Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (10): 2862-2868.DOI: 10.11772/j.issn.1001-9081.2018020482

Previous Articles     Next Articles

Data fusion algorithm of coupled images

REN Xiaoxu1, LYU Liangfu1, CUI Guangtai2   

  1. 1. School of Mathematics, Tianjin University, Tianjin 300072, China;
    2. School of Science, Hohai University, Nanjing Jiangsu 211100, China
  • Received:2018-03-09 Revised:2018-05-20 Online:2018-10-10 Published:2018-10-13
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Tianjin (15JCQNJC00200).


任晓旭1, 吕良福1, 崔广泰2   

  1. 1. 天津大学 数学学院, 天津 300072;
    2. 河海大学 理学院, 南京 211100
  • 通讯作者: 吕良福
  • 作者简介:任晓旭(1994-),女,河北保定人,硕士研究生,主要研究方向:机器学习、稀疏优化;吕良福(1979-),男,山东潍坊人,副教授,博士,主要研究方向:机器学习、稀疏优化;崔广泰(1996-),男,山东潍坊人,主要研究方向:机器学习、稀疏优化。
  • 基金资助:

Abstract: Coupled data fusion algorithms mainly improve estimation accuracy and explain related latent variables of the other coupled data sets by using the information of one data set. Aiming at the large number of coupled images existing in reality, based on the Coupled Matrix and Tensor Factorization-OPTimization (CMTF-OPT) algorithm in coupled data fusion, a Coupled Images Factorization-OPTimization (CIF-OPT) algorithm for coupled images was proposed. The corresponding theoretical analysis and experimental results show that the effects of coupled image fusion by CIF-OPT algorithm under different noise influence are robust, and better than those by other coupling algorithms. Particularly, the CIF-OPT algorithm can accurately restore an image of missing some data elements with its coupled image at a certain probability.

Key words: data fusion, coupled image, matrix decomposition, tensor decomposition, optimization algorithm

摘要: 耦合数据的融合算法主要通过利用其中一个数据集的信息提高对其他耦合数据集的估计精度和完善对相关潜变量的解释。针对现实中存在的大量耦合图像,基于耦合数据融合中的耦合矩阵和张量分解优化(CMTF-OPT)算法,提出一种针对耦合图像的耦合图像分解优化(CIF-OPT)算法。相应的理论分析及实验结果表明,不同噪声影响下用CIF-OPT算法进行耦合图像融合后的效果均具有鲁棒性,且融合效果优于其他耦合算法(如:CMTF-OPT算法)。特别地,针对其中缺失数据元素的图像,CIF-OPT算法可以利用与其耦合的图像,对缺失数据元素的图像进行精确的数据恢复。

关键词: 数据融合, 耦合图像, 矩阵分解, 张量分解, 优化算法

CLC Number: