A Novel Nonlinear Regression Approach for Efficient and Accurate Image Matting
A Novel Nonlinear Regression Approach for Efficient and Accurate Image Matting
复制标题
DOI：
10.1109/lsp.2013.2274874
复制
发表时间：
2013-08
影响因子：
3.9
通讯作者：
Qingsong Zhu;Zhanpeng Zhang;Zhan Song;Yaoqin Xie;Lei Wang
中科院分区：
文献类型：
--
作者：
Qingsong Zhu;Zhanpeng Zhang;Zhan Song;Yaoqin Xie;Lei Wang
当前的图像抠图方法通常是基于各种局部假设下的颜色样本来实现的。在这封信中，一种新的图像抠图算法的研究通过处理阿尔法抠图作为一个回归问题。具体来说，我们使用支持向量回归学习像素特征和alpha值之间的空间变化关系。通过基于学习的方法，可以大大减轻局部图像假设所带来的局限性。此外，在学习阶段计算的置信度项可以方便地与其他抠图方法相结合，以提高抠图精度。定性和定量评估是以公共铺垫基准进行的。并将其结果与一些最近的抠图算法进行了比较，以显示其在效率和准确性方面的优势。
Current image matting approaches are often implemented based upon color samples under various local assumptions. In this letter, a novel image matting algorithm is investigated by treating the alpha matting as a regression problem. Specifically, we learn spatially-varying relations between pixel features and alpha values using support vector regression. Via the learning-based approach, limitations caused by local image assumptions can be greatly relieved. In addition, the computed confidence terms in learning phase can be conveniently integrated with other matting approaches for the matting accuracy improvement. Qualitative and quantitative evaluations are implemented with a public matting benchmark. And the results are compared with some recent matting algorithms to show its advantages in both efficiency and accuracy.