A novel methodology for mapping objective video quality metrics to the subjective MOS scale

Moldovan, Arghir-Nicolae; Ghergulescu, Ioana; Muntean, Cristina Hava

doi:10.1109/bmsb.2014.6873572

Cited by 27 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 summarizes the PSNR and SSIM results of the proposed and reference methods; these results provide the average values for 100 intensity images that were numerically obtained. The PSNR and SSIM of the proposed method are less than those of the reference method; however, they exceeds the standard of fair quality images (PSNR is 25 dB and SSIM is 0.88 higher) [32]. Thus, from the quantitative results, we confirmed that the proposed method can reconstruct the 3D images with sufficient image quality.…”

Section: B Image Qualitysupporting

confidence: 52%

Approximated Wavefront Composition for Computer-Generated Holograms Based on Tiny Logic Operations

Nishitsuji,

Shimobaba,

Shiraki

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Accelerating the calculation of computer-generated holograms (CGHs) is an urgent requirement for realizing practical electro-holography for three-dimensional (3D) displays. Although many algorithms have been developed for fast CGH calculations, sufficient acceleration of the CGH calculations is yet to be achieved. Simplifying CGH calculations using the redundancy of a hologram while recording a 3D image is a promising way for CGH acceleration. That is, the feature that a hologram can reproduce the 3D image almost correctly even if it was recorded with deviations originating from the approximation, etc., can be used to perform the CGH calculations rapidly. Therefore, this study proposes an approximation method for trigonometric functions, which have a heavy computational load and are heavily used in the composition process of the wavefronts emitted from a virtual 3D object such as point-light sources. The proposed method substitutes sin or cos functions with tiny logic operations that are expected to have lower computational loads than the normal functions for fixed or floating precision numbers. Numerical and optical experiments showed that the proposed method can calculate CGH 2.20 times faster on a central processing unit (CPU) and 8.43 times faster on a graphics processing unit (GPU) than the normal implementation, while maintaining sufficient image quality. The proposed method is not only effective in CPU and GPU implementations but also is expected to make a significant contribution to future circuit implementations for CGH-specific computers.

show abstract

Section: B Image Qualitysupporting

confidence: 52%

Approximated Wavefront Composition for Computer-Generated Holograms Based on Tiny Logic Operations

Nishitsuji,

Shimobaba,

Shiraki

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This paper extends our preliminary work [14] with a detailed description of the VQAMap mechanism as well as a comprehensive evaluation conducted on data from three public databases (i.e., ECVQ, EVVQ and LIVEM). The paper also illustrates how VQAMap can be used to create mapping rules for six different full-reference metrics (i.e., PSNR, 0018-9316 c 2016 IEEE.…”

Section: Introductionmentioning

confidence: 98%

VQAMap: A Novel Mechanism for Mapping Objective Video Quality Metrics to Subjective MOS Scale

Moldovan

Ghergulescu²,

Muntean

2016

IEEE Trans. on Broadcast.

Self Cite

View full text Add to dashboard Cite

The reliable estimation of video quality has become increasingly important with the proliferation of online video services and users becoming more quality aware. A multitude of objective video quality assessment (VQA) metrics with various performance and complexity have been proposed. However, their applicability in real-world scenarios is limited by the lack of clear interpretations of how the metric values reflect the subjective user-perceived video quality. This paper proposes a novel mechanism called VQAMap, that uses data from public VQA databases and enables to automatically create generic rules for mapping the values of objective VQA metrics to the subjective MOS scale (i.e., 1 -bad, 2 -poor, 3 -fair, 4 -good, and 5 -excellent). An extensive evaluation study of VQAMap was conducted using data from three public VQA databases, considering six objective VQA metrics. The results analysis has shown that VQAMap provides mapping rules with quality estimation accuracy as high as 95%, while the variation in performance being caused by the varying accuracy of the different objective metrics.Index Terms-Video quality assessment (VQA), mean opinion score (MOS), subjective methods, objective metrics, video quality mapping, performance evaluation, public video quality databases.

show abstract

“…Users are exposed to distorted videos and through this process a mean opinion score (MOS) is derived [19]. Although subjective methods are the most accurate way for VQA [20], they require resources and are time-consuming. This is the reason why objective methods are more attractive to researchers and a lot of work has been done towards developing objective quality metrics [21].…”

Section: Introductionmentioning

confidence: 99%

Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment

Margetis

Tsagkatakis

Stamou

et al. 2023

Sensors

View full text Add to dashboard Cite

Existing video Quality-of-Experience (QoE) metrics rely on the decoded video for the estimation. In this work, we explore how the overall viewer experience, quantified via the QoE score, can be automatically derived using only information available before and during the transmission of videos, on the server side. To validate the merits of the proposed scheme, we consider a dataset of videos encoded and streamed under different conditions and train a novel deep learning architecture for estimating the QoE of the decoded video. The major novelty of our work is the exploitation and demonstration of cutting-edge deep learning techniques in automatically estimating video QoE scores. Our work significantly extends the existing approach for estimating the QoE in video streaming services by combining visual information and network conditions.

show abstract

A novel methodology for mapping objective video quality metrics to the subjective MOS scale

Cited by 27 publications

References 21 publications

Approximated Wavefront Composition for Computer-Generated Holograms Based on Tiny Logic Operations

Approximated Wavefront Composition for Computer-Generated Holograms Based on Tiny Logic Operations

VQAMap: A Novel Mechanism for Mapping Objective Video Quality Metrics to Subjective MOS Scale

Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment

Contact Info

Product

Resources

About