arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.00723cs.CV
收藏

基于与或树表示的轮廓片段形状模型学习

Learning Contour-Fragment-based Shape Model with And-Or Tree Representation

Sun Yat-Sen University(中山大学);Lotus Hill Research Institute(莲花山研究院)

Liang Lin, Xiaolong Wang, Wei Yang, Jianhuang Lai

摘要:

本文提出了一种简单而有效的方法来学习分层对象的形状模型组成的局部轮廓片段,它表示的一个类别的形状的形式与或树。该模型通过引入“开关”变量(即或节点)来扩展传统的分层树结构,该“开关”变量明确指定产生式规则以捕获形状变化。因此,我们定义的模型有三层:用于检测局部轮廓片段的叶节点,指定选择的叶节点或节点,和根节点编码的整体失真。在训练阶段,为了优化与或树学习,我们通过在迭代学习步骤中嵌入结构聚类来扩展凹凸过程(CCCP)。形状检测的推理与模型优化是一致的,它将通过叶节点和或节点的局部测试与通过根节点的全局验证相结合。我们的方法的优点在具有挑战性的形状数据库(即,ETHZ和INRIA马),并总结如下。(1)该方法能够准确地定位形状轮廓对不可靠的边缘检测和边缘跟踪。(2)与或树模型使我们能够很好地捕捉组内方差。

英文摘要:

This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree. This model extends the traditional hierarchical tree structures by introducing the "switch" variables (i.e. the or-nodes) that explicitly specify production rules to capture shape variations. We thus define the model with three layers: the leaf-nodes for detecting local contour fragments, the or-nodes specifying selection of leaf-nodes, and the root-node encoding the holistic distortion. In the training stage, for optimization of the And-Or tree learning, we extend the concave-convex procedure (CCCP) by embedding the structural clustering during the iterative learning steps. The inference of shape detection is consistent with the model optimization, which integrates the local testings via the leaf-nodes and or-nodes with the global verification via the root-node. The advantages of our approach are validated on the challenging shape databases (i.e., ETHZ and INRIA Horse) and summarized as follows. (1) The proposed method is able to accurately localize shape contours against unreliable edge detection and edge tracing. (2) The And-Or tree model enables us to well capture the intraclass variance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑