Multiscale Symmetric Part Detection and Grouping
Multiscale Symmetric Part Detection and Grouping
复制标题
DOI：
10.1007/s11263-013-0614-3
复制
发表时间：
2009-09
影响因子：
19.5
通讯作者：
Alex Levinshtein;C. Sminchisescu;Sven J. Dickinson
中科院分区：
文献类型：
--
作者：
Alex Levinshtein;C. Sminchisescu;Sven J. Dickinson
轮廓化算法通常将对象的轮廓分解为一组对称部分，为形状分类提供了强大的表示。然而，访问对象的轮廓假设正确的图形-背景分割，导致与主流分类社区脱节，该社区试图从混乱的图像中识别对象。在本文中，我们提出了一种新的方法来恢复和分组的对象的对称部分从一个混乱的场景。我们开始通过使用多分辨率超像素分割来生成中间点假设，并使用学习的亲和度函数来感知地分组可能属于相同中间分支的附近中间点。在下一阶段，我们学习更高粒度的亲和度函数，以将可能属于同一对象的中间分支分组。由此产生的框架产生一个骨架近似，是免费的许多不稳定性，发生与传统的骨架。更重要的是，它不需要一个封闭的轮廓，使应用程序的分类系统，以更现实的图像。
Skeletonization algorithms typically decompose an object’s silhouette into a set of symmetric parts, offering a powerful representation for shape categorization. However, having access to an object’s silhouette assumes correct figure-ground segmentation, leading to a disconnect with the mainstream categorization community, which attempts to recognize objects from cluttered images. In this paper, we present a novel approach to recovering and grouping the symmetric parts of an object from a cluttered scene. We begin by using a multiresolution superpixel segmentation to generate medial point hypotheses, and use a learned affinity function to perceptually group nearby medial points likely to belong to the same medial branch. In the next stage, we learn higher granularity affinity functions to group the resulting medial branches likely to belong to the same object. The resulting framework yields a skeletal approximation that is free of many of the instabilities that occur with traditional skeletons. More importantly, it does not require a closed contour, enabling the application of skeleton-based categorization systems to more realistic imagery.