Abstract An efficient predictor for subjective video quality rating measures processes a reference video and an impaired video corresponding to the reference video in respective processing channels. Each channel applies a contrast sensitivity function from a human vision system model to the respective videos and a contrast discrimination function for self-masking to the output of the contrast sensitivity function. The outputs from the channels are input to a differencing circuit to obtain absolute difference values. The absolute difference values are modified by a global masking factor derived from the output from the reference video channel, and the resulting values are converted into units conforming to a standard quality rating metric.
An apparatus for efficient prediction of subjective video quality rating measures comprising: a pair of processing channels, a first channel for processing a reference video and a second channel for processing an impaired video corresponding to the reference video, the reference and impaired videos being processed directly in the respective channels according to a human vision system model without pyramid decomposition to produce a processed reference video and a processed impaired video; and means for obtaining an absolute difference between the processed reference video and the processed impaired video as a quality rating measure.
Claim 2
Independent Claim
94 words
An apparatus for efficient prediction of subjective video quality rating measures comprising: a pair of processing channels, a first channel for processing a reference video and a second channel for processing an impaired video corresponding to the reference video, the reference and impaired videos being processed directly in the respective channels according to a human vision system model without pyramid decomposition to produce a processed reference video and a processed impaired video; and means for obtaining an absolute difference between the processed reference video and the processed impaired video as a quality rating measure.
Claim 3
Dependent Claim
39 words
The apparatus as recited in claim 1 further comprising means for applying a global masking factor as a function of the processed reference video to the absolute difference, the output of the applying means being the quality rating measure.
Claim 4
Independent Claim
26 words
The apparatus as recited in claims 1 or 2 further comprising means for converting the quality rating measure to units of a standard quality rating measure.
Claim 5
Dependent Claim
70 words
The apparatus as recited in claim 1 wherein each channel comprises: a two-dimensional filter for obtaining a spatial frequency response for an input video, the two-dimensional filter emulating the human vision system model; and a contrast discrimination stage having the spatial frequency response as an input to account for the effects of self-masking, the output from the contrast discrimination stage being a processed video for input to the obtaining means.