3D Face Recognition using Local Depth Information

  • Published : 2002.12.01

Abstract

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

얼굴의 깊이 정보는 얼굴 인식에서 가장 중요한 요소이다. 3차원 얼굴 영상은 깊이 정보를 잘 나타내므로 얼굴의 깊이 값을 비교하는데 아주 유용하다. 얼굴 전체에 대한 처리는 많은 계산량과 데이터 량을 포함해야 하는 문제점이 있다. 따라서 본 논문에서는 얼굴의 국부적인 영역들에 대한 3차원 깊이 값을 이용하여 인식하였다. 3D 레이저 스캐너로 입력된 3차원 얼굴 영상으로부터 어떤 깊이에 있는 등고선 영역을 추출한 후, 이를 영역별로 취하면 국부적인 얼굴 깊이에 대한 특징을 잘 반영하게 된다. 얼굴의 가장 중심인 코를 기준점으로 깊이 영역에 대한 등고선 영역을 추출하며, 얼굴의 깊이를 고려한 국부적 깊이 정보를 다중 특징 벡터를 이용하여 얼굴을 인식한다. 다중 특징 벡터는 벡터 수가 적으면서 얼굴의 지역적 깊이 특성을 잘 나타내므로 간단한 방법으로 높은 인식률을 얻을 수 있었다.

Keywords

References

  1. L. C. Jain, U. Halici, I. Hayashi, S. B. Lee, Intelligent biometric techniques in fingerprint and face recognition, CRC Press, 1999
  2. (주)포디컬쳐, 'http://www.4dculture.com'
  3. Cyberware, 'http://www.cyberware.com'
  4. P. L. Hallinan, G. G. Gordon. A. L. Yuille. P. Giblin, D. Mumford, Two and three dimensional pattern of the face, A K Peters. Ltd., 1999
  5. M. Grob, Visual computing, Springer_Verlag, 1994
  6. A. Nikolaidis, I. Pitas, 'Facial feature extration and pose determination,' Pattern Recognition, 1783-1791, 33(2000) https://doi.org/10.1016/S0031-3203(99)00176-4
  7. B. Moghaddam, T. Jebara, A. Pentland 'Bayesian face recognition,' Pattern Recognition, 1771-1782, 33(2000) https://doi.org/10.1016/S0031-3203(99)00179-X
  8. C. S. Chua, F. Han, Y. K. Ho, '3D Human Face Recognition Using Point Signature,' 4th ICAFGR, 2000 https://doi.org/10.1109/AFGR.2000.840640
  9. G. G. Gordon, 'Face Recognition based on depth and curvature feature,' Preceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 808-810, 1992 https://doi.org/10.1109/CVPR.1992.223253
  10. R. Chellapa, C. L. Wilson, and S.Sirohey 'Human and machine recognition of faces : A survey,' Preceeding of the IEEE, 83(5): pp.705-740, May 1995 https://doi.org/10.1109/5.381842
  11. H. T. Tanaka, M. Ikeda and Hchiaki, 'Curvature-based face surface recognition using spherial correlation,' Third IEEE International Conference on Automatic Face and Gesture Recognition, pp.372-377, 1998 https://doi.org/10.1109/AFGR.1998.670977
  12. J. C. Lee and E. Milios. 'Matching range image of human faces,' Third International Conference on Computer Vision, pp.722-726, 1990 https://doi.org/10.1109/ICCV.1990.139627
  13. J. R. Parker, Algorithm for Image Processing and Computer Vision, Wiley Computer Publishing McGraw-Hill 1996
  14. Barnabas Takacs, Harry Wechsler, 'Face Recognition Using Binary Image Metrics', Proc. of the 3rd Int. Conf. on Automatic Face and Recognition, Nara, Japan, pp.294-299, April 1998
  15. O. Nakamura, S. Mathur, and T. Minami, 'Identification of human faces based on isodensity maps', Pattern Recognition, Vol. 24, pp.263-272, 1991 https://doi.org/10.1016/0031-3203(91)90068-G