摘要
针对经典全局颜色迁移算法在处理具有复杂色彩的自然图像时常出现较多颜色误传的问题,提出一种基于交互式分割与勾画匹配的局部自适应颜色迁移算法。该算法不仅适用于彩色图像间的颜色迁移,而且适用于灰度图着色。算法基本思路是首先分别对两幅图像进行交互式分割,然后对分割后图像的同质景物区域进行勾画匹配,最后在相匹配区域间进行局部颜色迁移。实验结果表明该算法能很好地实现参考图像和目标图像中同质景物内容区域间的颜色迁移,减少颜色误传的现象。结果图像颜色自然度与局部景物一致度有明显提高。
A local adaptive color transfer algorithm based on interactive segmentation and matched by marking is proposed to overcome the problem of color misrepresentation in classical global color transfer approaches when dealing with the complex nature images. The algorithm contains three phases. In the first phase, the interactive segmentation is applied to the reference image and target image. In the second phase, the regions with similar scenes in the two segmented images are grouped into matched region pairs by marking scribbles. Finally, local adaptive color transfer is carried out between the matched region pairs. The proposed method not only can be used for color transfer between color images, but also can serve for grayscale image colorization. Experimental results demonstrate that the proposed method can reduce color misrepresentation in the color transfer which improves the naturalness and the local consistency of the result image.
出处
《太赫兹科学与电子信息学报》
2014年第3期433-439,共7页
Journal of Terahertz Science and Electronic Information Technology
基金
国家自然科学基金资助项目(61171165)
关键词
交互式分割
彩色图像颜色迁移
灰度图像着色
勾画式匹配
interactive segmentation
color transfer between color images
grayscale image colorization
match by marking scribbles
