Compassionately Conservative Balanced Cuts for Image Segmentation
Compassionately Conservative Balanced Cuts for Image Segmentation
复制标题
DOI：
10.1109/cvpr.2018.00181
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
N. Cahill;Tyler L. Hayes;R. T. Meinhold;John F. Hamilton
中科院分区：
文献类型：
--
作者：
N. Cahill;Tyler L. Hayes;R. T. Meinhold;John F. Hamilton
归一化切割（NCut）目标函数广泛用于数据聚类和图像分割，它以一种方式量化图分区的成本，使平衡的聚类或段偏向于具有比不平衡分区更低的值。然而，这种偏差是如此强烈，以至于它避免了任何单例分区，即使当顶点与图的其余部分连接非常弱时也是如此。在平衡削减成本的Bührer - hein家族的激励下，我们提出了同情保守平衡（CCB）削减成本家族，它由一个参数索引，可以用来在避免过多的单例分区的愿望和所有分区都应该平衡的概念之间达成妥协。我们证明了CCB-Cut最小化可以被放宽为一个正交约束最小化问题，该问题与计算一个特定指标值的分段平面嵌入（PFE）问题相一致，并且我们提出了一种通过迭代最小化重加权瑞利商（IRRQ）序列来解决松弛问题的算法。使用来自BSDS500数据库的图像，我们发现基于CCB-Cut最小化的图像分割比基于ncut的图像分割在ground truth方面具有更好的准确性和更大的区域大小可变性。
The Normalized Cut (NCut) objective function, widely used in data clustering and image segmentation, quantifies the cost of graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than unbalanced partitionings. However, this bias is so strong that it avoids any singleton partitions, even when vertices are very weakly connected to the rest of the graph. Motivated by the Bühler-Hein family of balanced cut costs, we propose the family of Compassionately Conservative Balanced (CCB) Cut costs, which are indexed by a parameter that can be used to strike a compromise between the desire to avoid too many singleton partitions and the notion that all partitions should be balanced. We show that CCB-Cut minimization can be relaxed into an orthogonally constrained lt-minimization problem that coincides with the problem of computing Piecewise Flat Embeddings (PFE) for one particular index value, and we present an algorithm for solving the relaxed problem by iteratively minimizing a sequence of reweighted Rayleigh quotients (IRRQ). Using images from the BSDS500 database, we show that image segmentation based on CCB-Cut minimization provides better accuracy with respect to ground truth and greater variability in region size than NCut-based image segmentation.