Rotation and scale invariant wavelet feature for content‐based texture image retrieval

Abstract

This article introduces an effective rotation and scale invariant log-polar wavelet texture feature for image retrieval. The proposed feature is an attempt to enhance the existing content-based image retrieval systems that largely present difficulty in coping with images with changes in orientations and scales. The underlying feature extraction process involves a log-polar transform followed by an adaptive row shift invariant wavelet packet transform. The log-polar transform converts a given image into a rotation and scale invariant but rowshifted image, which is then further processed through an adaptive row-shift invariant wavelet packet transform operation to generate adaptively selected subbands of rotation and scale invariant wavelet coefficients, based on an information cost function. An energy signature is computed for each subband of these wavelet coefficients. To reduce feature dimensionality, only the most dominant log-polar wavelet energy signatures are selected for the feature vector for image retrieval. The overall feature extraction process is quite efficient and involves only O(n ⅐ log n) complexity. Experimental results show that this rotation and scale invariant wavelet feature is quite effective for image retrieval and outperforms the traditional wavelet packet signatures.

Content-Based Image Retrieval: A Comparison between Query by Example and Image Browsing Map Approaches

“…Texture features. Many texture features have been investigated in the past, including the conventional pyramid-structured wavelet transform (PWT) features, tree-structured wavelet transform (TWT) features, the multi-resolution simultaneous autoregressive model (MR-SAR) features and the Gabor wavelet features [18]. Experiments have been conducted and have found that the Gabor features produce the best performance [2,20].…”

Adaptive LUM pre-ltering for af ne invariant interest point detection

“…Some of the most recent solutions propose invariant features to geometric distortions [19] [20]. Once again, an effective retrieval method can be designed by using affine invariant interest points as features, without the need of performing a matching operation.…”