Hybrid Sharpening Transformation Approach for Multifocus Image Fusion Using Medical and Nonmedical Images

Table 1

Measurements to evaluate the experimental results.

Quality metrics	Description	Formula	What value to look for best fusion	Reference
RMSE	The RMSE is generally used to calculate the difference among the true image and resultant image by directly calculating the variations in pixel values. RMSE is highly indicating the spectral quality of the resultant image.		Lower (close to zero)	[38]
PFE	It is calculated as the norm of the difference among the corresponding pixels of the true image and resultant image to the norm of the true image.		Lower (equal to zero)	[2]
MAE	It gives the MAE of the corresponding pixels in the true image and resultant image.		Lower (equal to zero)	[2]
Entropy	Entropy (E) is a significant quantitative metric, which can be used to distinguish the texture, appearance, or information contents in the image.		Higher value	[18]
SNR	SNR is the performance measure used to find the ratio among information and noise of the resultant image.		Higher value	[39]
PSNR	PSNR is one of the significant metrics and most commonly used in fusion. PSNR is specifically used for the measurement of spatial quality in the image. The computation is performed by the value of grey levels divided by the identical pixels in the true and the resultant images.		Higher value	[40]
CC	The CORR is a quantitative metric that demonstrates the correlation among the true image and the resultant image. When the true and resultant images look the same, the value will be near to one. If the true and resultant images are dissimilar, then the value will be near zero.		Higher value (close to +1)	[30, 41]
ERGAS	ERGAS is used to calculate the quality of the resultant image in terms of the normalization average error of each channel (band) of the processed image.		Lower (equal to zero)	[42]