a machine learning approach to no-reference objective video quality assessment for high definition resources

the video quality assessment must be adapted to the human visual system, which is why researchers have performed subjective viewing experiments in order to obtain the conditions of encoding of video systems to provide the best quality to the user. the objective of this study is to assess the video quality using image features extraction without using reference video. rmse values and processing time of svr for bmp and jpeg formats in quality assessment were 0.78×10-2, 0.81×10-2, 6.0s and 4.8s, respectively. in this study, a metric system for no-reference assessing the video quality is presented using wavelet transform and generalized gaussian distribution parameters. results of itu-bt tests for each video were used to train svr and its performance for video frames is evaluated