arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.05074cs.CV
收藏

深度活动轮廓

Deep Active Contours

Johns Hopkins University(约翰霍普金斯大学);Technische Universität München(慕尼黑工业大学)

Christian Rupprecht, Elizabeth Huaroc, Maximilian Baust, Nassir Navab

摘要:

我们提出了一种交互式的边界提取方法,它结合了一个深,补丁为基础的表示与活动轮廓框架。我们训练一个类特定的卷积神经网络,它预测一个向量,该向量从发展轮廓上的相应点指向感兴趣对象边界上的最近点。这些预测形成一个矢量场,然后用于发展的轮廓由Sundaramoorthi等人提出的Sobolev活动轮廓框架。由此产生的交互式分割方法是非常有效的计算资源,甚至可以在相对较小的图形卡上进行训练。我们评估了所提出的方法在医疗和非医疗挑战数据集(如STACOM数据集和PASCAL VOC 2012数据集)上的潜力。

英文摘要:

We propose a method for interactive boundary extraction which combines a deep, patch-based representation with an active contour framework. We train a class-specific convolutional neural network which predicts a vector pointing from the respective point on the evolving contour towards the closest point on the boundary of the object of interest. These predictions form a vector field which is then used for evolving the contour by the Sobolev active contour framework proposed by Sundaramoorthi et al. The resulting interactive segmentation method is very efficient in terms of required computational resources and can even be trained on comparatively small graphics cards. We evaluate the potential of the proposed method on both medical and non-medical challenge data sets, such as the STACOM data set and the PASCAL VOC 2012 data set.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑