Multiscale conditional random fields for image labeling
Multiscale conditional random fields for image labeling
复制标题
DOI：
10.1109/cvpr.2004.173
复制
发表时间：
2004-06
期刊：
影响因子：
--
通讯作者：
Xuming He;R. Zemel;M. A. Carreira-Perpiñán
中科院分区：
文献类型：
--
作者：
Xuming He;R. Zemel;M. A. Carreira-Perpiñán
我们提出了一种包含上下文特征的方法来标记图像，其中每个像素被分配到一个有限的标签集。这些特征被合并到一个概率框架中，该框架结合了几个组件的输出。组件编码的信息不同。一些关注图像-标签映射，而另一些只关注标签字段中的模式。组件的规模也不同，因为一些组件专注于精细分辨率模式，而另一些组件专注于更粗糙、更全局的结构。对比散度算法的监督版本被应用于从标记的图像数据中学习这些特征。我们在两个真实世界的图像数据库上演示了性能，并将其与分类器和马尔可夫随机场进行了比较。
We propose an approach to include contextual features for labeling images, in which each pixel is assigned to one of a finite set of labels. The features are incorporated into a probabilistic framework, which combines the outputs of several components. Components differ in the information they encode. Some focus on the image-label mapping, while others focus solely on patterns within the label field. Components also differ in their scale, as some focus on fine-resolution patterns while others on coarser, more global structure. A supervised version of the contrastive divergence algorithm is applied to learn these features from labeled image data. We demonstrate performance on two real-world image databases and compare it to a classifier and a Markov random field.