模糊颜色聚类在颜色传输中的应用

Application of Fuzzy Color Cluster in Color Transfer between Images

提出一种自动的、基于模糊颜色聚类的自适应颜色传输算法.首先将源图像和目标图像从RGB空间转换到ιαβ空间,在ιαβ空间对2幅图像进行模糊颜色聚类分析;根据目标图像特征属性对每个聚类域计算相应的匹配权值,图像间匹配权值相近的聚类域确定为图像传输的匹配方向;最后将隶属度控制引入传输方程,实现图像间自适应颜色传输.实验结果表明,该算法比原有颜色传输算法的传输效果更加平滑、自然.

An automatic color transfer algorithm based on fuzzy color clustering is proposed in this paper. By the algorithm, the source and target images are first transformed into tαβ space from RGB space. Then fuzzy color clustering is applied to obtain different clustering fields. According to the target statistical properties, the matching weights are calculated to determine the direction of local color transfer. Finally, membership degree control is introduced to color transfer equations to realize the adaptive color transfer between images. The experimental results show that more natural and smoother effects could be achieved by the algorithm proposed in the paper than the classical color transfer algorithms.