Title :
Image quality assessment based on detail differences
Author :
Di Claudio, Elio D. ; Jacovitti, Giovanni
Author_Institution :
Dept. of Inf. Eng., Electron. & Telecommun. (DIET), Univ. of Rome La Sapienza, Rome, Italy
Abstract :
This paper presents a novel Full Reference method for image quality assessment based on two indices measuring respectively detail loss and spurious detail addition. These indices define a two dimensional (2D) state in a Virtual Cognitive State (VCS) space. The quality estimation is obtained as a 2D function of the VCS, empirically determined via polynomial fitting of DMOS values of training images. The method provides at the same time highly accurate DMOS estimates, and a quantitative account of the causes of quality degradation.
Keywords :
estimation theory; image processing; polynomial approximation; 2D function; DMOS estimates; DMOS values; VCS space; detail differences; full reference method; image quality assessment; polynomial fitting; quality estimation; training images; two dimensional state; virtual cognitive state space; Databases; Fitting; Image quality; Loss measurement; Noise; Transform coding; Image quality assessment; VICOM; detail analysis; gradient tensor; virtual cognitive space;
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European
Conference_Location :
Lisbon
