Combining Belief Networks and Neural Networks for Scene Segmentation
Combining Belief Networks and Neural Networks for Scene Segmentation
复制标题
DOI：
10.1109/34.993555
复制
发表时间：
2002-04
期刊：
影响因子：
--
通讯作者：
X. Feng;Christopher K. I. Williams;Stephen N. Felderhof
中科院分区：
文献类型：
--
作者：
X. Feng;Christopher K. I. Williams;Stephen N. Felderhof
我们关注图像分割问题，其中每个像素被分配给预定义的有限数量的标签之一。在贝叶斯图像分析中，这需要将类标签的局部预测与标签图像的先验模型融合在一起。继 Bouman 和 Shapiro（1994）的工作之后，我们考虑使用树结构信念网络（TSBN）作为先验模型。 TSBN 中的参数使用最大似然目标函数和 EM 算法进行训练，并通过计算其编码标签图像的效率来评估生成的模型。许多作者使用高斯混合模型将标签字段连接到图像数据。我们将此方法与 Smyth (1994) 以及 Morgan 和 Bourlard (1995) 的缩放似然方法进行比较，其中神经网络像素分类的局部预测与 TSBN 先验融合。我们的结果表明神经网络可以获得更高的性能。我们评估获得的分类结果，不仅强调最大后验分割，而且强调不确定性，例如通过像素后验边缘熵证明的那样。我们还研究了 TSBN 条件最大似然训练的使用，发现这比 ML 训练的 TSBN 提高了分类性能。
We are concerned with the problem of image segmentation, in which each pixel is assigned to one of a predefined finite number of labels. In Bayesian image analysis, this requires fusing together local predictions for the class labels with a prior model of label images. Following the work of Bouman and Shapiro (1994), we consider the use of tree-structured belief networks (TSBNs) as prior models. The parameters in the TSBN are trained using a maximum-likelihood objective function with the EM algorithm and the resulting model is evaluated by calculating how efficiently it codes label images. A number of authors have used Gaussian mixture models to connect the label field to the image data. We compare this approach to the scaled-likelihood method of Smyth (1994) and Morgan and Bourlard (1995), where local predictions of pixel classification from neural networks are fused with the TSBN prior. Our results show a higher performance is obtained with the neural networks. We evaluate the classification results obtained and emphasize not only the maximum a posteriori segmentation, but also the uncertainty, as evidenced e.g., by the pixelwise posterior marginal entropies. We also investigate the use of conditional maximum-likelihood training for the TSBN and find that this gives rise to improved classification performance over the ML-trained TSBN.