Image Segmentation by Cascaded Region Agglomeration
Image Segmentation by Cascaded Region Agglomeration
复制标题
DOI：
10.1109/cvpr.2013.262
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Zhile Ren;Gregory Shakhnarovich
中科院分区：
文献类型：
--
作者：
Zhile Ren;Gregory Shakhnarovich
我们提出了一个分层分割算法，开始与一个非常精细的分割，并逐步合并区域使用级联的边界分类器。这种方法允许区域和边界特征的权重适应于应用它们的分割尺度。级联的各个阶段是按顺序训练的，不对称损失是为了最大化边界召回。在六个分割数据集上，我们的算法在大多数区域质量指标下都达到了最佳性能，并且比以前的工作使用更少的片段。我们的算法在基于边界的措施下的密集过分割（超像素）制度中也具有很强的竞争力。
We propose a hierarchical segmentation algorithm that starts with a very fine over segmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights of region and boundary features to adapt to the segmentation scale at which they are applied. The stages of the cascade are trained sequentially, with asymetric loss to maximize boundary recall. On six segmentation data sets, our algorithm achieves best performance under most region-quality measures, and does it with fewer segments than the prior work. Our algorithm is also highly competitive in a dense over segmentation (super pixel) regime under boundary-based measures.