Enhanced image capture through fusion

Burt, Peter J.; Kolczynski, R.J.

doi:10.1109/iccv.1993.378222

Cited by 630 publications

(443 citation statements)

References 3 publications

Supporting

Mentioning

435

Contrasting

Unclassified

Order By: Relevance

“…It is founded on the observation that multiresolution decomposition of an image allows for localization of features at the proper scale (resolution). Early proofs of principles already exist (Burt and Kolczynski, 1993;Li et al, 1995). The basic idea is demonstrated by Figure 1 (cf.…”

Section: Multiresolution Image Fusionmentioning

confidence: 99%

“…From the composite multiresolution representation m F thus obtained, the fused image i F is derived by application of the backtransform Ψ −1 . A framework for more sophisticated fusion rules has been proposed by Burt et al (Burt and Kolczynski, 1993), for an overview of rules see (Piella, 2003b;Piella, 2003a).…”

Section: Multiresolution Image Fusionmentioning

confidence: 99%

“…For the multiresolution part of the fusion algorithm many schemes are available to us, ranging from pyramid schemes as Laplacian Pyramids (Burt and Adelson, 1983), Steerable Pyramids (Simoncelli and Freeman, 1995), Gradient Pyramids (Burt and Kolczynski, 1993), an abundance of wavelets (Mallat, 1989) and even a multigrid method solving diffusion equations on a range of grids (De Zeeuw, 2005;De Zeeuw, 2007). So far, our method of choice is the Gradient Pyramid (GP).…”

Section: Choice Of Multiresolutionmentioning

confidence: 99%

“…The gradient pyramid (Burt and Kolczynski, 1993) is derived from a Gaussian pyramid using a specific kernel. The Gaussian pyramid involves the application of a generating kernel followed by downsampling.…”

Section: Choice Of Multiresolutionmentioning

confidence: 99%

“…Figure 4 (cp. (Piella, 2003a, Figure 6.7) & (Burt and Kolczynski, 1993, Figure 2)) shows the general framework with the building blocks of importance, i.e. the computations of match measure, activity measure (saliency), the fusion decision and the combination (weights).…”

Section: Fusion Of Multimodal Imagesmentioning

confidence: 99%

See 4 more Smart Citations

Multimodality and Multiresolution Image Fusion

Zeeuw¹,

Pauwels²,

Han

2012

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Standard multiresolution image fusion of multimodal images may yield an output image with artifacts due to the occurrence of opposite contrast in the input images. Equal but opposite contrast leads to noisy patches, instable with respect to slight changes in the input images. Unequal and opposite contrast leads to uncertainty of how to interpret the modality of the result. In this paper a biased fusion is proposed to remedy this, where the bias is towards one image, the so-called iconic image, in a preferred spectrum. A nonlinear fusion rule is proposed to prevent that the fused image reverses the local contrasts as seen in the iconic image. The rule involves saliency and a local match measure. The method is demonstrated by artificial and real-life examples.

show abstract

Section: Multiresolution Image Fusionmentioning

confidence: 99%

Section: Multiresolution Image Fusionmentioning

confidence: 99%