Image Fusion


Rui Shen


Overview

(Pixel-level) image fusion aims to create a single informative representation of the scene by combining images captured from different sensors or from the same sensor under different configurations. Applications include but are not limited to fusion of multi-exposure images, fusion of multi-focus images, fusion of flash and ambient-light images, fusion of medical images, fusion of visible and infrared images, and fusion of remote sensing images.

Although a formulation, framework, or algorithm is generally proposed in the context of one application to demonstrate its effectiveness, the same formulation, framework, or algorithm is normally applicable (sometimes directly applicable) to other applications as well.

Multiple Exposure Fusion

Multiple exposure fusion combines information from images captured under different exposures. In this project [1][3][4], Generalized Random Walks and (Hierarchical) Multivariate Gaussian Conditional Random Field were applied to solve this problem.

Medical Image Fusion

Medical image fusion combines information from images captured from one or more medical imaging modalities. In this project [2][4], Multiscale Random Walks was applied to solve this problem, which results in a cross-scale fusion rule. In particular, 3D images were considered in the validation of the fusion algorithm.

Related Publications

[1]. Rui Shen, Irene Cheng, and Anup Basu. QoE-Based Multi-Exposure Fusion in Hierarchical Multivariate Gaussian CRF. IEEE Transactions on Image Processing, vol. 22, no. 6, pages 2469-2478, 2013. [Type(s) of fusion applications discussed: Fusion of multi-exposure images][Probabilistic Model Page]

[2]. Rui Shen, Irene Cheng, and Anup Basu. Cross-Scale Coefficient Selection for Volumetric Medical Image Fusion. IEEE Transactions on BioMedical Engineering, vol. 60, no. 4, pages 1069-1079, 2013. [Type(s) of fusion applications discussed: Fusion of medical images]

[3]. Rui Shen, Irene Cheng, Jianbo Shi, and Anup Basu. Generalized Random Walks for Fusion of Multi-Exposure Images. IEEE Transactions on Image Processing, vol. 20, no. 12, pages 3634-3646, 2011. [Type(s) of fusion applications discussed: Fusion of multi-exposure images][Probabilistic Model Page][TIP11 Page]

[4]. Rui Shen. Probabilistic Methods for Discrete Labeling Problems in Digital Image Processing and Analysis. PhD Thesis, University of Alberta, 2012. [Type(s) of fusion applications discussed: Fusion of multi-exposure images, fusion of multi-focus images, fusion of flash and ambient-light images, and fusion of medical images][Probabilistic Model Page]

Patents

[1]. Rui Shen. Method and System for Fusing Multiple Images. US Patent 9,053,558, 2015.

 

More to Come...