant polar-wavelet energy signatures are selected as feature vectors for image retrieval. The whole feature extraction process is quite efficient and involves only O(n·log n) complexity. Experimental results show that this rotation-invariant texture feature is effective and outperforms traditional wavelet packet signatures.