Popular approaches to objective full reference image quality assessment use the local normalized MSE to quantify the distance between the observed and the reference image. In the present approach, multiple statistics are employed to separately analyze image structures having distinct visual impact. It is shown here how the measurement of the above statistics allows diagnostics of the reproduced image, indicating the relative amount of the impairment factors. A composite metric for overall objective image quality scoring is then defined, and applied to objective quality assessment of HDTV sequences.
Diagnostic quality monitoring of video sequences based on multiple structural analysis / V., Baroncini; L., Capodiferro; DI CLAUDIO, Elio; Iacovitti, Giovanni; F., Mangiatordi; M., Visca. - ELETTRONICO. - (2009). (Intervento presentato al convegno Fourth International Workshop on Video Processing and Quality Metrics for Consumer Electronics, VPQM2009 tenutosi a Scottsdale, Arizona, USA nel 15-16 Gennaio 2009).
Diagnostic quality monitoring of video sequences based on multiple structural analysis
DI CLAUDIO, Elio;IACOVITTI, Giovanni;
2009
Abstract
Popular approaches to objective full reference image quality assessment use the local normalized MSE to quantify the distance between the observed and the reference image. In the present approach, multiple statistics are employed to separately analyze image structures having distinct visual impact. It is shown here how the measurement of the above statistics allows diagnostics of the reproduced image, indicating the relative amount of the impairment factors. A composite metric for overall objective image quality scoring is then defined, and applied to objective quality assessment of HDTV sequences.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
