Laser & Optoelectronics Progress, Volume. 55, Issue 9, 91101(2018)
No Reference Video Quality Assessment Based on Transfer Learning
In video quality assessment, most researchers manually extract the features first, and then use machine learning to predict video quality score, which leads to unideal result. Since the VGG-16 net has excellent robustness in feature extraction, we use the network model and migrate parameters to construct the end-to-end video quality assessment network. The experimental results on LIVE video database show that the assessment score of this method is consistent with the subjective assessment score, and its assessment indexes of Spearman rank correlation coefficient and Pearson correlation coefficient reached 0.867 and 0.843, respectively, which indicated that the performance of the proposed method is better than most of the current video quality assessment algorithms based on manual feature extraction.
Get Citation
Copy Citation Text
Zhang Hao, Sang Qingbing. No Reference Video Quality Assessment Based on Transfer Learning[J]. Laser & Optoelectronics Progress, 2018, 55(9): 91101
Category: Imaging Systems
Received: Mar. 30, 2018
Accepted: --
Published Online: Sep. 8, 2018
The Author Email: Qingbing Sang (sangqb@163.com)