Subjective Video Quality Prediction from Objective Video Quality to Enrich Datasets

method is proposed for the generation of set of video sequence with predictive subjective video quality (Mean Opinion Score) based on limited numberof sequences and the associated objective video quality measure (Peak Signal-to-Noise Ratio). The MOS is predicted using sigmoid function model that is optimized based on limited number of subjective tests for each video sequence. The correlation of the P-MOS to MOS achieved using this method is 0.94. The method can be used to enrich an existing video sequence dataset for the training phase in machine learning or deep leaning applications without bearing the burden and cost of the human opinion based regular subjective video quality test.