Objective image fusion performance measure

By Costas S. Xydeas, Vladimir S. Petrovic. 2000

1,952 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4883a68d4eea3ef73908d3b1068faf94a615222b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hui Li
2. Xiaojun Wu
3. Jiayi Ma
4. Yu Liu
5. Josef Kittler
6. Xun Chen
7. Shutao Li
8. Zengfu Wang

In Media Technology

1. Hui Li
2. Xiaojun Wu
3. Yu Liu
4. Jiayi Ma
5. Zengfu Wang
6. Josef Kittler
7. Xun Chen
8. Shutao Li

Citations in the corpus

• Image Fusion With Guided Filtering (2013, methodology): “4) The gradient based index Q G evaluates the success of edge information transferred from the source images to the fused image [25].”
• Multifocus Image Fusion and Restoration With Sparse Representation (2010, methodology): “In addition to the subjective evaluation, two objective evaluation criteria, i.e., 1) root mean square error (RMSE) [1] and 2) Q AB/F metric [ 37 ], are used to compare the different fusion methods.”
• Group-Sparse Representation With Dictionary Learning for Medical Image Denoising and Fusion (2012, positive): “For comparing objectively, five metrics including mutual information (MI) [33], universal quality index (UIQI) [34], QE [35], QW [35], and Q [36] are applied to assess the quality of fused results.”
• A medical image fusion method based on convolutional neural networks (2017, background): “They are the information entropy (EN ) of the fused image, the feature mutual information (FMI) [29], Xydeas-Petrovic’s gradient based metric QG [30], Piella-Heijmans’s similarity based metric QE [31], and the visual information fidelity fusion (V IFF ) metric [32].”
• An overview of multi-modal medical image fusion (2016, background): “QAB/F [63-66] measures the success of edge information transferred from the input images to the fused image.”
• Image matting for fusion of multi-focus images in dynamic scenes (2013, methodology): “The index Q proposed by Petrović and Xydeas assesses fusion performance by evaluating the amount of edge information transfer from the source images to the fused image [35].”
• Image Fusion With Convolutional Sparse Representation (2016, background): “Four popular objective metrics, namely, the entropy EN, the gradient-based metric QAB/F [35],”
• Gradient-based multiresolution image fusion (2004, methodology): “Note that in subjective tests the human visual system automatically “filters out” similarities, concentrating only on the differences effectively amplifying the score variances making them perceptually much more significant [22], [23].”
• Image fusion: Advances in the state of the art (2007, neutral): “In recent years, a number of computational image fusion quality assessment metrics have been proposed [65,66].”
• Performance comparison of different multi-resolution transforms for image fusion (2011, background): “The metric Q [37] is defined as follows:”
• A general framework for image fusion based on multi-scale transform and sparse representation (2015, methodology): “The gradient based fusion metric Q G proposed by Xydeas and Petrovic [23].”