퍼지 클러스터링 방법을 이용한 흉부 혈관의 검출에 관한 연구

  • 황준현 (서울대학교 의과대학 의공학교실) ;
  • 박광석 (서울대학교 의과대학 의공학교실) ;
  • 민병구 (서울대학교 의과대학 의공학교실)
  • Published : 1991.06.01

Abstract

A new algorithm is proposed for the automatic detection of pulmonary blood vessels by simulating the human recognition process by the pyramid images. Large and wide vessels are detected from the most compressed level, followed by the detection of small and narrow ones from the less compressed images with FCM(fuzzy c means). As the proposed algorithm detects blood vessels orderly according to their size, there is no need to consdier the variation of parameters and the brance points which should be considered in other detection algorithms.

Keywords