Nonintrusive Method Based on Neural Networks for Video Quality of Experience Assessment

Table 1

Comparative table of the main QoE metrics.

Metric	Standard	Class	Estimate	Type
PSNR		Objective	Pixel-by-pixel comparison between reference image and compressed image.	FR
VQM; (Video Quality Metric)	NTIA	Objective	Sequences are divided into temporal-space blocks. Calculate the orientation of each block using spatial luminance gradient. Score tends to 0 (best).; Assess blurring, global noise, block distortion, and color distortion	RR
SSIM; (Structural Similarity Index)		Objective	Find the mean, variance, and covariance within a frame and combine them in a distortion map. Use luminance, contrast, and structure similarity.; Use decimal value from 0 to 1 (high correlation with original picture).	FR
MOS	ITU-T P.800	Subjective	Subjective scale from 1 (poor) to 5 (good).	NA