Extraction of face region and features based on chromatic properties of human faces

  • Tae-Woong Yoo
  • Il-Seok Oh
Pattern Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1114)


This paper presents a methodology to detect face region and some features, i.e., eyes and mouth, from color frontal face images as follows. Firstly we scissor face regions from many color face images and construct a face chromatic histogram in hue and saturation chromatic space. Secondly we use both the face symmetry information and chromatic histogram to detect the face region from the input image. Thirdly the locations of the eyes and mouth on the face region are determined by both detecting the intensity valley regions and using the positional relations of eyes and mouth in the face region. To support the methodology, this paper presents an implementation of the methodology. The results of the implementation show a high success rate.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    R. Brunelli and T. Poggio, “Face recognition: features versus templates,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 15, No. 10, 1993, pp. 1042–1052.Google Scholar
  2. [2]
    G. Chow and X. Li, “Towards a system for automatic facial feature detection,” Pattern Recognition, Vol. 26, N0. 12, pp. 1739–1775.Google Scholar
  3. [3]
    G. Gordon, “Face recognition based on depth maps and surface curvature,” SPIE Geometric Methods in Computer Vision, Vol. 1570, 1991, pp. 234–246.Google Scholar
  4. [4]
    T. C. Chang, T. S. Huang and C. Novak, “Facial feature extraction from color Images,” Proceeding of 12th International Conference on Pattern Recognition, Vol. 2, 1994, pp. 39–43.Google Scholar
  5. [5]
    Y. H. Kwon and N. V. Lobo, “Face detection using templates,” 12th IAPR: International Conference on Pattern Recognition, Vol. 1, 1994, pp. 764–767.Google Scholar
  6. [6]
    C. L. Huang and C. W. Chen, “Human facial feature extraction for face interpretation and recognition,” ICPR'92, 1992, pp. 204–207.Google Scholar
  7. [7]
    B. Takacs and H. Wechsler, “Locating facial features using SOFM,” Proceeding of 12th International Conference on Pattern Recognition, Vol. 2, 1994, pp. 55–60.Google Scholar
  8. [8]
    X. Song, C. W. Lee, G. Xu and S. Tsuji, “Extracting facial features with partial feature template,” Asian Conference on Computer Vision '93, November, 1993, pp. 751–754.Google Scholar
  9. [9]
    J. K. Wu and A. D. Narasimhalu, “Identifying faces using multiple retrievals,” IEEE Multimedia, Summer, 1994, pp. 27–38.Google Scholar
  10. [10]
    S. W. Smoliar and H. Zhang, “Content-based video indexing and retrieval,” IEEE Multimedia, Vol. 1, No. 2, Summer 1994, pp. 62–72.Google Scholar
  11. [11]
    R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison Wesley, 1992.Google Scholar
  12. [12]
    Y. Gong and M. Sakauchi, “Detection of regions matching specified chromatic features,” Computer Vision and Image Understanding, Vol. 61, No. 2, 1995, pp. 263–269.Google Scholar
  13. [13]
    M. J. Swain and D. H. Ballard, “Color Indexing,” International Journal Computer Vision, Vol. 7, No. 1, 1991, pp. 11–32.Google Scholar
  14. [14]
    I. S. Oh, S. M Choi and T. W. Yoo, “Local comparison-based document image binarization preserving stroke connectivity,” Proceedings of Pacific Rim International Conference on Artificial Intelligence, Beijing, 1994, pp. 939–942.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Tae-Woong Yoo
    • 1
  • Il-Seok Oh
    • 1
  1. 1.Department of Computer ScienceChonbuk National UniversityChonbuk

Personalised recommendations