대한의용생체공학회:학술대회논문집 (Proceedings of the KOSOMBE Conference)

대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지

주변 평균 밝기차를 이용한 초음파 영상의 에지 검출

Edge Detection of Ultrasonic Image Using Neighhood Mean Intensity Difference

  • 원철호 (경북대학교 공과대학 전자공학과) ;
  • 구성모 (경북대학교 공과대학 전자공학과) ;
  • 김명남 (경북대학교 공과대학 전자공학과) ;
  • 조진호 (경북대학교 전자공학과 및 경북대학교병원 의공학과)
  • Won, Chul-Ho (Dept. of Electronics, Kyungpook National University) ;
  • Koo, Sung-Mo (Dept. of Electronics, Kyungpook National University) ;
  • Kim, Myoung-Nam (Dept. of Electronics, Kyungpook National University) ;
  • Cho, Jin-Ho (Dept. of Electronics, Kyungpook National University, Dept. of Biomedical Eng., Kyungpook University Hospital)
  • 발행 : 1994.05.13
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A new algorithm using a measure for edge detection from ultrasonic image is proposed. Ultrasonic image is blurred by pre-processing for removing speckle noises and precise edge placement is not clear. Because extracted edge from blurred image is thick, a measure utilizing the absolute difference of mean between two windows is used to thin the thickness of extracted edge in blurred image. The algorithm is effective to process blurred image due to the noise filtering that remove speckle noises. Results of the proposed algorithm using a measure show good edge detection performance comparing with other gradient edge operators.

키워드