No-reference video quality assessment for MPEG-2 video streams using BP neural networks

Authors:
Xiuhua Jiang;Yuxia Wang;Caihong Wang
Affiliations:
Communication University of China, Beijing, China;Communication University of China, Beijing, China;Communication University of China, Beijing, China
Venue:
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
Year:
2009

Citing 4
Cited 1

The use of psychophysical data and models in the analysis of display system performance

Digital images and human vision
DCT-domain blind measurement of blocking artifacts in DCT-coded images

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Blind Image Quality Assessment for Measuring Image Blur

CISP '08 Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 1 - Volume 01
Objective quality assessment of MPEG-2 video streams by using CBP neural networks

IEEE Transactions on Neural Networks

A personalized QoE-aware handover decision based on distributed reinforcement learning

Wireless Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An objective quality assessment method for MPEG-2 video in the compressed domain is proposed in this paper. We extract various features directly from the streams and select five representative features as the inputs of our model. By means of an artificial neural network (ANN) with BP algorithm, those selected features are linked the corresponding subjective assessments in order to obtain the reliable objective scores. The experimental results show that our model can achieve good performance for the video quality prediction. Furthermore, since it requires neither the original picture, nor the decoding process, this measure could be used for real-time multimedia applications.