A level-set model driven by Bidimensional EMD for sonar image segmentation

This paper proposes a new multiphase level set model. Its energy function is driven by Bidimensional EMD (Empirical Mode Decomposition) to resolve the segmentation problem of sonar image. We introduce the EMD and BEMD, and give the steps of BEMD. It is used to extract intrinsic components of images. Then, we integrate them into the VC's (Vese-Chan) multiphase level set energy functions to resolve the sensitiveness of level set models to noise. Experimental results show that the segmentation results of our method is superior than the VC level set model.

[1]  Silong Peng,et al.  Boundary Processing of bidimensional EMD using texture synthesis , 2005, IEEE Signal Processing Letters.

[2]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[3]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[4]  Thomas Brox,et al.  Universität Des Saarlandes Fachrichtung 6.1 – Mathematik Level Set Segmentation with Multiple Regions Level Set Segmentation with Multiple Regions , 2022 .

[5]  Enfang Sang,et al.  Sonar image segmentation using snake models based on cellular neural network , 2005, 2005 IEEE International Conference on Information Acquisition.

[6]  Scott Reed,et al.  An automatic approach to the detection and extraction of mine features in sidescan sonar , 2003 .

[7]  Peter X. Liu,et al.  Sonar image segmentation based on GMRF and level-set models , 2010 .

[8]  Patrick Pérez,et al.  Sonar image segmentation using an unsupervised hierarchical MRF model , 2000, IEEE Trans. Image Process..

[9]  Lin Zhao,et al.  A novel automatic segmentation algorithm for sonar imagery , 2008, 2008 IEEE International Conference on Mechatronics and Automation.

[10]  Christophe Chesnaud,et al.  Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Jie Wei,et al.  An efficient two-pass MAP-MRF algorithm for motion estimation based on mean field theory , 1999, IEEE Trans. Circuits Syst. Video Technol..

[12]  Patrick Pérez,et al.  Three-Class Markovian Segmentation of High-Resolution Sonar Images , 1999, Comput. Vis. Image Underst..

[13]  Aly A. Farag,et al.  Modified fuzzy c-mean in medical image segmentation , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).