An audio-visual objective quality model based on BP neutral network

This article proposes an audio-visual objective quality model, which is adaptive to the content changes. The major disadvantage of most existing models is that there is no unified model to evaluate the quality according to the content. So we firstly extracted the audio and video features and the correlation of the audio and video. Then we used BP neutral network to build the model, and used the subjective test to train and verify the model. The result of the test shows that this model is better than the second-order model.