Image quality evaluation using image quality ruler and graphical model

Wang, Weibao; Allebach, Jan P.; Guo, Yandong

doi:10.1109/icip.2015.7351203

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the label inference problem, [14] proposes a solution based on probablistic graphical model. [15] further extends the idea to the task of image quality evaluation. There is a number of differences between their approach and this work.…”

Section: Related Workmentioning

confidence: 97%

Recover Subjective Quality Scores from Noisy Measurements

Bampis

2017

2017 Data Compression Conference (DCC)

View full text Add to dashboard Cite

Simple quality metrics such as PSNR are known to not correlate well with subjective quality when tested across a wide spectrum of video content or quality regime. Recently, efforts have been made in designing objective quality metrics trained on subjective data (e.g. VMAF), demonstrating better correlation with video quality perceived by human. Clearly, the accuracy of such a metric heavily depends on the quality of the subjective data that it is trained on. In this paper, we propose a new approach to recover subjective quality scores from noisy raw measurements, using maximum likelihood estimation, by jointly estimating the subjective quality of impaired videos, the bias and consistency of test subjects, and the ambiguity of video contents all together. We also derive closed-from expression for the confidence interval of each estimate. Compared to previous methods which partially exploit the subjective information, our approach is able to exploit the information in full, yielding tighter confidence interval and better handling of outliers without the need for z-scoring or subject rejection. It also handles missing data more gracefully. Finally, as side information, it provides interesting insights on the test subjects and video contents.

show abstract

Section: Related Workmentioning

confidence: 97%

Recover Subjective Quality Scores from Noisy Measurements

Bampis

2017

2017 Data Compression Conference (DCC)

View full text Add to dashboard Cite

show abstract

“…Image quality [1][2] is the most important performance parameter of an optical imaging system. At present, the research about it mainly focuses on the complete failure research of the product, and there is little research on the attenuation of its imaging quality.…”

Section: Introductionmentioning

confidence: 99%

Quantitative analysis of the effect of the damp heat test on optical imaging system under different scene usage conditions

Wang

Zhou²,

Yao³

2022

Second International Conference on Testing Technology and Automation Engineering (TTAE 2022)

View full text Add to dashboard Cite

As a widely used sensing device, the optical imaging system mainly includes products used in outdoor and indoor scenarios. However, there are few studies on the effect of environmental aging test on the imaging performance of the two types of products. In this paper, typical products used in two different scenarios, outdoor and indoor, are selected to investigate the quantitative impact of the damp heat test on their imaging quality. The investigated parameters used include imaging resolution, color revent and gray scale value. The study found that after about 10 cycles of damp heat test, the imaging quality of optical imaging products used indoors decreased significantly, with a decrease of more than 20% in key parameter. Outdoor use products have good tolerance to environmental testing, and there is basically no big difference. This paper will provide some reference for the rational use of optical imaging systems and the compilation of test standards.

show abstract

“…Currently, there are two methods to evaluate the imaging quality [1][2] of an imaging system. One is to analyze the electrical signal of the system [3].…”

Section: Introductionmentioning

confidence: 99%