arrow
Volume 34, Issue 2
Variational Image Fusion with First and Second-Order Gradient Information

Fang Li & Tieyong Zeng

J. Comp. Math., 34 (2016), pp. 200-222.

Published online: 2016-04

Export citation
  • Abstract

Image fusion is important in computer vision where the main goal is to integrate several sources images of the same scene into a more informative image. In this paper, we propose a variational image fusion method based on the first and second-order gradient information. Firstly, we select the target first-order and second-order gradient information from the source images by a new and simple salience criterion. Then we build our model by requiring that the first-order and second-order gradient information of the fused image match with the target gradient information, and meanwhile the fused image is close to the source images. Theoretically, we can prove that our variational model has a unique minimizer. In the numerical implementation, we take use of the split Bregman method to get an efficient algorithm. Moreover, four-direction difference scheme is proposed to discrete gradient operator, which can dramatically enhance the fusion quality. A number of experiments and comparisons with some popular existing methods demonstrate that the proposed model is promising in various image fusion applications.

  • Keywords

Image fusion, Feature selection, Bounded variation, Second bounded variation, Split Bregman.

  • AMS Subject Headings

65N06, 65B99.

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address

fli@math.ecnu.edu.cn (Fang Li)

zeng@hkbu.edu.hk (Tieyong Zeng)

  • BibTex
  • RIS
  • TXT
@Article{JCM-34-200, author = {Li , Fang and Zeng , Tieyong}, title = {Variational Image Fusion with First and Second-Order Gradient Information}, journal = {Journal of Computational Mathematics}, year = {2016}, volume = {34}, number = {2}, pages = {200--222}, abstract = {

Image fusion is important in computer vision where the main goal is to integrate several sources images of the same scene into a more informative image. In this paper, we propose a variational image fusion method based on the first and second-order gradient information. Firstly, we select the target first-order and second-order gradient information from the source images by a new and simple salience criterion. Then we build our model by requiring that the first-order and second-order gradient information of the fused image match with the target gradient information, and meanwhile the fused image is close to the source images. Theoretically, we can prove that our variational model has a unique minimizer. In the numerical implementation, we take use of the split Bregman method to get an efficient algorithm. Moreover, four-direction difference scheme is proposed to discrete gradient operator, which can dramatically enhance the fusion quality. A number of experiments and comparisons with some popular existing methods demonstrate that the proposed model is promising in various image fusion applications.

}, issn = {1991-7139}, doi = {https://doi.org/10.4208/jcm.1512-m2014-0008}, url = {http://global-sci.org/intro/article_detail/jcm/9791.html} }
TY - JOUR T1 - Variational Image Fusion with First and Second-Order Gradient Information AU - Li , Fang AU - Zeng , Tieyong JO - Journal of Computational Mathematics VL - 2 SP - 200 EP - 222 PY - 2016 DA - 2016/04 SN - 34 DO - http://doi.org/10.4208/jcm.1512-m2014-0008 UR - https://global-sci.org/intro/article_detail/jcm/9791.html KW - Image fusion, Feature selection, Bounded variation, Second bounded variation, Split Bregman. AB -

Image fusion is important in computer vision where the main goal is to integrate several sources images of the same scene into a more informative image. In this paper, we propose a variational image fusion method based on the first and second-order gradient information. Firstly, we select the target first-order and second-order gradient information from the source images by a new and simple salience criterion. Then we build our model by requiring that the first-order and second-order gradient information of the fused image match with the target gradient information, and meanwhile the fused image is close to the source images. Theoretically, we can prove that our variational model has a unique minimizer. In the numerical implementation, we take use of the split Bregman method to get an efficient algorithm. Moreover, four-direction difference scheme is proposed to discrete gradient operator, which can dramatically enhance the fusion quality. A number of experiments and comparisons with some popular existing methods demonstrate that the proposed model is promising in various image fusion applications.

Fang Li & Tieyong Zeng. (2020). Variational Image Fusion with First and Second-Order Gradient Information. Journal of Computational Mathematics. 34 (2). 200-222. doi:10.4208/jcm.1512-m2014-0008
Copy to clipboard
The citation has been copied to your clipboard