Objective image fusion performance measure
TL;DR: Experimental results clearly indicate that this metric reflects the quality of visual information obtained from the fusion of input images and can be used to compare the performance of different image fusion algorithms.
Abstract: A measure for objectively assessing the pixel level fusion performance is defined. The proposed metric reflects the quality of visual information obtained from the fusion of input images and can be used to compare the performance of different image fusion algorithms. Experimental results clearly indicate that this metric is perceptually meaningful.
Citations
More filters
TL;DR: Experimental results demonstrate that the proposed method can obtain state-of-the-art performance for fusion of multispectral, multifocus, multimodal, and multiexposure images.
Abstract: A fast and effective image fusion method is proposed for creating a highly informative fused image through merging multiple images. The proposed method is based on a two-scale decomposition of an image into a base layer containing large scale variations in intensity, and a detail layer capturing small scale details. A novel guided filtering-based weighted average technique is proposed to make full use of spatial consistency for fusion of the base and detail layers. Experimental results demonstrate that the proposed method can obtain state-of-the-art performance for fusion of multispectral, multifocus, multimodal, and multiexposure images.
1,300 citations
Additional excerpts
...First, the base and detail layers of different source images are fused together by weighted averaging B = N∑ n=1 WBn Bn (17) D = N∑ n=1 WDn Dn. (18) Then, the fused image F is obtained by combining the fused base layer B and the fused detail layer D F = B + D. (19)...
[...]
TL;DR: The results show that the measure represents how much information is obtained from the input images and is meaningful and explicit.
Abstract: Mutual information is proposed as an information measure for evaluating image fusion performance. The proposed measure represents how much information is obtained from the input images. No assumption is made regarding the nature of the relation between the intensities in both input modalities. The results show that the measure is meaningful and explicit.
1,059 citations
TL;DR: A general image fusion framework by combining MST and SR to simultaneously overcome the inherent defects of both the MST- and SR-based fusion methods is presented and experimental results demonstrate that the proposed fusion framework can obtain state-of-the-art performance.
952 citations
Cites methods from "Objective image fusion performance ..."
...The gradient based fusion metric Q G proposed by Xydeas and Petrovic [23]....
[...]
TL;DR: It is concluded that although various image fusion methods have been proposed, there still exist several future directions in different image fusion applications and the researches in the image fusion field are still expected to significantly grow in the coming years.
871 citations
Cites background from "Objective image fusion performance ..."
...For instance, Xydeas and Petrović propose a gradient-based fusion metric which estimates the amount of edge information that is transferred from the inputs to the fusion result [104]....
[...]
TL;DR: A new multi-focus image fusion method is primarily proposed, aiming to learn a direct mapping between source images and focus map, using a deep convolutional neural network trained by high-quality image patches and their blurred versions to encode the mapping.
826 citations
References
More filters
TL;DR: In this article, an image fusion scheme based on the wavelet transform is presented, where wavelet transforms of the input images are appropriately combined, and the new image is obtained by taking the inverse wavelet transformation of the fused wavelet coefficients.
1,532 citations
Book•
01 Apr 1993TL;DR: This book examines the current status of what is known (and not known) about human vision, how human observers interpret visual data, and how to present such data to facilitate their interpretation and use.
Abstract: From the Publisher:
This book examines the current status of what is known (and not known) about human vision, how human observers interpret visual data, and how to present such data to facilitate their interpretation and use. Written by experts who are able to cross disciplinary boundaries, the book provides an educational pathway through several models of human vision; describes how the visual response is analyzed and quantified; presents current theories of how the human visual response is interpreted; discusses the cognitive responses of human observers; and examines such applications as space exploration, manufacturing, surveillance, earth and air sciences, and medicine. The book is intended for everyone with an undergraduate-level background in science or engineering with an interest in visual science.
128 citations
"Objective image fusion performance ..." refers methods in this paper
...Notice that this visual to edge information association is supported by Human Visual System [4] studies and is extensively used in image analysis and compression systems....
[...]
12 Mar 1999
TL;DR: Preliminary subjective image fusion results demonstrate clearly the advantage which the proposed cross-band selection technique offers, when compared to conventional area based pixel selection.
Abstract: The work described in this paper focuses on cross band pixel selection as applied to pixel level multi-resolution image fusion. In addition, multi-resolution analysis and synthesis is realized via QMF sub-band decomposition techniques. Thus cross-band pixel selection is considered with the aim of reducing the contrast and structural distortion image artifacts produced by existing wavelet based, pixel level, image fusion schemes. Preliminary subjective image fusion results demonstrate clearly the advantage which the proposed cross-band selection technique offers, when compared to conventional area based pixel selection.
39 citations