Automatic Hair Colorization and Relighting Using Chroma-ticity Distribution Matching

Volume 5, Issue 2, April 2020     |     PP. 20-45      |     PDF (1480 K)    |     Pub. Date: May 10, 2020
DOI:    195 Downloads     4212 Views  

Author(s)

Uri Lipowezky, Research and Development Department/Facetrom, Tel Aviv, Israel

Abstract
Human hair colorization, concerning given model hair image without changing neither hairstyle nor hair texture, is a challenging task. The principle problem making this task complicated is the difference in the texture and the illumination between a user and model images. The natural human hair consists of a mix of hair swatches. Each swatch has its chromaticity distribution, which, generally, is non-Gaussian. These swatches can be determined as color clusters in the hair image. In this case, the problem can be solved by matching between the user and the model hair swatches or color clusters. After this matching, the color transfer between the relevant model and user swatches is applied. Besides, the model’s hair should be compressed to a reasonable size to provide simultaneous representation for a variety of hair colors. The model’s hair colors are taken from the images of hair color packs usually available in decorative cosmetic stores. These images, however, are taken in standard illumination condition, so appropriate relighting should be applied to provide photorealistic user’s image. Experimental results with 530 different color models, and more than 20,000 users show that the proposed technique achieves high photorealistic perception and a reasonable compression ratio.

Keywords
Color measurement, Image color analysis, Chromaticity distribution, Probability distributions matching

Cite this paper
Uri Lipowezky, Automatic Hair Colorization and Relighting Using Chroma-ticity Distribution Matching , SCIREA Journal of Electrical Engineering. Volume 5, Issue 2, April 2020 | PP. 20-45.

References

[ 1 ] Badrinarayanan, V., A. Kendall, and Cipolla, R. (2016). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. arXiv:1511. 00561v3.
[ 2 ] G. R. Greenfield and D. H. House, “A palette-driven approach to image color transfer,” in Computational Aesthetics in Graphics, Visualization and Imaging, L. Neumann, M. Sbert., B. Gooch., and W. Purgathofer, Eds. Eurographics Association, Goslar, Germany, 2005, pp. 91-99.
[ 3 ] Hou, J.-y. , Chang, Y.-l. , Wang, J., and X.-x. Wei (2006). Robust Automatic White Balance Algorithm using Gray Color Points in Images. IEEE Trans. on Consumer Electronics, 52(2): 541-546.
[ 4 ] Huang, H.-Z., S.-H. Zhang, R. R. Martin, and S.-M. Hu (2014). Learning Natural Colors for Image Recoloring. Pacific Graphics, 33 (7): 299–308.
[ 5 ] Kawakami, R., Zhao H., Tan R. T., and K. Ikeutchi (2013). Camera Spectral Sensitivity and White Balance Estimation from Sky Image. International Journal of Computer Vision, 105: 187-205.
[ 6 ] Kuhn, H. W. (1957) The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2: 83–97.
[ 7 ] Levin, A., Lischinski, D., and Y. Weiss (2008). A Closed-Form Solution to Natural Image Matting. IEEE Trans. Pattern Analysis and Machine Intelligence, 30(2): 228-242.
[ 8 ] Lin, S., Ritchie, D., Fisher, M., and P. Hanrahan (2013). Probabilistic color-by-numbers: suggestion pattern colorizations using factor graphs. ACM Trans. on Graphics, 32 (4): 37.1, 2, 6, 9.
[ 9 ] U. Lipowezky, O. Mamo, and A. Cohen, “Using integrated color and texture features for automatic hair detection,” Proc. 25th IEEE Convention Electrical and Electronic Engineers in Israel, pp. 51-55, December 2008.
[ 10 ] Q. Luan, F. Wen, and Y.-Q. Xu, “Color transfer brush,” Proc. 15th Pacific Conference on Computer Graphics and Applications, pp. 465-468, 2007.
[ 11 ] Provenzi, E., Gatto, C., Fierro, M., and A. Rizzi (2008) A Spatially Variant White Patch and Gray World Method for Color Image Enhancement Driven by Local Contrast. IEEE Trans. Pattern Analysis and Machine Intelligence, 30(10): 1757-70.
[ 12 ] Reinhard, E., M., Ashikhmin, B., Gooch, and P. Shirley (2001) Color transfer between images. IEEE Trans. Computer Graphics and Applications 21(5): 34-41.
[ 13 ] Y.-W. Tai, J. Jia, and C.-K. Tang, “Local color transfer via probabilistic segmentation by expectation-maximization,” Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 747-754, 2005.
[ 14 ] Y. Xiang, B. Zou, H. Wang, H. Li, and Z. Xie, “Multi-source color transfer for natural images,” Proc. 15th IEEE International Conference on Image Processing, vol. 1, pp. 469-472, 2008.
[ 15 ] Yacoob, Y., and L.S. Davis (2006). Detection and Analysis of Hair. IEEE Trans. Pattern Analysis and Machine Intelligence, 28(6): 1164-69.
[ 16 ] [Online]. Available http://www.ezface.com: EZface Virtual Mirror, EZface Inc., 2008.
[ 17 ] [Online]. Available http://www.taaz.com: Taaz.com/Photometria Inc., May 2008.
[ 18 ] [Online]. Available http://www.photoshopessentials.com/photo-editing/hair-color/page-2. php: Change Hair Color in Photoshop, Photoshop Essentials.com, 2009.