This article describes a novel approach to orientation andscale-invariant detection of textured objects in images. It performsboth, a segmentation of multi-object scenes and the identification ofrotation angles and scale rates of textures in an image by applying acomparison with reference texture features stored in a database. Themain novelty of the proposed method is the transform of rotation anddilation into shifts in the feature space by employing a polar-log Gaborfilter bank. Texture segmentation and identification of the rotationangles and scale rates have been carried out using symmetric phase onlymatched filters. The simulation results illustrated highlight theperformance of the presented method in an exemplary manner
展开▼
