Rotation Invariant Face Detection using Haar-like Feature Variation

Haar-like Feature 변형을 이용한 기울어진 얼굴 검출

  • Kim, Seok-Ho (School of Electric and Information and Control Engineering Hongik University) ;
  • Kim, Jae-Min (School of Electric and Information and Control Engineering Hongik University) ;
  • Cho, Seoung-Won (School of Electric and Information and Control Engineering Hongik University) ;
  • Lee, Gi-Seong (School of Electric and Information and Control Engineering Hongik University) ;
  • Chung, Sun-Tae (School of Electronic Engineering Soongsil University)
  • 김석호 (홍익대학교 전기정보제어공학과) ;
  • 김재민 (홍익대학교 전기정보제어공학과) ;
  • 조성원 (홍익대학교 전기정보제어공학과) ;
  • 이기성 (홍익대학교 전기정보제어공학과) ;
  • 정선태 (숭실대학교 정보통신전자공학부)
  • Published : 2008.06.18

Abstract

In this paper, we propose a rotation invariant face detection method using Haar-like feature variation. Previous approaches using rectangular features can be calculated very fast. But rectangular features is weak in rotated face. Rotated Haar-like features can get high accuracy, but the performance is slow because it can't use the integral image. Our method vary Haar-like features keeping rectangular. this method makes the performance a bit slow, but gives better accuracy.

Keywords