Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs
Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs
复制标题
DOI：
10.1109/cvpr.2006.91
复制
发表时间：
2006-06
期刊：
影响因子：
--
通讯作者：
C. Rother;T. Minka;A. Blake;V. Kolmogorov
中科院分区：
文献类型：
--
作者：
C. Rother;T. Minka;A. Blake;V. Kolmogorov
我们引入了协同分割这一术语，它表示同时分割一对图像的共同部分的任务。提出了一种用于协同分割的生成模型。该模型中的推理导致最小化一个能量，其中包含一个编码空间连贯性的马尔可夫随机场（MRF）项以及一个试图匹配共同部分的外观直方图的全局约束。这种能量之前未曾被提出过，其优化具有挑战性且是NP难的。针对这个问题，提出了一种我们称之为信赖域图割的新颖优化方案。我们证明这个框架有可能改进广泛的研究领域：基于对象的图像检索、视频跟踪与分割以及交互式图像编辑。该框架的强大之处在于它的通用性，共同部分可以是一个刚性/非刚性的对象（或场景），从不同的视角观察，甚至是同一类别的相似对象。
We introduce the term cosegmentation which denotes the task of segmenting simultaneously the common parts of an image pair. A generative model for cosegmentation is presented. Inference in the model leads to minimizing an energy with an MRF term encoding spatial coherency and a global constraint which attempts to match the appearance histograms of the common parts. This energy has not been proposed previously and its optimization is challenging and NP-hard. For this problem a novel optimization scheme which we call trust region graph cuts is presented. We demonstrate that this framework has the potential to improve a wide range of research: Object driven image retrieval, video tracking and segmentation, and interactive image editing. The power of the framework lies in its generality, the common part can be a rigid/non-rigid object (or scene), observed from different viewpoints or even similar objects of the same class.