图像融合评价指标之QCBChen and Blum (2009)

https://doi.org/10.1007/s12652-019-01199-0

 Chen and Blum (2009) proposed a perceptual quality evaluation method for image fusion that is based on human visual system (HVS) models.

In this metric, the source and fused images are filtered by a contrast sensitivity function (CSF) after computing a local contrast map for each image.

Then, a contrast preservation map is generated to describe the relationship between the fused image and each source image.

Finally, the preservation maps are weighted by a saliency map to obtain an overall quality map. The mean of the quality map indicates the quality of the fused image. 

========================================================================

https://doi.org/10.1007/s00521-020-05358-9

 Qcb is a perceptual quality measure for image fusion, which employs the major features in a human visual system model [3]. Consider two input images IA and IB, and a resulting fused image IF. All of the images are filtered by an empirical CSF using a DOG filter and Fourier transform.

The local contrast is defined as 

A common choice for uj would be a Gaussian kernel with a standard deviation of

Then, the masked contrast map for input image IAðx; yÞ is calculated as .***** where t, h, p, q, and Z are real scalar parameters that determine the shape of the nonlinearity of the masking function. Normally, t = 1, h = 1, p = 3, q = 2, Z = 0.0001.

After the masked contrast map is calculated, the salience map for IAðx; yÞ is defined as kAðx;

The information preservation value is QAF

We can obtain the global quality map as QGQM

Finally, the metric value is obtained by averaging the global quality map:

A larger value of any of the above three metrics indicates better fusion performance. A good comprehensive survey of quality metrics can be found in Liu et al. [24]. For fair comparison, we use appropriate default parameters for these metrics, and all codes are derived from their public codes [23].