Selective color transfer with multi-source images
Selective color transfer with multi-source images
复制标题
DOI：
10.1016/j.patrec.2009.01.004
复制
发表时间：
2009-05
期刊：
影响因子：
--
通讯作者：
Yao Xiang;Beiji Zou;Hong Li
中科院分区：
文献类型：
--
作者：
Yao Xiang;Beiji Zou;Hong Li
提出了一种新的方法来转移选择性的颜色从一组源图像到目标图像。提出了一种改进的EM方法，利用高斯混合模型（GMM）对目标图像的区域颜色分布进行建模，然后在该模型的训练下，从给定的源图像中自动选择合适的参考颜色对每个目标区域进行着色。实验结果表明，该方法适用于灰度图像的彩色化和彩色图像间的颜色传递。提出了一种新的综合考虑颜色和结构相似性的客观评价方法，验证了该方法的有效性。
A novel method is proposed to transfer selective colors from a set of source images to a target image. An improved EM method is presented to model regional color distribution of the target image by Gaussian Mixture Model (GMM), then, trained by this model, appropriate reference colors are automatically selected from the given source images to color each target region. The generated compelling results prove that our proposed method is applicable to colorize grayscale images and color transfer between chromatic images. A new objective metric considering colorfulness and structural similarity is also proposed to evaluate the quality of the transferred image, which verifies good performance of our method.