An adaptive fuzzy-inference-rule-based flexible model for automatic elastic image registration

Fu Lai Korris Chung, Zhaohong Deng, Shitong Wang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

9 Citations (Scopus)


In this study, a fuzzy-inference-rule-based flexible model (FIR-FM) for automatic elastic image registration is proposed. First, according to the characteristics of elastic image registration, an FIR-FM is proposed to model the complex geometric transformation and feature variation in elastic image registration. Then, by introducing the concept of motion estimation and the corresponding sum-of-squared-difference (SSD) objective function, the parameter learning rules of the proposed model are derived for general image registration. Based on the likelihood objective function, particular attention is also paid to the derivation of parameter learning rules for the case of partial image registration. Thus, an FIR-FM-based automatic elastic image registration algorithm is presented here. It is distinguished by its 1) strong ability in approximating complex nonlinear transformation inherited from fuzzy inference; 2) efficiency and adaptability in obtaining precise model parameters through effective parameter learning rules; and 3) completely automatic registration process that avoids the requirement of manual control, as in many traditional landmark-based algorithms. Our experiments show that the proposed method has an obvious advantage in speed and is comparable in registration accuracy as compared with a state-of-the-art algorithm.
Original languageEnglish
Pages (from-to)995-1010
Number of pages16
JournalIEEE Transactions on Fuzzy Systems
Issue number5
Publication statusPublished - 22 Oct 2009


  • Adaptive learning
  • Elastic image registration
  • Fuzzy inference rule
  • Motion estimation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this