DOI QR코드

DOI QR Code

Robust Face and Facial Feature Tracking in Image Sequences

연속 영상에서 강인한 얼굴 및 얼굴 특징 추적

  • 장경식 (동의대학교 멀티미디어공학과) ;
  • 이찬희 (동의대학교 디지털미디어공학과)
  • Received : 2010.05.13
  • Accepted : 2010.06.30
  • Published : 2010.09.30

Abstract

AAM(Active Appearance Model) is one of the most effective ways to detect deformable 2D objects and is a kind of mathematical optimization methods. The cost function is a convex function because it is a least-square function, but the search space is not convex space so it is not guaranteed that a local minimum is the optimal solution. That is, if the initial value does not depart from around the global minimum, it converges to a local minimum, so it is difficult to detect face contour correctly. In this study, an AAM-based face tracking algorithm is proposed, which is robust to various lighting conditions and backgrounds. Eye detection is performed using SIFT and Genetic algorithm, the information of eye are used for AAM's initial matching information. Through experiments, it is verified that the proposed AAM-based face tracking method is more robust with respect to pose and background of face than the conventional basic AAM-based face tracking method.

AAM(Active Appearance Model)은 변형 가능한 형태의 검출에 가장 효과 적인 방법의 하나이며, 수학적으로 최적화 문제이다. 비용함수는 최소자승 함수이어서 볼록 함수이나, 탐색 공간이 볼록공간이 아니므로 국소 최소값이 전역 최소값인 것으로 보장 되지 않는다. 즉 초기값이 전역 최소값 근방에서 출발하지 않으면, 지역 최소값에 수렴하여 정확한 얼굴 윤곽 검출이 어려워진다. 본 논문에서는 연속적인 입력영상에 SIFT(Scale Invariant Feature Transform)와 유전자 알고리즘을 사용하여 눈동자를 검출하고 AAM 모델의 초기화 정보로 사용함으로써 조명과 배경에 강인한 AAM 기반의 얼굴 정합 방법을 제안한다. 실험을 통하여 제안한 AAM 기반 얼굴 정합 방법이 자세, 얼굴 배경 등에 대해 기존의 AAM 기반 얼굴 정합 방법보다 더 강인한 것으로 확인 되었다.

Keywords

References

  1. Wang Chuan-xu, Li Zuo-yong, "A New Face Tracking Algorithm Based on Local Binary Pattern and Skin Color Information", ISCSCT '08, pp.657-660, Dec. 2008
  2. Xun Xu, Changshui Zhang, Huang, T.S, "Active Morphable Model; an efficient method for face analysis", IEEE Int. Conf. on Automatic Face and Gesture Recognition, pp.837-842, May, 2004.
  3. M. Yang, D. J. Kriegman, and N. Ahuja, "Detecting Faces in Images: A Servey," IEEE Trans. on PAMI, Vol. 24, No. 1, pp. 34-58. Jan. 2002 https://doi.org/10.1109/34.982883
  4. D. Cristinancce, T. Cootes, and I. Scott, "A Multi-Stage Approach to Facial Feature Detection," Proc. British Machine Vision Conference, Vol.1, pp.277-286, 2004.
  5. S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge University Press, March 2004.
  6. Hyoung-Joon Kim, Whoi-Yul Kim, "Eye Detection in Facial Images Using Zernike Moments with SVM, ETRI Journal-Vol. 30, no. 2, 2008.
  7. A.L. Yuille, P.W. Hallinan, D.S. Cohen, "Feature extraction from faces using deformable templates", Int. J. Comput. Vision 8, pp99-111, 1992. https://doi.org/10.1007/BF00127169
  8. A. Pentland, B. Moghaddam, and Thad Starner, "View-based and modular eigenspaces for face recongnition", In Proceedings of IEEE Conf. on Computer Vision and Pattern Recongnition, pp.84-91, 1994
  9. T. Akashi, Y. Wakasa, K. Tanaka, S. G. Karungaru, and M. Fukumi, "Genetic eye detection using artificial template," Journal of Signal Processing, vol. 10, no. 6, pp. 453-463, November 2006.
  10. Scovanner Paul, Ali S, Shah M, "A 3 dimensional sift descriptor and its application to action recognition", Int. Conf. on Multimedia. pp.357-360, 2007.
  11. M. B. Stegmann, B. K. Ersboll, R. Larsen, "FAME - A Flexible Appearance Modleling Enviroment," IEEE Trans. on Medical Imaging, Vol. 22, pp.1319-1331, Oct, 2003. https://doi.org/10.1109/TMI.2003.817780
  12. H. Je, S. Kim, B. Jun, D. Kim, H. Kim, J. Sung, and S. Bang, "Asian Face Image Database PF01," Database, Intelligent Multimedia Lab, Dept. of CSE, POSTECH, 2001.

Cited by

  1. 눈동자를 이용한 사용자 인증기법 vol.14, pp.9, 2016, https://doi.org/10.14400/jdc.2016.14.9.325