Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Face Tracking and Recognition in Video with PCA-based Pose-Classification and (2D)2PCA recognition algorithm

비디오속의 얼굴추적 및 PCA기반 얼굴포즈분류와 (2D)2PCA를 이용한 얼굴인식

  • Kim, Jin-Yul (Dept. of Electronic Engineering, University of Suwo) ;
  • Kim, Yong-Seok (Dept. of Electronic Engineering, University of Suwo)
  • 김진율 (수원대학교 전자공학과) ;
  • 김용석 (수원대학교 전자공학과)
  • Received : 2013.06.28
  • Accepted : 2013.10.16
  • Published : 2013.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

In typical face recognition systems, the frontal view of face is preferred to reduce the complexity of the recognition. Thus individuals may be required to stare into the camera, or the camera should be located so that the frontal images are acquired easily. However these constraints severely restrict the adoption of face recognition to wide applications. To alleviate this problem, in this paper, we address the problem of tracking and recognizing faces in video captured with no environmental control. The face tracker extracts a sequence of the angle/size normalized face images using IVT (Incremental Visual Tracking) algorithm that is known to be robust to changes in appearance. Since no constraints have been imposed between the face direction and the video camera, there will be various poses in face images. Thus the pose is identified using a PCA (Principal Component Analysis)-based pose classifier, and only the pose-matched face images are used to identify person against the pre-built face DB with 5-poses. For face recognition, PCA, (2D)PCA, and $(2D)^2PCA$ algorithms have been tested to compute the recognition rate and the execution time.

통상의 얼굴인식은 사람이 똑바로 카메라를 응시해야 하거나, 혹은 이동하는 통로의 정면과 같이 특정 얼굴포즈를 취득할 수 있는 위치에 카메라를 설치하는 등 통제적인 환경에서 이루어진다. 이러한 제약은 사람에게 불편을 초래하고 얼굴인식의 적용 범위를 제한하는 문제가 있다. 본 논문은 이러한 기존방식의 한계를 극복하기 위하여 대상이 특별한 제약 없이 자유롭게 움직이더라도 동영상 내에서 대상의 얼굴을 추적하고 얼굴인식을 하는 방법을 제안한다. 먼저 동영상 속의 얼굴은 IVT(Incremental Visual Tracking) 추적기를 사용하여 지속적으로 추적이 되며 이때 얼굴의 크기변화와 기울기가 보상이 되어 추출이 된다. 추출된 얼굴영상은 사람과 카메라의 각도를 특정각도로 제한하지 않았으므로 다양한 포즈를 가지게 되며 따라서 얼굴인식을 하기 위해서 포즈에 대한 판정이 선행되어야 한다. 본 논문에서는 PCA(Principal Component Analysis)기반의 얼굴포즈판정방법을 사용하여 추적기에서 추출된 이미지가 5개 포즈별 DB속의 학습된 포즈와 유사한 것으로 판정될 때만 얼굴인식을 수행하여 인식률을 높이는 방법을 제안하였다. 얼굴인식에서는 PCA, 2DPCA, $(2D)^2PCA$의 인식알고리즘을 사용하여 얼굴인식률과 수행시간을 비교 제시하였다.

Keywords

References

  1. H. K. Ekenel, J. Stallkamp, and R. Stiefelhagen, "A video-based door monitoring system using local appearance-based face models," Computer Vision and Image Understanding, Vol. 114, Issue 5, pp. 596-608, 2010. https://doi.org/10.1016/j.cviu.2009.06.009
  2. M. Kass, "Snake: Active contour model," International Journal of Computer Vision, Vol.1 pp. 312-331, 1988.
  3. D. Comaniciu, V. Ramesh, "Mean-shift and opimal prediction for efficient object tracking," International Conference on Image Processing, pp 70-73, 2000.
  4. K. Nummiaro, E. Koller-Meier and L.van Gool, "A color-based particle filter," First International Workshop on Generative Model Based Vision, pp. 53-60, June 2002.
  5. D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. "Incremental learning for robust visual tracking," IJCV, 2007.
  6. M. A. Turk, A. P. Pentland, "Face recognition using eigenface," Proc. Computer Vision and Pattern Recognition, pp 586 - 591, 1991.
  7. S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K. R. Mullers, "Fisher discriminant analysis with kernels," Neural Networks for Signal Processing IX, Proceedings of the IEEE Signal Processing Society Workshop, pp. 41-48. 1999.
  8. D. Anguita, S. Ridella, F. Rivieccio, R. Zunino, "Hyperparameter design criteria for support vector classifiers," Neurocomputing, Volume 55, Issues 1-2, Sep. 2003, pp. 109-134. https://doi.org/10.1016/S0925-2312(03)00430-2
  9. Z. Daoqiang, Z. Zhi-Hua, "Two-directional two-dimensional PCA for efficient face representation and recognition," Neurocomputing, Vol 69, Issues 1-3, December 2005, Pages 224-231. https://doi.org/10.1016/j.neucom.2005.06.004
  10. E. Murphy-Chutorian, "Head Pose Estimation in Computer Vision: A Survey," Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 31, pp 607-626, 2009. https://doi.org/10.1109/TPAMI.2008.106
  11. Y.-O. Kim, "A new 3D active camera system for robust face recognition by correcting pose variation," ICCAS 2004, pp. 1485-1490.
  12. S. Srinivasan, "Head pose estimation using view based eigenspaces," Proc. 16th International Conference on Pattern Recognition 2002, Vol. 4, 302-305, 2002.
  13. A. Levey, and M. Lindenbaum, "Sequential Karhunen-Loeve basis extraction and its application to images," Image Processing, IEEE Transactions on, Vol. 9, Issue 8, 1371-1374, Aug 2000. https://doi.org/10.1109/83.855432
  14. B. Moghaddam, and A. Pentland, "Probabilistic visual learning for object detection," Proc. IEEE International Conference on Computer Vision, pp. 786-793, 1995.
  15. Q. Zhao, B. Liang, and F. Duan, "Combination of Improved PCA and LDA for Video-based Face Recognition." Journal of Computational Information Systems, 9.1, pp. 273-280, 2013.
  16. G. Aggarwal, A. K. R. Chowdhury, and R. Chellappa, "A system identification approach for video-based face recognition," 17th International Conference on Pattern Recognition, ICPR 2004, Vol. 4. IEEE, 2004.
  17. X. Liu and T. Chen, " Video-based face recognition using adaptive hidden markov models," Proc. Computer Vision and Pattern Recognition, 2003, Vol. 1, pp. I-340.
  18. R. Wang, S. Shan, X. Chen, and W. Gao, "Manifold-manifold distance with application to face recognition based on image set," Proc. Computer Vision and Pattern Recognition, 2008, pp. 1-8.
  19. U. Park, H. Chen, and A. K. Jain, "3D model-assisted face recognition in video," Proc. Computer and Robot Vision, 2005, pp. 322-329.
  20. Honda UCSD Video Database, Available: http://vision.ucsd.edu/content/honda-ucsd-video-database, 2005, [Accessed: Oct 22, 2013]

Cited by

  1. Face Classification Using Cascade Facial Detection and Convolutional Neural Network vol.26, pp.1, 2016, https://doi.org/10.5391/JKIIS.2016.26.1.070