Multiple Reference Images Color Transfer Based on Improved GMM Model

Color transfer is to change the image color according to one or more reference images to match people’s cognition. Usually, there are two problems deserved to be researched further. One is to find suitable reference colors for a complex image. The other is to lessen the details loss in the process. In the paper, GMM model is improved by considering the geometric position relation of the color clustering to construct color transfer intentions between source image and multiple reference images. The geometric coordinate smoothing parameter is introduced to improve EM algorithm to reduce the details loss. Based on Baidu data set and the reference paper data sets, a comparison experiment between typical color transfer algorithms and our method was presented. The experimental results can demonstrate that the algorithm proposed in the paper is reasonable and effective.

[1]  Lizhuang Ma,et al.  Color transfer in correlated color space , 2006, VRCIA '06.

[2]  A.C. Kokaram,et al.  N-dimensional probability density function transfer and its application to color transfer , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  Xueting Li,et al.  A Closed-form Solution to Photorealistic Image Stylization , 2018, ECCV.

[4]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[5]  László Neumann,et al.  Color Style Transfer Techniques using Hue, Lightness and Saturation Histogram Matching , 2005, CAe.

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

[7]  Chi-Keung Tang,et al.  Local color transfer via probabilistic segmentation by expectation-maximization , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Rozenn Dahyot,et al.  Robust Registration of Gaussian Mixtures for Colour Transfer , 2017, ArXiv.

[9]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[10]  Xing Mei,et al.  Content‐Based Colour Transfer , 2013, Comput. Graph. Forum.

[11]  Li Liu,et al.  Corruptive Artifacts Suppression for Example-Based Color Transfer , 2014, IEEE Transactions on Multimedia.

[12]  Guanbo Bao,et al.  Fast local color transfer via dominant colors mapping , 2010, SIGGRAPH ASIA.

[13]  Masayuki Nakajima,et al.  Example-Based Color Stylization of Images , 2005, TAP.

[14]  Sabine Süsstrunk,et al.  Measuring colorfulness in natural images , 2003, IS&T/SPIE Electronic Imaging.

[15]  Youngbae Hwang,et al.  Color Transfer Using Probabilistic Moving Least Squares , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.