2 June 2011 Perception-based image/video quality metric using CIELAB color space
Author Affiliations +
Abstract
This paper addresses the problem of color image quality assessment. The paper presents a novel image/ video quality metrics, Color-SSIM (color-based structural similarity index), based on CIELAB color model. The main drawback of the SSIM algorithm in the spatial domain is that it is highly sensitive to the translation, rotation and scaling of images. This problem can be solved by applying SSIM to the individual channels of a color image in CIELAB color space and by combining the results from the individual channels into a weighted vector mean. Experimental results show that proposed quality metric is highly correlated with the experimental data collected through subjective experiments.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sertan Kaya, Sertan Kaya, Travis Bennett, Travis Bennett, Mariofanna Milanova, Mariofanna Milanova, John Talburt, John Talburt, Brian Tsou, Brian Tsou, Marina Altynova, Marina Altynova, Hongyan Xu, Hongyan Xu, } "Perception-based image/video quality metric using CIELAB color space", Proc. SPIE 8019, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense X, 801908 (2 June 2011); doi: 10.1117/12.883682; https://doi.org/10.1117/12.883682
PROCEEDINGS
6 PAGES


SHARE
Back to Top