Skip to main content
. 2020 Aug 8;12(2):2483–2493. doi: 10.1007/s12652-020-02386-0

Table 5.

Comparative analysis among the proposed deep transfer learning based multi-modality image fusion and the competitive approaches in terms of edge strength (maximum is better)

Group LEPN (Zhu et al. 2019) DSA (Zhu et al. 2020) CNN (Kumar et al. 2020) EGDM (Lu et al. 2014) DDcGAN (Ma et al. 2020) 3GANs (Wang et al. 2019) Proposed
G1 0.61±0.012 0.62±0.014 0.64±0.012 0.63±0.013 0.59±0.012 0.63±0.012 0.64±0.008
G2 0.62±0.014 0.62±0.015 0.62±0.012 0.62±0.012 0.62±0.011 0.61±0.009 0.62±0.009
G3 0.61±0.012 0.64±0.015 0.62±0.008 0.63±0.009 0.62±0.012 0.62±0.012 0.64±0.008
G4 0.61±0.013 0.63±0.014 0.63±0.012 0.63±0.008 0.63±0.012 0.63±0.009 0.63±0.008
G5 0.63±0.013 0.62±0.013 0.64±0.012 0.62±0.011 0.64±0.012 0.62±0.007 0.64±0.007
G6 0.61±0.014 0.61±0.011 0.62±0.011 0.62±0.011 0.63±0.008 0.62±0.012 0.63±0.008
G7 0.62±0.011 0.64±0.012 0.64±0.011 0.63±0.012 0.62±0.009 0.59±0.007 0.64±0.007
G8 0.63±0.015 0.61±0.011 0.62±0.011 0.62±0.009 0.64±0.009 0.63±0.007 0.64±0.007
G9 0.62±0.014 0.62±0.012 0.61±0.008 0.62±0.012 0.63±0.011 0.62±0.008 0.63±0.008
G10 0.59±0.013 0.64±0.012 0.63±0.008 0.62±0.011 0.63±0.012 0.59±0.008 0.64±0.008
G11 0.62±0.015 0.64±0.015 0.62±0.011 0.61±0.008 0.63±0.009 0.61±0.007 0.64±0.007
G12 0.62±0.011 0.61±0.013 0.61±0.013 0.63±0.012 0.64±0.011 0.62±0.008 0.64±0.008
G13 0.61±0.013 0.63±0.013 0.63±0.008 0.61±0.009 0.63±0.012 0.63±0.009 0.63±0.008
G14 0.63±0.014 0.64±0.014 0.59±0.012 0.64±0.012 0.63±0.009 0.63±0.012 0.64±0.009
G15 0.63±0.012 0.63±0.015 0.61±0.008 0.62±0.009 0.63±0.012 0.59±0.009 0.63±0.008
HHS Vulnerability Disclosure