公开(公告)号：US10430928B2

公开(公告)日：2019-10-01

申请号：US14920556

申请日：2015-10-22

申请人： Cal Poly Corporation

发明人： Erin P. J. Pearse ,  Jonathan A. Lindgren ,  Chad Eckman ,  Zachariah Zhang ,  David J. Sacco

IPC分类号： G06N5/02 ,  G06T5/00 ,  G06F17/17

摘要： Systems and methods for reconstruction of missing data using iterated geometric harmonics are described herein. A method includes receiving a dataset having missing entries, initializing missing values in the dataset with random data, and then performing the following actions for multiple iterations. The iterated actions include selecting a column to be updated, removing the selected column from the dataset, converting the dataset into a Gram matrix using a kernel function, extracting rows from the Gram matrix for which the selected column does not contain temporary values to form a reduced Gram matrix, diagonalizing the reduced Gram matrix to find eigenvalues and eigenvectors, constructing geometric harmonics using the eigenvectors to fill in missing values in the dataset, and filling in missing values to improve the dataset and create a reconstructed dataset. The result is a reconstructed dataset. The method is particularly useful in reconstructing image and video files.

公开(公告)号：US20160117605A1

公开(公告)日：2016-04-28

申请号：US14920556

申请日：2015-10-22

申请人： Cal Poly Corporation

发明人： Erin P.J. Pearse ,  Jonathan A. Lindgren ,  Chad Eckman ,  Zachariah Zhang ,  David J. Sacco

IPC分类号： G06N99/00 ,  G06F17/16

CPC分类号： G06T5/005 ,  G06F17/175 ,  G06T2207/20076 ,  G06T2207/30201

摘要： Systems and methods for reconstruction of missing data using iterated geometric harmonics are described herein. A method includes receiving a dataset having missing entries, initializing missing values in the dataset with random data, and then performing the following actions for multiple iterations. The iterated actions include selecting a column to be updated, removing the selected column from the dataset, converting the dataset into a Gram matrix using a kernel function, extracting rows from the Gram matrix for which the selected column does not contain temporary values to form a reduced Gram matrix, diagonalizing the reduced Gram matrix to find eigenvalues and eigenvectors, constructing geometric harmonics using the eigenvectors to fill in missing values in the dataset, and filling in missing values to improve the dataset and create a reconstructed dataset. The result is a reconstructed dataset. The method is particularly useful in reconstructing image and video files.

摘要翻译： 本文描述了使用迭代几何谐波重建丢失数据的系统和方法。 一种方法包括接收具有缺失条目的数据集，使用随机数据初始化数据集中的缺失值，然后对多次迭代执行以下操作。 迭代操作包括选择要更新的列，从数据集中移除所选列，使用内核函数将数据集转换为格阵，从所选列不包含临时值的Gram矩阵中提取行，形成 减少的Gram矩阵，使缩减的Gram矩阵对角化，找到特征值和特征向量，使用特征向量来构建几何谐波，以填补数据集中的缺失值，并填充缺失值以改进数据集并创建重构数据集。 结果是一个重建的数据集。 该方法在重建图像和视频文件中特别有用。