단계형 구조를 이용한 실시간 얼굴 탐지 시스템

Rotation Invariant Real-time Face Detection Using Cascade Structure In Color Images

  • 김승구 (고려대학교 공과대학 전자컴퓨터공학과) ;
  • 김혜수 (고려대학교 공과대학 전자컴퓨터공학과) ;
  • 고성제 (고려대학교 공과대학 전자컴퓨터공학과)
  • Kim, Seung-Goo (Department of Electric and Computer Engineering Korea University) ;
  • Kim, Hye-Soo (Department of Electric and Computer Engineering Korea University) ;
  • Ko, Sung-Jea (Department of Electric and Computer Engineering Korea University)
  • 발행 : 2007.07.11

초록

Face detection plays an important role in HCI and face recognition. In this paper, we propose a rotation-invariant real-time face detection algorithm for color images in complex background. It consists of four processing step: (1) motion detection, (2) skin color region filler, (3) Eyemap detector for rotated face, and (4) Adaboost face classifier. This system has been tested in in-door environments, such as office and achieves over 95% detection rate.

키워드