Image quality assessment for performance evaluation of image fusion

We present a novel approach on objective non-reference image fusion performance assessment. The Global-Local Image Quality Analysis (GLIQA) approach takes into account local measurements to estimate how well the important information in the source images is represented by the fused image. The metric is an extended version of the Universal Image Quality Index (UIQI) and uses the similarity between blocks of pixels in the input images and the fused image as the weighting factors. When the difference of an image pixel in the input images and its correspondence in the fused image is larger than a threshold and difficult to assess the fusion quality, global measurements will be applied to assist the judgment. The global measurement metric considers a set of properties of human Gestalt visual perception, such as image structure, texture, and spectral signature, for image quality assessment. Preliminary study results confirm that the performance scores of the proposed metrics correlate well with the subjective quality of the fused images.