Nunez Elvis, Joshi Shantanu H
Department of Applied Mathematics and Statistics, Johns Hopkins University.
Ahmanson Lovelace Brain Mapping Center, Department of Neurology, UCLA.
Conf Comput Vis Pattern Recognit Workshops. 2020 Jun;2020:3782-3790. doi: 10.1109/cvprw50498.2020.00441. Epub 2020 Jul 28.
Rate-invariant or reparameterization-invariant matching between functions and shapes of curves, respectively, is an important problem in computer vision and medical imaging. Often, the computational cost of matching using approaches such as dynamic time warping or dynamic programming is prohibitive for large datasets. Here, we propose a deep neural-network-based approach for learning the warping functions from training data consisting of a large number of optimal matches, and use it to predict optimal diffeomorphic warping functions. Results show prediction performance on a synthetic dataset of bump functions and two-dimensional curves from the ETH-80 dataset as well as a significant reduction in computational cost.
函数与曲线形状之间的速率不变或重新参数化不变匹配分别是计算机视觉和医学成像中的一个重要问题。通常，使用动态时间规整或动态规划等方法进行匹配的计算成本对于大型数据集来说过高。在此，我们提出一种基于深度神经网络的方法，用于从由大量最优匹配组成的训练数据中学习变形函数，并使用它来预测最优的微分同胚变形函数。结果显示了在凹凸函数合成数据集和来自ETH - 80数据集的二维曲线数据集上的预测性能，以及计算成本的显著降低。
