MPEG-7 Homogeneous Texture Descriptor

MPEG7 standardization work has started with the aims of providing fundamental tools for describing multimedia contents. MPEG7 defines the syntax and semantics of de-scriptors and description schemes so that they may he used as fundamental tools for multimedia content description. In this paper, we introduce a texture based image descrip-tion and retrieval method, which is adopted as the homo-geneous texture descriptor in the visual part of the MPEG 7 final committee draft. The current MPEG7 homogene-ous texture descriptor consists of the mean, the standard deviation value of an image, energy, and energy deviation values of Fourier transform of the image. These are ex-tracted from partitioned frequency channels based on the human visual sjktem (HVS). For reliable extraction of the texture descriptor, Radon transformation is employed. This is suitable for HVS behavior. We alqo introduce vari-ous matching methods; for example, intensity-invariant, rotation-invariant andlor scale-invariant matching. This technique retrieves relevant texture images when the user gives a querying texture image. In order to show the prom-ising performance of the texture descriptor, we take the ex-perimental results with the MPEG7 test sets. Experimen-tal results show that the MPEG7 texture descriptor gives an efficient and effective retrieval rate. Furthermore, it gives fast feature extraction time for constructing the tex-ture descriptor.