대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

조명영향 분리 얼굴 고유특성 텍스쳐 부분공간 기반 얼굴 이미지 조명 정규화

Face Illumination Normalization based on Illumination-Separated Face Identity Texture Subspace

  • 최종근 (숭실대학교 정보통신 전자공학부) ;
  • 정선태 (숭실대학교 정보통신 전자공학부) ;
  • 조성원 (홍익대학교 전자전기공학부)
  • Choi, Jong-Keun (School of Electronic Engineering, Soongsil University) ;
  • Chung, Sun-Tae (School of Electronic Engineering, Soongsil University) ;
  • Cho, Seong-Won (Department of Electronic and Electrical Engineering, Hongik University)
  • 발행 : 2010.01.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

다양한 조명 환경에서 강인한 얼굴 인식 성취는 어렵다. 조명에 강인한 얼굴 인식을 위해서 보통 전처리 단계로 얼굴 이미지 조명 정규화를 수행한다. 기존 조명 전처리 기법들은 투영 음영을 효과적으로 처리할 수 없다. 본 논문에서는 조명 영향 분리 얼굴 고유특성 텍스쳐 부분공간에 기반한 새로운 얼굴 조명 정규화 기법을 제안한다. 조명분리 얼굴 고유특성 텍스쳐 부분 공간은 얼굴 텍스쳐 공간에서 조명 변화 영향이 분리된 부분공간으로 구축되기 때문에 얼굴 이미지를 이 부분공간으로 투영하여 얻은 얼굴 이미지는 조명 변화 영향이 최소화된 좋은 조명 정규화를 달성한다. 실험을 통해 본 논문에서 제안한 얼굴 조명정규화 기법이 표면 음영뿐만 아니라 투영 음영도 효과적으로 제거할 수 있으며, 좋은 얼굴 조명 정규화를 달성한다는 것을 확인하였다.

Robust face recognition under various illumination environments is difficult to achieve. For robust face recognition with respect to illumination variations, illumination normalization of face images is usually applied as a preprocessing step. Most of previously proposed illumination normalization methods cannot handle cast shadows in face images effectively. In this paper, We propose a new face illumination normalization method based on the illumination-separated face identity texture subspace. Since the face identity texture subspace is constructed so as to be separated from the effects of illumination variations, the projection of face images into the subspace produces a good illumination-normalized face images. Through experiments, it is shown that the proposed face illumination normalization method can effectively eliminate cast shadows as well as attached shadows and achieves a good face illumination normalization.

키워드

참고문헌

  1. S. Z. Li and A. K. Jain, "Handbook of Face Recognition," 2004.
  2. E. H. Land and J. J. McCann, "Lightness and retinex theory," Journal of the Optical Society of America, pp. 61:1-11, 1971. https://doi.org/10.1364/JOSA.61.000001
  3. R. Gross and V. Brajovic, "An image preprocessing algorithm for illumination invariant face recognition," In Audio-and Video-Based Biometric Person Authentication, Vol. 2688, pp. 10-18, June 2003. https://doi.org/10.1007/3-540-44887-X_2
  4. P. N. Belhumeur and D. J. Kriegman, "What is the set of images of an object under all possible lighting conditions?," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'96), pp. 270-280, 1996.
  5. R. Epstein, P. Hallinan, and A. Yuille, "5+/-2 eigenimages suffice: An empirical investigation of low-dimensional lighting models," Proc. Workshop Physics-Based Modeling in Computer Vision, 1995.
  6. R. Basri and D.W. Jacobs, "Lambertian reflec -tances and linear subspaces," IEEE Int. Conf. on Computer Vision, pp. 383–390, 2001.
  7. F. Kahraman and et al., "An Active Illumination and Appearance (AIA) Model for Face Alignment," Proc. of the CVPR 2007, IEEE Computer Society Workshop on Biometrics, 2007.
  8. B. Horn, "Robot Vision," MIT Press, 1986.
  9. I. T. Jollie, "Principal Component Analysis," Springer - Verlag, New York, 1986.
  10. J. C. Gower, "Generalized Procrustes analysis," Psychometrika, Vol. 40, pp. 33-51, 1975. https://doi.org/10.1007/BF02291478
  11. M. Turk and A. Pentland, "Eigenfaces for recognition," Journal of Cognitive Neuroscience 3 (1), pp. 71–86, 1991. https://doi.org/10.1162/jocn.1991.3.1.71
  12. D.T. Lee, and B. J. Schachter, "Two Algorithms for Constructing a Delaunay Triangulation," Int. J. Computer Information Sci. Vol. 9, pp. 219-242, 1980. https://doi.org/10.1007/BF00977785
  13. T. F. Cootes, D. J. Edwards, and S. J. Taylor, "Active Appearance Models," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 23, no. 6, pp. 681–685, Jun. 2001. https://doi.org/10.1109/34.927467
  14. CMU PIE Face database, http://www.ri.cmu.edu/research_project_detail.html?project_id=418&menu_id=261