Texture Segmentation Using Directional Empirical Mode Decomposition (MA-P2)

Author(s) : Zhongxuan Liu (Institute of Automation, Chinease Academy of Sciences, China) Hongjian Wang (Institute of Automation, Chinease Academy of Sciences, China) Silong Peng (Institute of Automation, Chinease Academy of Sciences, China)

Abstract : In this paper the technique of Directional Empirical Mode Decomposition (DEMD) and its application to texture segmentation are presented. Empirical Mode Decomposition (EMD) decomposes signals by sifting and then analyzes the instantaneous frequency of the obtained components called Intrinsic Mode Functions (IMFs). As a new form of extending 1-D EMD to 2-D case, DEMD considers the directional frequency and envelope at each point. One type of 2-D Hilbert transform is introduced to compute the analytical functions for the frequency and envelope. The technique of selecting directions for DEMD based on texture's Wold theory is also presented. Experimental results indicate the effectiveness of the method for texture segmentation.

Menu