Objective assessment of MPEG-2 video quality

Abstract

The increasing use of video compression standards in broadcasting television systems has required, in recent years, the development of video quality measurements that take into account artifacts specifically caused by digital compression techniques. In this paper we present a methodology for the objective quality as- sessment of MPEG video streams by using circular back- propagation feedforward neural networks. Mapping neural networks can render nonlinear relationships between objective features and subjective judgments, thus avoiding any simplifying assumption on the complexity of the model. The neural network processes an in- stantaneous set of input values, and yields an associated estimate of perceived quality. Therefore, the neural-network approach turns objective quality assessment into adaptive modeling of subjective perception. The objective features used for the estimate are chosen according to the assessed relevance to perceived quality and are continuously extracted in real time from compressed video streams. The overall system mimics perception but does not require any ana- lytical model of the underlying physical phenomenon. The capability to process compressed video streams represents an important ad- vantage over existing approaches, like avoiding the stream- decoding process greatly enhances real-time performance. Experi- mental results confirm that the system provides satisfactory, continuous-time approximations for actual scoring curves concern- ing real test videos. © 2002 SPIE and IS&T.