US 11,989,868 B2
Video quality assessing method and apparatus
Anant Baijal, Suwon-si (KR); and Cheulhee Hahm, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jun. 30, 2021, as Appl. No. 17/364,114.
Claims priority of application No. 10-2020-0094689 (KR), filed on Jul. 29, 2020.
Prior Publication US 2022/0036536 A1, Feb. 3, 2022
Int. Cl. G06T 7/00 (2017.01); G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06N 3/08 (2023.01); G06V 20/40 (2022.01)
CPC G06T 7/0002 (2013.01) [G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06V 20/46 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A video quality assessing method by using only a distorted image rather than a reference image, the video quality assessing method comprising:
obtaining a model-based quality score for each of a plurality of sub-areas included in a frame by using a neural network, the neural network being trained based on a mean opinion score (MOS) obtained by using an assessor display apparatus;
obtaining a screen information from a mapping table pre-stored in a user display apparatus;
obtaining a weight matrix from at least one of rendering information or the screen information about a screen included in the user display apparatus;
applying the weight matrix to the model-based quality score for each sub-area of the plurality of sub-areas; and
obtaining a quality score of the frame, based on the model-based quality score for each sub-area to which the weight matrix is applied.