Image Fusion Quality Measure Based on a Multi-scale Approach

SILVINA PISTONESI; JORGE MARTINEZ; ANA GEORGINA FLESIA; MARIA CRISTINA MACIEL

Proceedings 12 th International Symposium on Visual Computing (ISVC?16)

Springer

Lugar: Berlin; Año: 2016; p. 836 - 846

In this paper, we present a general purpose and non-referencemulti-scale structural similarity measure for objective quality assessmentof image fusion. We aim to extend Piella?s measure [1] in several ways,within a multi-scale approach, by making multiple Piella?s measure imageevaluations at different image scales, fusing the result into a single evaluation.The main advantage of multi-scale methods lie in its ability tocapture the relevant and useful image information at different resolutions.We validated our proposal in different imaging application scenarios, particularlyin a 2015 multi-exposure image fusion database that provideshuman subjective evaluations. Experimental results show that our approachachieves high correlation with the subjective scores provided by thedatabase and makes a significant improvement over the previous Piella?ssingle-scale fusion quality measure.