Rotation invariant textural feature extraction for image retrieval using eigen value analysis of intensity gradients and multi-resolution analysis

• Eigen value analysis of gradients for accurate principal texture direction.
• Rotation invariant feature extraction by aligning the principal texture direction.
• Independent existence of sub-band features in forming textural feature set.
• Robust and computationally efficient principal texture detection algorithm.
• Significant improvement of retrieval performance for anisotropic textures.

In this paper a novel rotation invariant multi-resolution based texture retrieval technique is proposed. The rotation invariance is achieved by aligning the direction of maximum variation of intensity gradient (defined as principal texture direction) along the reference axis. The principal direction is determined using eigen value analysis of gradient image. Wavelet transform based techniques are applied on the rotated image. The independent representation of textural energies along various directions enhances the retrieval performance over the existing rotation invariant wavelet based techniques which achieve rotation invariance by averaging the direction sensitive components. Extensive experiments on Brodatz database support this postulate.