&lt;title&gt;Evaluation model considering static-temporal quality degradation and human memory for SSCQE video quality&lt;/title&gt;

Horita, Yuukou; Miyata, Takamichi; Gunawan, Irwan Prasetya; Murai, Tetsuya; Ghanbari, M.

doi:10.1117/12.502638

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ninassi et al [36] proposed to take into account the temporal variation of spatial distortions in the temporal pooling process. In [24], [37], and [38], the authors considered the asymmetric human behavior in responding to quality degradation and improvement.…”

Section: B Exploiting Temporal Information For Video Quality Assessmentmentioning

confidence: 99%

“…Compared with our preliminary work [40] in which motion information of the video was not considered and with most previous studies, the contribution of the proposed VQM comes from the extensive use of motion information to simulate the HVS processing, that is, motion vectors are derived in the wavelet domain, and employed in the eye-movement model, the spatiovelocity CSF, the motion-based temporal masking, and so on. We also simulate cognitive human behavior, which originally was proposed to be used in continuous quality evaluations [37], [38], and have proved its effectiveness in sequence-level quality prediction. In Section II-B, an introduction is given on how the previous VQMs use motion information and HVS characteristics for video quality assessment.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments

Ngan

2012

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Video quality assessment plays a fundamental role in video processing and communication applications. In this paper, we study the use of motion information and temporal human visual system (HVS) characteristics for objective video quality assessment. In our previous work, two types of spatial distortions, i.e., detail losses and additive impairments, are decoupled and evaluated separately for spatial quality assessment. The detail losses refer to the loss of useful visual information that will affect the content visibility, and the additive impairments represent the redundant visual information in the test image, such as the blocking or ringing artifacts caused by data compression and so on. In this paper, a novel full-reference video quality metric is developed, which conceptually comprises the following processing steps: 1) decoupling detail losses and additive impairments within each frame for spatial distortion measure; 2) analyzing the video motion and using the HVS characteristics to simulate the human perception of the spatial distortions; and 3) taking into account cognitive human behaviors to integrate frame-level quality scores into sequence-level quality score. Distinguished from most studies in the literature, the proposed method comprehensively investigates the use of motion information in the simulation of HVS processing, e.g., to model the eye movement, to predict the spatio-temporal HVS contrast sensitivity, to implement the temporal masking effect, and so on. Furthermore, we also prove the effectiveness of decoupling detail losses and additive impairments for video quality assessment. The proposed method is tested on two subjective quality video databases, LIVE and IVP, and demonstrates the state-of-the-art performance in matching subjective ratings.Index Terms-Human visual system (HVS), spatial distortions decoupling, video quality assessment.

show abstract

Section: B Exploiting Temporal Information For Video Quality Assessmentmentioning

confidence: 99%

mentioning

confidence: 99%

Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments

Ngan

2012

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…We can also classify PVQMs with regard to reference requirements: doubleended and single-ended. Double-ended metrics require both the reference (original) signal and the test (processed) signal, and can be further divided into two subclasses: reduced-reference (RR) metrics [57,185] that need only part of the reference signal and full-reference (FR) ones [17,139,140,167]) that need the complete reference signal. Single-ended metrics use only the processed signal, and are therefore also called no-reference (NR) ones [35,120,189].…”

Section: Perceptual Visual Quality Metrics (Pvqms)mentioning

confidence: 99%

“…The metric performed well in the VQEG FR-TV Phase II Test [157]. For another RR metric proposed in [57], spatial features are computed for the luminance image, and temporal features are obtained by the frame difference and global motion detection.…”

Section: Metrics With Referencementioning

confidence: 99%

Perceptual visual quality metrics: A survey

Wang

Kuo

2011

Journal of Visual Communication and Image Representation

827

346

View full text Add to dashboard Cite

“…If only partial information or no information of the original image or video is available, RR and NR IQA measures can be utilized. RR measures often extract important features from the original image or video, and utilize these features to assist quality assessment [11,32]. NR measures directly infer the quality of the degraded image or video, for example based on natural scene statistics (NSS) [21].…”

Section: Related Workmentioning

confidence: 99%

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Liu

Wang

2016

Sens Imaging

View full text Add to dashboard Cite

Traditionally, image compression was optimized for the pixel-wise fidelity or the perceptual quality of the compressed images given a bit-rate budget. But recently, compressed images are more and more utilized for automatic semantic analysis tasks such as recognition and retrieval. For these tasks, we argue that the optimization target of compression is no longer perceptual quality, but the utility of the compressed images in the given automatic semantic analysis task. Accordingly, we propose to evaluate the quality of the compressed images neither at pixel level nor at perceptual level, but at semantic level. In this paper, we make preliminary efforts towards image semantic quality assessment (ISQA), focusing on the task of optical character recognition (OCR) from compressed images. We propose a fullreference ISQA measure by comparing the features extracted from text regions of original and compressed images. We then propose to integrate the ISQA measure into an image compression scheme. Experimental results show that our proposed ISQA measure is much better than PSNR and SSIM in evaluating the semantic quality of compressed images; accordingly, adopting our ISQA measure to optimize compression for OCR leads to significant bit-rate saving compared to using PSNR or SSIM. Moreover, we perform subjective test about text recognition from compressed images, and observe that our ISQA measure has high consistency with subjective recognizability. Our work explores new dimensions in image quality assessment, and demonstrates promising direction to achieve higher compression ratio for specific semantic analysis tasks.

show abstract

<title>Evaluation model considering static-temporal quality degradation and human memory for SSCQE video quality</title>

Cited by 10 publications

References 0 publications

Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments

Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments

Perceptual visual quality metrics: A survey

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Contact Info

Product

Resources

About