Multiscale fuzzy reasoning (MFR) for automatic object extraction

A. Sheikh Akbari, J.J. Soraghan

Research output: Contribution to journalArticlepeer-review


A new Multiscale Fuzzy Reasoning (MFR) based image-processing technique for automatic object extraction is described. MFR utilizes skewed versions of an input frame wherein each skewed frame is processed independently using fuzzy reasoning. MFR achieves optimal edge detection using the wavelet decomposition followed by a novel fuzzy based decision technique. The processed frames are de-skewed and combined using a fuzzy union operation to extract the objects.
Original languageEnglish
Pages (from-to)77-81
Number of pages5
JournalPattern Recognition Letters
Issue number1
Publication statusPublished - Jan 2005


  • automatic object extraction
  • fuzzy reasoning
  • multiscale edge detection


Dive into the research topics of 'Multiscale fuzzy reasoning (MFR) for automatic object extraction'. Together they form a unique fingerprint.

Cite this