Assessment of image fusion procedures using entropy, image quality, and multispectral classification

By John Roberts, J. V. van Aardt, Fethi B. Ahmed. 2008

796 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Media Technology

View Paper: https://www.semanticscholar.org/paper/cdf32c034acd2002ca0d7cdf5dd249f0b7281a7c

How researchers see this paper

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

In Artificial Intelligence

1. Hui Li
2. Tariq Salim Durrani
3. Xiaojun Wu
4. Josef Kittler
5. Xiao-Ping Zhang
6. Wei Zhong
7. Xin Fan
8. Zhongxuan Luo

In Media Technology

1. Jiayi Ma
2. Hui Li
3. Linfeng Tang
4. Xiaojun Wu
5. Josef Kittler
6. Yiannis Demiris
7. Xingchen Zhang
8. Hao Zhang

Citations in the corpus

• DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion (2020, methodology): “Eight metrics such as entropy (EN) [50], mean gradient (MG), spatial frequency (SF), standard deviation (SD) [51], peak signal-to-noise ratio (PSNR), and correlation coefficient (CC), structural similarity index measure (SSIM) [52] and visual information fidelity (VIF) [53] are used for evaluation.”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, background): “Four objec-tive metrics are leveraged for the comparison, including entropy (EN)[48], standard deviation (SD)[49], spatial frequency (SF)[50] and the sum of the correlations of differences (SCD)[51].”
• RFN-Nest: An end-to-end residual fusion network for infrared and visible images (2021, methodology): “En[47] S D[48] MI[49] Nab f [50] S CD[51] MS-SSIM[52] No-nest 6.”
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection (2022, background): “Besides, three evaluation metrics, i.e. , mutual information (MI) [30], entropy (EN) [31] and standard deviation (SD) [1] are introduced for evaluation.”
• CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach (2024, methodology): “Furthermore, six image quality metrics are utilized to assess the objective evaluation, which includes: Entropy (En) [65]; Standard Deviation (SD) [66]; Mutual Information (MI) [67]; Image feature based Mutual Information ( FMI dct , FMI pixel ) [68]; the sum of correlations of di ff erences (SCD)…”
• STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection (2021, methodology): “In this article, four popular metrics are selected, including EN [29], MI [30], VIF [31], and SF [32].”
• MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion (2018, background): “These are: entropy(En) [38]; mutual information(M I ) [10] indicates how much features are”
• GANMcC: A Generative Adversarial Network With Multiclassification Constraints for Infrared and Visible Image Fusion (2021, methodology): “In this work, six metrics are used to achieve this goal, which are structural similarity index measure (SSIM) [48], correlation coefficient (CC) [49], sum of the correlations of differences (SCD) [50], entropy (EN) [51], standard deviation (SD) [52], and mutual information (MI) [53].”
• NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention Models (2020, background): “These are: 1) entropy (En) [44]; 2) standard deviation (SD) [45]; 3) mutual information (MI) [46]; 4) FMIdct; and 5) FMIw [47], which calculates mutual information (FMI) for the discrete cosine transform and the region feature; the modified structural similarity for no-reference image (SSIMa); and v”