Objective evaluation of chromatic quality assessment

Abstract

This paper provides a study on the ability of Full-Reference quality metrics to measure the Quality of Experience that results on images that suffer chromatic errors. Considering this, the well known PSNR, MSSIM and VIFP will be compared with the MOS results. It is important to highlight that these measures are usually applied to the image luminance channel. However, in this study only the chromatic components of the image represented in the CIELAB color space have been changed resulting in similar values of luminosity. Moreover, the CIEDE2000 was also considered, because the knowledge of the scene illuminant allows a reliable computation. Using correlation estimates it was concluded that the CIEDE2000 and the MSSIM provides the best MOS estimation. The MSSIM results in a slightly better Pearson correlation value while the CIEDE2000 results in a better RMSE and Outlier Ratio. The VIFP also provides a good correlation, while the PSNR shows a poor correlation with the MOS values.

Intelligent Luminance Control of Lighting Systems Based on Imaging Sensor Feedback

“…The contrast reflects the salience and the difference degree between the image pixels of foreground and background. To improve the robustness of contrast evaluation, both the color region contrast [ 12 ] and the gray region contrast [ 22 ] are considered. Equation (9) shows the computation method of the gray region contrast.…”

“…Second, a series of subjective and objective Lighting Effect Evaluation Metrics (LEEMs) are defined and evaluated for these datasets above; and then the cluster benchmarks of these objective LEEMs can be obtained. The LEEMs include: the Subjective and the Objective Surface Luminance Degree [ 11 ] of Display SM SLDD and OM SLDD , the Subjective and the Objective Color Deviation Degree [ 12 ] of Display Content SM CDDDC and OM CDDDC , the Subjective and the Objective Region Contrast Degree [ 13 ] of Display Content SM RCDDC and OM RCDDC , the Subjective and the Objective Edge Blur Degree [ 14 ] of Display Content SM EBDDC and OM EBDDC , and the Objective Glare Degree [ 15 ] of Display OM GDD . Third, both a single LEEM-based control and a multiple LEEMs-based control are developed to realize a kind of optimal luminance tuning.…”