Title :
DIBR synthesized image quality assessment based on morphological pyramids
Author :
Sandic-Stankovica, Dragana ; Kukolj, Dragan ; Le Calletc, Patrick
Author_Institution :
Inst. for Telecommun. & Electron., IRITEL, Belgrade, Serbia
Abstract :
Most Depth Image Based Rendering (DIBR) techniques produce synthesized images which contain non-uniform geometric distortions affecting edges coherency. This type of distortions are challenging for common image quality metrics. Morphological filters maintain important geometric information such as edges across different resolution levels. There is inherent congruence between the morphological pyramid decomposition scheme and human visual perception. In this paper, multi-scale measure, morphological pyramid peak signal-to-noise ratio MP-PSNR, based on morphological pyramid decomposition is proposed for the evaluation of DIBR synthesized images. It is shown that MPPSNR achieves much higher correlation with human judgment compared to the state-of-the-art image quality measures in this context.
Keywords :
edge detection; image filtering; mathematical morphology; rendering (computer graphics); visual perception; DIBR synthesized image quality assessment; MP-PSNR; depth image based rendering technique; edge coherency; human judgment; human visual perception; morphological filter; morphological pyramid; morphological pyramid decomposition scheme; morphological pyramid peak signal-to-noise ratio; multiscale measure; nonuniform geometric distortion; state-of-the-art image quality measure; Band-pass filters; Context; Distortion; Distortion measurement; Image quality; Three-dimensional displays; DIBR synthesized image quality assessment; Multi-scale PSNR; morphological pyramids;
Conference_Titel :
3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2015
Conference_Location :
Lisbon
DOI :
10.1109/3DTV.2015.7169368