Face colour synthesis using partial least squares and the luminance-α-β colour transform

Author(s): J. Miranda-Hernández ; M. Castelán ; L.A. Torres-Méndez
DOI: 10.1049/iet-cvi.2011.0168

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): J. Miranda-Hernández ¹ ; M. Castelán ¹ ; L.A. Torres-Méndez ¹
- Affiliations: 1: Robotics and Advanced Manufacturing Group, Centro de Investigación y Estudios Avanzados del I.P.N., Coahuila, Mexico
Source: Volume 6, Issue 4, July 2012, p. 263 – 272
DOI: 10.1049/iet-cvi.2011.0168 , Print ISSN 1751-9632, Online ISSN 1751-9640

For many tasks, it is necessary to synthesise realistic colour in faces from greyscale values. This is the problem the authors address in this study. Rather than propagating colour information in some regions of the image or transferring colour from an image source to a greyscale using some corresponding criterion, as many colouring systems attempt to do, they seek to synthesise facial colour information using a database of examples. This methodology is divided into two main stages. In the first stage the facial skin tone is predicted through the multiple linear regression method known as partial least squares. This regression allows to define a linear transformation between facial greyscale and colour subspaces. The second stage involves the luminance-α-β (Lαβ) colour transform which is responsible for the recovery of the fine facial detail. The core of the proposed methodology is the combination of statistical subspace analysis with the appropriate colour transform so as to produce realistic facial colourisation results in a direct manner.

References

1. 1)
  - T. Sim , S. Barker , M. Bsat . The CMU Pose, Illumination, and Expression Database. IEEE Trans. Pattern Anal. Mach. Intell. , 12 , 1615 - 1618
2. 2)
  - Horiuchi, T.: `Estimation of color for gray level image by probabilistic relaxation', Proc. IEEE Int. Conf. on Pattern Recognition, 2002, p. 867–870.
3. 3)
  - S.K. Shevell . (2003) The science of color.
4. 4)
  - E. Reinhard , M. Ashikhmin , B. Gooch , P. Shirley . Colour transfer between images. IEEE Comput. Graph. Appl. , 5 , 34 - 41
5. 5)
  - A. Levin , D. Lischinski , Y. Weiss . Colourisation using optimization. ACM Trans. Graph. , 3 , 689 - 694
6. 6)
  - G. Wyszecki , W.S. Stiles . (1982) Color science: concepts and methods, quantitative data and formulae.
7. 7)
  - D.L. Ruderman , T.W. Cronin , C.C. Chiao . Statistics of coneresponses to natural images: implications for visual coding. J. Opt. Soc. Am. , 8 , 2036 - 2045
8. 8)
  - L. Vieira , E. do Nascimento , F. Fernandes , R. Carceroni , R. Vilela , A. Araújo . Fully automatic coloring of greyscale images. Image Vis. Comput. , 1 , 50 - 60
9. 9)
  - R. Jenkins , D. White , X. Van Montfort , M. Burton . Variability in photos of the same face. Cognition , 313 - 323
10. 10)
  - Torres-Mendez, L.A., Dudek, G.: `Color correction of underwater images for aquatic robot inspection', Proc. Int. Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, 2005, 3757, p. 60–73.
11. 11)
  - Castelán, M., Puerto-Souza, G.A., Van Horebeek, J.: `Using subspace multiple linear regression for 3D face shape prediction from a a single image', Proc. Int. Symp. on Visual Computing, 2009, p. 662–663.
12. 12)
  - J. Koenderink . The structure of images. Biol. Cybern. , 363 - 370
13. 13)
  - H. Wold . (1985) Partial least squares.
14. 14)
  - M. Castelán , J. Van Horebeek . Relating intensities with three-dimensional facial shapeusing partial least squares. IET Comput. Vis. , 2 , 60 - 73
15. 15)
  - Qiu, G., Guan, J.: `Color by linear neighborhood embedding', IEEE Int. Conf. on Image Processing, 2005, 11, p. 988–991, No. 14.
16. 16)
  - L. Qing , F. Wen , D. Cohen-Or , L. Liang , Y.Q. Xu , H. Shum . (2007) Natural image colorization.
17. 17)
  - D. Blasi , R. Recupero . (2003) Fast colorization of gray images.
18. 18)
  - C.M. Wang , Y.H. Huang . A novel color transfer algorithm for image sequences. J. Inf. Sci. Eng. , 1039 - 1056
19. 19)
  - Schwartz, K., Harwood, D.: `Human detection using partial least squares analysis', Proc. Int. Conf. on Computer Vision, 2009.
20. 20)
  - T. Welsh , M. Ashikhmin , k. Mueller . Transferring color to grayscale images. ACM Trans. Graph. , 3 , 277 - 280
21. 21)
  - E.H. Land . The Retinex theory of color vision. Sci. Am. , 6 , 108 - 128
22. 22)
  - L. Yatziv , G. Sapiro . Fast image and video colourisation using chrominance blending. IEEE Trans. Image Process. , 5 , 1120 - 1129
23. 23)
  - Chen, T., Wang, Y., Schillings, V., Meinel, C.: `Grayscale image matting and colorization', Proc. ACCV2004, 2004, 27, p. 1164–1169, No. 30.
24. 24)
  - Levin, A., Rav-Acha, A., Lischinski, D.: `Spectral matting', IEEE Conf. on Computer Vision and Pattern Recognition, 2007.
25. 25)
  - Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: `Image analogies', Proc. ACM SIGGRAPH, 2001, p. 327–340.

Face colour synthesis using partial least squares and the luminance-α-β colour transform

Face colour synthesis using partial least squares and the luminance-α-β colour transform

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content