Color Style Transfer Techniques using Hue, Lightness and Saturation Histogram Matching

We present new methods which transfer the color style of a source image into an arbitrary given target image having a different 3D color distribution. The color transfer has a high importance ensuring a wide area of applications from artistic transformation of the color atmosphere of images until different scientific visualizations using special gamut mappings. Our technique use a permissive, or optionally strict, 3D histogram matching, similarly to the sampling of multivariable functions applying a sequential chain of conditional probability density functions. We work by order of hue, hue dependent lightness and from both dependent saturation histograms of source and target images, respectively. We apply different histogram transformations, like smoothing or contrast limitation, in order to avoid some unexpected high gradients and other artifacts. Furthermore, we use dominance suppression optionally, by applying sub-linear functions for the histograms in order to get well balanced color distributions, or an overall appearance reflecting the memory color distribution better. Forward and inverse operations on the corresponding cumulative histograms ensure a continuous mapping of perceptual attributes correlating to limited derivatives. Sampling an appropriate fraction of the pixels and using perceptually accurate and continuous histograms with minimal size as well as other gems make this method robust and fast.

[1]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[2]  Ján Morovic,et al.  Accurate 3D image colour histogram transformation , 2003, Pattern Recognit. Lett..

[3]  Jeffrey J. Rodriguez,et al.  Enhancement of multispectral images using histogram explosion , 1994, Optics & Photonics.

[4]  Asen Asenov,et al.  Excessive Over-Relaxation Method for Multigrid Poisson Solvers , 2002 .

[5]  Klaus Mueller,et al.  Transferring color to greyscale images , 2002, ACM Trans. Graph..

[6]  Ján Morovic,et al.  A fast, non-iterative and exact histogram matching algorithm , 2002, Pattern Recognit. Lett..

[7]  Ján Morovic,et al.  The Influence of Image Histograms on Cross-Media Colour Image Reproduction , 2001, PICS.

[8]  M. Ronnier Luo,et al.  Evaluating gamut mapping algorithms for universal applicability , 2001 .

[9]  David Salesin,et al.  Image Analogies , 2001, SIGGRAPH.

[10]  Florin Cutzu,et al.  Differences of edge properties in photographs and paintings , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[11]  Guojun Lu,et al.  Using perceptually weighted histograms for colour-based image retrieval , 1998, ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344).

[12]  D. Ruderman,et al.  Statistics of cone responses to natural images: implications for visual coding , 1998 .

[13]  Donald H. House,et al.  Image Recoloring Induced by Palette Color Associations , 2003, WSCG.

[14]  Shi-Kuo Chang,et al.  Optimal histogram matching by monotone gray level transformation , 1978, CACM.

[15]  Arthur R. Weeks,et al.  Histogram equalization of 24-bit color images in the color difference (C-Y) color space , 1995, J. Electronic Imaging.

[16]  Rangaraj M. Rangayyan,et al.  Adaptive-neighborhood histogram equalization of color images , 2001, J. Electronic Imaging.

[17]  Guillermo Sapiro,et al.  Color histogram equalization through mesh deformation , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[18]  Arthur R. Weeks,et al.  Histogram specification of 24-bit color images in the color difference (C-Y) color space , 1999, J. Electronic Imaging.

[19]  James Lee Hafner,et al.  Efficient Color Histogram Indexing for Quadratic Form Distance Functions , 1995, IEEE Trans. Pattern Anal. Mach. Intell..