Learning a Dictionary of Shape Epitomes with Applications to Image Labeling.
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling.
复制标题
DOI：
10.1109/iccv.2013.49
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Yuille AL
中科院分区：
文献类型：
--
作者：
Chen LC;Papandreou G;Yuille AL
本文的第一个主要贡献是一种新的方法表示图像的基础上字典的形状摘要。这些形状缩影表示图像的局部边缘结构，并包括隐藏变量来编码移位和旋转。它们以无监督的方式从地面实况边缘学习。这个字典是紧凑的，但也能够捕捉自然图像中的边缘的典型形状。在本文中，我们说明了形状的缩影，将它们应用到图像标记任务。在补充材料中描述的其他工作中，我们将它们应用于边缘检测和图像建模。我们使用条件随机场（CRF）模型将形状摘要应用于图像标记。它们是大多数CRF中使用的超像素或像素表示的替代品。在我们的方法中，一个图像补丁的形状编码的形状缩影从字典。与超像素表示不同，我们的方法避免了做出无法逆转的早期决定。我们由此产生的分层CRF有效地捕获本地和全球类共现属性。我们证明了我们的方法的定量和定性性质的图像标记实验上的两个标准数据集：MSRC-21和斯坦福大学背景。
The first main contribution of this paper is a novel method for representing images based on a dictionary of shape epitomes. These shape epitomes represent the local edge structure of the image and include hidden variables to encode shift and rotations. They are learnt in an unsupervised manner from groundtruth edges. This dictionary is compact but is also able to capture the typical shapes of edges in natural images. In this paper, we illustrate the shape epitomes by applying them to the image labeling task. In other work, described in the supplementary material, we apply them to edge detection and image modeling. We apply shape epitomes to image labeling by using Conditional Random Field (CRF) Models. They are alternatives to the superpixel or pixel representations used in most CRFs. In our approach, the shape of an image patch is encoded by a shape epitome from the dictionary. Unlike the superpixel representation, our method avoids making early decisions which cannot be reversed. Our resulting hierarchical CRFs efficiently capture both local and global class co-occurrence properties. We demonstrate its quantitative and qualitative properties of our approach with image labeling experiments on two standard datasets: MSRC-21 and Stanford Background.