A TV Flow Based Local Scale Measure for Texture Discrimination

We introduce a technique for measuring local scale, based on a special property of the so-called total variational (TV) flow. For TV flow, pixels change their value with a speed that is inversely proportional to the size of the region they belong to. Exploiting this property directly leads to a region based measure for scale that is well-suited for texture discrimination. Together with the image intensity and texture features computed from the second moment matrix, which measures the orientation of a texture, a sparse feature space of dimension 5 is obtained that covers the most important descriptors of a texture: magnitude, orientation, and scale. A demonstration of the performance of these features is given in the scope of texture segmentation. In Proc. 8th European Conference on Computer Vision, Springer LNCS 3022, T. Pajdla and J. Matas (Eds.), vol. 2, pp. 578-590, Prague, Czech Republic, May 2004 c Springer-Verlag Berlin Heidelberg 2004

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Thomas Brox, Joachim Weickert
• Keywords: Computer Vision, ECCV 2004, Region Based Measure, Springer-Verlag Berlin Heidelberg, Texture Discrimination, Texture Features, Texture Segmentation