1 August 2005 Objective evaluation of signal-level image fusion performance
Vladimir S. Petrovic, Costas S. Xydeas
Author Affiliations +
Abstract
An objective measurement framework for signal-level image fusion performance, based on a direct comparison of visual information in the fused and input images, is proposed. The aim is to model and predict subjective fusion performance results otherwise obtained through extremely time- and resource-consuming perceptual evaluation procedures. The measure associates visual information with edge, or gradient, information that is initially parametrized at all locations of the inputs and the fused image. A perceptual-information preservation model is then used to quantify the success of information fusion as the accuracy with which local gradient information is transferred from the inputs to the fused image. By considering the perceptual importance of different image regions, such local fusion success estimates are integrated into a single, numerical fusion performance score between 0 (total information loss) and 1 (ideal fusion). The proposed metric is optimized and validated using extensive subjective test results and validation procedures. The results clearly indicate that the proposed metric is perceptually meaningful in that it corresponds well with the results of perceptual fusion evaluation. Finally, an application of the proposed evaluation approach to fusion algorithm selection and fusion parameter optimization demonstrates its general usefulness.
©(2005) Society of Photo-Optical Instrumentation Engineers (SPIE)
Vladimir S. Petrovic and Costas S. Xydeas "Objective evaluation of signal-level image fusion performance," Optical Engineering 44(8), 087003 (1 August 2005). https://doi.org/10.1117/1.2009764
Published: 1 August 2005
Lens.org Logo
CITATIONS
Cited by 70 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image fusion

Atrial fibrillation

Information visualization

Visualization

Information fusion

Discrete wavelet transforms

Image processing

RELATED CONTENT


Back to Top