Figure 18 Fusion of Fig 17 and 18 using Discrete Wavelet Transform
Related Figures (20)
For the second data set, whose composite metrics are shown in Fig 21, the biologically based fusion method did well compare with other fusion techniques only when the Entropy was used as a MOE. For this data set TIR, TBIR and Fisher MOEs all decrease in going from visible to IR which is somewhat surprising. The cause can be due to the very low variance in the background regions. This figure also shows that the best results were obtained for the DWT fusion method for both entropy and FW metrics. PCA shows to have the best Fisher metrics. However this seems to be due mainly to the small variance of the target regions. In this paper we have presented the results of a study to provide a quantitative comparative analysis of a typical set of image fusion algorithms. The results were based on the a pplication of these algorithms on two sets of collocated visible (electro-optic) and infrared (IR) imagery. The quantitative comparative analysis of their per formances was based on using 5 different measures of effectiveness. These metrics were based on measuring information content and/or Fig 5. Fusion using Contrast Pyramid Fig 8. Fusion using Principle Component Analysis Fig 7. Fusion using Gradient Pyramid Fig 9. Fusion using Morphological Pyramids Fig 6. Fusion using Filter-Shift Decimate technique Fig 12. Fusion using a Biologically -inspired approach Fig 11. Fusion using Shift Invariant Wavelet Transform Fig 10. Fusion using Discrete Wavelet Transform Fig 17.Visible-band Image of a Scene Shown in Fig 16 Fig 16. Infrared Image of a Scene Showing a Man Fig 15. Image Fusion Evaluation Tool Box Fig 14. A Schematic of a Model for Biologically -inspired Image Fusion Fig 20. Fusion of Figs 17 and 18 using Total Probability Density Technique Fig 19. Fusion of Figs 17 and 18 using Laplacian Pyramid
