A novel approach for multi-scale texture segmentation based on fractional differential

  • Authors:

  • Yi-Fei Pu;Ji-Liu Zhou

  • Affiliations:

  • School of Computer Science and Technology, Sichuan University, Chengdu, China,Laboratoire de l'IADI ERI (INSERM-UHP) au CHU de Nancy Brabois, Universite Henri Poincare (Nancy I), Vandoeuvre les Na ...;School of Computer Science and Technology, Sichuan University, Chengdu, China

  • Venue:
  • International Journal of Computer Mathematics
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we intend to implement multi-scale texture segmentation by fractional differential. We propose two fractional differential masks and present the structures and parameters of each mask, respectively, on eight directions. Moreover, by theoretical and experimental analysis, we find the better performance fractional differential mask. Finally, we further discuss the capability of fractional differential for multi-scale texture segmentation. Experiments show that, for rich-grained digital images, the capability for multi-scale texture segmentation by fractional differential-based approach appears efficient.