A new shape descriptor based on tensor scale

Tensor scale is a morphometric parameter that unifies the repre-sentation of local structure thickness, orientation, and anisotropy, which can be used in several computer vision and image process-ing tasks. In this paper, we exploit this concept for binary images and propose a shape descriptor that encodes region and contour properties in a very efficient way. Experimental results are pro-vided, showing the effectiveness of the proposed descriptor, when compared to other relevant shape descriptors, with regard to their use in content-based image retrieval systems.