IEEE Trans Image Process. 2014 May;23(5):2109-21. doi: 10.1109/TIP.2014.2312287.
This paper addresses the problem of automatic figure-ground segmentation, which aims at automatically segmenting out all foreground objects from background. The underlying idea of this approach is to transfer segmentation masks of globally and locally (glocally) similar exemplars into the query image. For this purpose, we propose a novel high-level image representation method named as object-oriented descriptor. Using this descriptor, a set of exemplar images glocally similar to the query image is retrieved. Then, using over-segmented regions of these retrieved exemplars, a discriminative classifier is learned on-the-fly and subsequently used to predict foreground probability for the query image. Finally, the optimal segmentation is obtained by combining the online prediction with typical energy optimization of Markov random field. The proposed approach has been extensively evaluated on three datasets, including Pascal VOC 2010, VOC 2011 segmentation challenges, and iCoseg dataset. Experiments show that the proposed approach outperforms state-of-the-art methods and has the potential to segment large-scale images containing unknown objects, which never appear in the exemplar images.
本文针对自动前景-背景分割问题展开研究，旨在自动从背景中提取出所有前景对象。该方法的基本思想是将全局和局部（glocally）相似样本的分割掩模转移到查询图像中。为此，我们提出了一种新颖的高层图像表示方法，称为面向对象描述符。使用该描述符，可以检索到与查询图像在全局和局部上都相似的一组样本图像。然后，使用这些检索到的样本的过分割区域，实时学习判别分类器，并随后用于预测查询图像的前景概率。最后，通过将在线预测与马尔可夫随机场的典型能量优化相结合，获得最优分割。我们在三个数据集（包括 Pascal VOC 2010、VOC 2011 分割挑战和 iCoseg 数据集）上对所提出的方法进行了广泛评估。实验表明，所提出的方法优于最先进的方法，并且有潜力分割包含未知对象的大规模图像，这些对象从未出现在样本图像中。
