Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs
Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs
复制标题
MRF 中具有二次全局约束的图像对的联合分割
DOI：
10.1007/978-3-540-76390-1_82
复制
发表时间：
2007-11
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
本文提供了一种新的联合分割方法，即同时分割具有相同前景和不同背景的多个图像。我们的贡献主要有四个方面。首先，图像对通常是在不同的成像条件下捕获的，这使得所需对象的颜色分布发生很大变化，因此给基于颜色的联合分割带来了挑战。在这里，我们提出了一种稳健的回归方法来最小化相应图像区域之间的颜色差异。其次，尽管已经进行了深入的讨论，但“协同分割”一词的确切含义相当模糊，并且之前忽略了图像背景的重要性，这促使我们为协同分割提供一个新颖、清晰和全面的定义。第三，特定区域往往被归类为前景是一个复杂的问题，因此我们引入“风险术语”来区分颜色，据我们所知，这在以前的文献中尚未讨论过。最后也是最重要的是，与 MRF 中传统的线性全局项不同，我们提出了一种基于平方差和（SSD）的全局约束，并推导了其等效的二次形式，该形式考虑了特征空间中的成对关系。做出合理的假设，通过交替图割可以有效地获得全局最优。
This paper provides a novel method for co-segmentation, namely simultaneously segmenting multiple images with same foreground and distinct backgrounds. Our contribution primarily lies in four-folds. First, image pairs are typically captured under different imaging conditions, which makes the color distribution of desired object shift greatly, hence it brings challenges to color-based co-segmentation. Here we propose a robust regression method to minimize color variances between corresponding image regions. Secondly, although having been intensively discussed, the exact meaning of the term ”co-segmentation” is rather vague and importance of image background is previously neglected, this motivate us to provide a novel, clear and comprehensive definition for co-segmentation. Thirdly, it is an involved issue that specific regions tend to be categorized as foreground, so we introduce ”risk term” to differentiate colors, which has not been discussed before in the literatures to our best knowledge. Lastly and most importantly, unlike conventional linear global terms in MRFs, we propose a sum-of-squared-difference (SSD) based global constraint and deduce its equivalent quadratic form which takes into account the pairwise relations in feature space. Reasonable assumptions are made and global optimal could be efficiently obtained via alternating Graph Cuts.
登录
查看更多内容
影响因子：
2.5
作者：
E. Ziegel
通讯作者：
E. Ziegel
DOI：
10.1109/cvpr.2006.91
发表时间：
2006-06
期刊：
2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
影响因子：
--
作者：
C. Rother;T. Minka;A. Blake;V. Kolmogorov
通讯作者：
C. Rother;T. Minka;A. Blake;V. Kolmogorov
DOI：
10.1109/iccv.2001.937606
发表时间：
2001-07
期刊：
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001
影响因子：
--
作者：
Yair Weiss
通讯作者：
Yair Weiss
DOI：
10.1109/cvpr.2005.90
发表时间：
2005-06
期刊：
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子：
--
作者：
V. Kolmogorov;A. Criminisi;A. Blake;G. Cross;C. Rother
通讯作者：
V. Kolmogorov;A. Criminisi;A. Blake;G. Cross;C. Rother
DOI：
10.1109/cvpr.2005.93
发表时间：
2005-06
期刊：
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子：
--
作者：
Joost van de Weijer;T. Gevers
通讯作者：
Joost van de Weijer;T. Gevers