Fuzzy Relaxation Based on the Theory of Possibility and FAM

  • Uam, Tae-Uk (Dept. of Electronci Tech., Kumi Polytechnic College) ;
  • Park, Yang-Woo (Dept. of Compute nforamtion Science, Hankook Univeristy) ;
  • Ha, Yeong-Ho (Sch. of Electronic and Electrical Eng., Kyungpook National University)
  • Published : 1997.10.01

Abstract

This paper presents a fuzzy relaxation algorithm, which is based on the possibility and FAM instead of he probability and compatibility coefficients used in most of existing probabilistic relaxation algorithms, Because of eliminating stages for estimating of compatibility coefficients and normalization of the probability estimates, the proposed fuzzy relaxation algorithms increases the parallelism and has a simple iteration scheme. The construction of fuzzy relaxation scheme consists of the following three tasks: (1) definition of in/output linguistic variables, their term sets, and possibility. (2) Definition of FAM rule bases for relaxation using fuzzy compound relations. (3) Construction of the iteration scheme for calculating the new possibility estimate. Applications to region segmentation an ege detectiojn algorithms show that he proposed method can be used for not only reducing the image ambiguity and segmentation errors, but also enhancing the raw edge iteratively.

Keywords

References

  1. IEEE Trans. on syst, Man, and Cybern v.SMC-6 Scene labelig by relaxation operation A.Rosenfeld;R.A.Hummel;S.W.Zucker
  2. IEEE Trans. Patt. Anal. and Mach. Intell v.PAMI-3 no.5 Thresholding using relaxation A.Rosenfeld;R.C.Smith
  3. IEEE Trans.Computer v.C-26 an application of relaxation labeling to line and curve enhancement S.w.Zucker;R.A.Hummel;A.Rosenfeld
  4. IEEE Trans. Patt. Anal. and Mach. Intell v.PAMI-2 Extracting aand labeling bouundary segment in natural scenes J.M.Prager
  5. IEEE Trans. Patt. Anal. and Mach. Intell v.PAMI-3 no.2 Pixel labeling by superived probabilistic relaxation J.A.Richard;D.A.Landgrade;P.H.Swain
  6. IEEE Trans. Patt. Anal. and Mach. Intell v.PAMI-4 no.6 Augmented relaxation labeling and dynamic relaxation labeling S.A.Kusclel;C.V.Page
  7. Computer Sciens Center Method ofdriving compatibility coefficents for relaxation operator H.Yamamoto
  8. Pattern Recognition Letters v.2 The fuzzy geometry of image subset A.Rosenfeld
  9. Fuzzy set Theory and Its Applications H.J.Zimmermann
  10. Neural Networks and Fuzzy Systems B.Kosko
  11. Fuzzy Sets, Uncertainy and Information G.J.Klir;T.A.Folger
  12. Computer Vision D.H.Ballard;C.M.Brown
  13. Proc. of Korean Sig. Pro. Conference the new iterative image swgmentation algorithm using by fuzzy relaxation T.A.Uam;K.M.Kim;TY.W.Park;Y.H.Ha