Foreground–background segmentation has recently been applied [S.X. Yu, J. Shi, Object-specific figure-ground segregation, Computer Vision and Pattern Recognition (CVPR), 2003; S. Kumar, M. Hebert, Man-made structure detection in natural images using a causal multiscale random field, Computer Vision and Pattern Recognition (CVPR), 2003] to the detection and segmentation of specific objects or structures of interest from the background as an efficient alternative to techniques such as deformable templates [A.L. Yuille, Deformable templates for face recognition. Journal of Cognitive Neuroscience 3 (1) (1991)]. We introduce a graphical model (i.e. Markov random field)-based formulation of structure-specific figure-ground segmentation based on simple geometric features extracted from an image, such as local configurations of linear features, that are characteristic of the desired figure structure. Our formulation is novel in that it is based on factor graphs, which are graphical models that encode interactions among arbitrary numbers of random variables. The ability of factor graphs to express interactions higher than pairwise order (the highest order encountered in most graphical models used in computer vision) is useful for modeling a variety of pattern recognition problems. In particular, we show how this property makes factor graphs a natural framework for performing grouping and segmentation, and demonstrate that the factor graph framework emerges naturally from a simple maximum entropy model of figure-ground segmentation.

We cast our approach in a learning framework, in which the contributions of multiple grouping cues are learned from training data, and apply our framework to the problem of finding printed text in natural scenes. Experimental results are described, including a performance analysis that demonstrates the feasibility of the approach.

最近应用了前景-背景分割 [SX Yu, J. Shi, Object-specific figure-ground segregation, Computer Vision and Pattern Recognition (CVPR), 2003; S. Kumar, M. Hebert, Man-made structure detection in natural images using a causal multiscale random field, Computer Vision and Pattern Recognition (CVPR), 2003] 从背景中检测和分割特定对象或感兴趣的结构作为一种有效的替代技术，例如可变形模板 [AL Yuille，用于人脸识别的可变形模板。认知神经科学杂志 3 (1) (1991)]。我们基于从图像中提取的简单几何特征（例如线性特征的局部配置）引入了基于图形模型（即马尔可夫随机场）的结构特定图形-地面分割的公式，这是所需图形结构的特征。我们的公式是新颖的，因为它基于因子图，因子图是对任意数量的随机变量之间的交互进行编码的图形模型。因子图表达高于成对阶（计算机视觉中使用的大多数图形模型中遇到的最高阶）的交互的能力对于建模各种模式识别问题非常有用。特别是，我们展示了这个特性如何使因子图成为执行分组和分割的自然框架，并证明因子图框架是从图形-背景分割的简单最大熵模型中自然产生的。它们是对任意数量的随机变量之间的交互进行编码的图形模型。因子图表达高于成对阶（计算机视觉中使用的大多数图形模型中遇到的最高阶）的交互的能力对于建模各种模式识别问题非常有用。特别是，我们展示了这个特性如何使因子图成为执行分组和分割的自然框架，并证明因子图框架是从图形-背景分割的简单最大熵模型中自然产生的。它们是对任意数量的随机变量之间的交互进行编码的图形模型。因子图表达高于成对阶（计算机视觉中使用的大多数图形模型中遇到的最高阶）的交互的能力对于建模各种模式识别问题非常有用。特别是，我们展示了这个特性如何使因子图成为执行分组和分割的自然框架，并证明因子图框架是从图形-背景分割的简单最大熵模型中自然产生的。

我们将我们的方法应用于学习框架中，其中从训练数据中学习多个分组线索的贡献，并将我们的框架应用于在自然场景中查找印刷文本的问题。描述了实验结果，包括证明该方法可行性的性能分析。