원통 모델과 스테레오 카메라를 이용한 포즈 변화에 강인한 얼굴인식

Pose-invariant Face Recognition using a Cylindrical Model and Stereo Camera

  • 발행 : 2004.07.01

초록

본 논문에서는 원통모델과 스테레오 카메라를 이용하여 대상의 포즈 변화에 강인한 얼굴인식 방법을 제안한다. 입력으로 하나의 영상을 취할 수 있는 경우와 스테레오 영상을 취할 수 있는 경우의 두 가지로 나누어 다룬다. 단일 입력 영상인 경우 정면이 아닌 입력 영상에 대하여 원통 모델을 이용하여 좌우방향(yaw)으로 포즈를 보상하고, 스테레오 입력 영상인 경우 스테레오 기하학을 이용하여 예측된 상하방향(pitch) 포즈로 대상의 상하 변화까지 보상한다. 또한 스테레오 카메라를 통하여 동시에 두 개의 영상을 얻는다는 장점이 있기 때문에 결정 단계 융합(decision-level fusion) 방법을 이용하여 전체적인 인식률을 향상시킨다. 실험 결과, 좌우 포즈 변환을 통하여 인식률이 61.43%에서 94.76%로 향상되었음을 볼 수 있었고, 보다 복잡한 3차원 얼굴 모델과의 비교 결과 인식률이 양호함을 확인할 수 있었다. 또한 스테레오 카메라 시스템을 이용하여 얼굴이 위로 향한 영상일 경우 5.24%의 인식률을 향상시켰고, 결정 단계융합에 의해 추가로 3.34%의 인식률을 향상시킬 수 있었다.

This paper proposes a pose-invariant face recognition method using cylindrical model and stereo camera. We divided this paper into two parts. One is single input image case, the other is stereo input image case. In single input image case, we normalized a face's yaw pose using cylindrical model, and in stereo input image case, we normalized a face's pitch pose using cylindrical model with previously estimated pitch pose angle by the stereo geometry. Also, since we have an advantage that we can utilize two images acquired at the same time, we can increase overall recognition performance by decision-level fusion. Through representative experiments, we achieved an increased recognition rate from 61.43% to 94.76% by the yaw pose transform, and the recognition rate with the proposed method achieves as good as that of the more complicated 3D face model. Also, by using stereo camera system we achieved an increased recognition rate 5.24% more for the case of upper face pose, and 3.34% more by decision-level fusion.

키워드

참고문헌

  1. D. J. Beymer, 'Face recognition under varying pose,' in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 556-761, Seattle, Washington, June 1994 https://doi.org/10.1109/CVPR.1994.323893
  2. A. Pentland, B. Moghanddam, and T. Starner, 'View-based and modular eigenspaces for face recognition,' in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 84-91, Seattle, Washington, June 1994 https://doi.org/10.1109/CVPR.1994.323814
  3. F. J. Huang, Z. Zhou, H. Zhang, and T. Chen, 'Pose invariant face recognition,' in Proc. of IEEE Conf. on Automatic Face and Gesture Recognition, pp. 245-250, Grenoble, France, 2000 https://doi.org/10.1109/AFGR.2000.840642
  4. T. S. Jebara, '3D Pose estimation and normalization for face recognition,' McGill University, 1996
  5. S. Akamatsu, T. Sasaki, H. Fukumachi, and Y. Suenaga, 'A robust face identification scheme KL expansion of an invariant feature space,' SP1E Proc., vol. 1607, pp. 71-84, Nov 1991 https://doi.org/10.1117/12.57048
  6. D. Graham and N. Allinson, 'Face recognition from unfamiliar views: Subspace methods and pose dependency,' in Proc. of IEEE Conf. on Automatic Face and Gesture Recognition, pp. 348-353, Nara, Japan, April 1998 https://doi.org/10.1109/AFGR.1998.670973
  7. M. Kirby and L. Sirovich, 'Application of the karhunen-loeve procedure for the characterization of human faces,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, Jan 1990 https://doi.org/10.1109/34.41390
  8. M. Turk and A. Pentland, 'Eigenfaces for recognition,' Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991 https://doi.org/10.1162/jocn.1991.3.1.71
  9. M. H. Yang, D. Kriegman, and N. Ahuja, 'Detecting Faces in Images: A Survey,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, Jan 2002 https://doi.org/10.1109/34.982883
  10. T. Horprasert, Y. Yacoob, and L. Davis, 'Computing 3-D head orientation from a monocular image sequence,' in Proc. of IEEE Conf. on Automatic Face and Gesture Recognition, pp. 242-247, Killington, VT, Oct 1996 https://doi.org/10.1109/AFGR.1996.557271
  11. C. G. Feng, P. C. Yuen, and D. Q. Dai, 'A novel method for face orientation determination in human face recognition,' in Proc. of The Fourth Joint Conf. on Information Science, pp. 295-298, 1998
  12. M. Xu and T. Akatsuka, 'Detecting head pose from stereo image sequence for active face recognition,' in Proc. of IEEE Conf. on Automatic Face and Gesture Recognition, pp, 82-87, Nara, Japan, April 1998 https://doi.org/10.1109/AFGR.1998.670929
  13. R. Hartley and A. Zisserman, Multiple View Geometry in computer vision, Cambridge University Press, 2000