Dual Pyramid of Agents for Image Segmentation

An effective method for the early detection of breast cancer is the mammographic screening. One of the most important signs of early breast cancer is the presence of microcalcifications. For the detection of microcalcification in a mammography image, we propose to conceive a multiagent system based on a dual irregular pyramid. An initial segmentation is obtained by an incremental approach; the result represents level zero of the pyramid. The edge information obtained by application of the Canny filter is taken into account to affine the segmentation. The edge-agents and region-agents cooper level by level of the pyramid by exploiting its various characteristics to provide the segmentation process convergence.

Authors:

• K. Idir
• H. Merouani
• Y. Tlili.

Keywords:

• Dual Pyramid
• Image Segmentation
• Multi-agent System
• Region/Edge Cooperation.

References:

[1] P. Bertolino. "Contributions des pyramides irrégulières en segmentation
d'images multirésolution". Ph.D. thesis, Institut National Polytechnique
de Grenoble, 1995
[2] A. Boucher. "Une approche décentralisée et adaptative de la gestion
d'informations en vision, Application ├á l'interprétation d'images de
cellules en mouvement". Ph.D. thesis, Université Joseph Fourier,
Grenoble, 1999.
[3] J.F. Canny. "A computational approach to edge detection". Patt
Ana.Mach. Int, 1986, pp. 8(6):679-698.
[4] DDSM: Digital Database for Screening Mammography. University of
South Florida.
http://marathon.csee.usf.edu/Mammography/Database.html00
[5] E. Duchesnay. "Agents situés dans l-image et organisés en pyramide
irrégulière. Contribution ├á la segmentation par une approche
d-agrégation coopérative et adaptative". Ph.D. Université de Rennes-1,
2001.
[6] J. Freixenet, X. Munoz, D. Raba, J. Mart and X. Cufi. "Yet Another
Survey on Image Segmentation: Region and Boundary Information
Integration". ECCV 2002, LNCS 2352, Springer- Berlin Heidelberg,
2002, pp. 408-422.
[7] F. Gaspoz. "Mammographie digitale & Analyse d-images par
ordinateur". Laboratoire TIMC - IMAG. Faculté de Médecine
Grenoble. Université Joseph Fourier Grenoble, France. 2003
[8] L. Germond, M.Dojat, C. Taylor, C. Garbay. "A Cooperative Framework
for Segmentation of MRI Brain Scans". Artif. Intell. in Med. 20 (2000),
pp. 277-94.
[9] Y. Haxhimusa, W.G. Kropatsch. "Hierarchical Image Partitioning with
Dual Graph Contraction". Technical Report PRIP-TR-81, Institute of
Computer Aided Automation 183/2, Patt. Recogn. Image. Proc Group,
Austria, 2003.
[10] J.M. Jolion and A. Montanvert. "The adapted pyramid: a framework for
2d image analysis". Computer Vision Graphics and Image Processing,
May 1992, pp. 55(3):339-348.
[11] W.G. Kropatsch. "Building irregular pyramids by Dual Graph
Contraction". Technical Report PRIP-TR-35, Institute of Automation
183/2, Dept. for Patt. Rec. Image. Proc, TU Wien,Austria, 1994.
[12] H. Macho, W. Kropatsch. "Finding connected components with dual
irregular pyramids". PRIP, Institute for Automation, AUSTRIA. In
Cinquième Colloque DGCI, p.147-158. LLAIC1, Université d'Auvergne
(1995).
[13] P. Meer. "Stochastic image pyramids". Comp. Vision. Graph. Image
Proc, 1989, pp. 45 (3): 269-294.
[14] N. Selmaoui, W. Kropatsch. "Watershed by Dual Graph Contraction."
PRIP - Institute for Automation, 183/2. Vienna University of
Technology, Austria (1997).
[15] H. Settache. "Une plate-forme multi-agents pour la segmentation
d-images: Application dans le domaine des IRM cérébrales 2D". DEA
Report, Université de Caen, 2002
[16] D. Willersinn. "Parallel Graph Contraction for Dual Irregular
Pyramids". PRIP-TR 28, Institute for Automation, 183/2, Technical
University of Vienna, Austria, 1994