Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Mot. Imag. J
Volume: 131, No. 3, pp. 35–41
Abstract: Banding is an annoying visual artifact that frequently appears at various stages along the chain of video acquisition, production, distribution, and display. With the thriving popularity of ultrahigh definition (UHD), high-dynamic range (HDR), wide-color-gamut (WCG) content, and the increasing user expectations that follow, the banding effect has been attracting increased attention for its strong negative impact on viewer experience in visual content that would otherwise have nearly perfect quality. Here, we present two different types of frameworks to detect the banding artifact. The first is knowledge-driven and is built upon computational models that account for the characteristics of the human visual system (HVS), the content acquisition, production, distribution, and display processes, and the interplay between them. The second is data-driven and is based on machine learning methods, by training deep neural networks (DNNs) with large-scale datasets.
Publication Date: 2022-04-01
DOI: 10.5594/JMI.2022.3155759
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/JMI.2022.3155759
Author(s): Hojatollah Yeganeh
bio
Hojatollah Yeganeh received a PhD from the University of Waterloo, Waterloo, ON, Canada, in 2014. He is the principal video architect with SSIMWAVE Inc., Waterloo, where he leads the Research and Development (R&D) Team. He has designed and implemented many algorithms in the field of image and video quality assessment and has published number of journals and conference papers and holds several U.S. patents. He is a Senior Member of IEEE and is one of the recipients of the 2020 Technology and Engineering Emmy Award, which is given by the National Academy of Television Arts and Sciences (NATAS) for outstanding achievement in the development of perceptual metrics for video encoding optimization.
Kai Zeng
bio
Kai Zeng received a PhD in electrical and computer engineering from the University of Waterloo, Waterloo, ON, Canada, in 2013. He is the Co-Founder and a Lead Researcher at SSIMWAVE Inc., Waterloo, with research interests including computational image and video processing, computer vision, multimedia communications, with emphasis on image and video quality assessment. He was one of the recipients of the 2020 Technology and Engineering Emmy Award which is given by the National Academy of Television Arts and Sciences (NATAS) for outstanding achievement in the development of perceptual metrics for video encoding optimization.
Zhou Wang
bio
Zhou Wang received a PhD from the University of Texas at Austin, Austin, TX, USA. He is a professor at the University of Waterloo, Waterloo, ON, Canada, holds the position of Canada Research Chair in Multimedia QoE, and directs the Image and Video Computing Laboratory focused on image/video quality assessment and optimization, machine learning, computational vision, and multimedia coding research. He is a co-founder and chief science officer of SSIMWAVE Inc., Waterloo, directing video quality-of-experience measurement and optimization solutions for industry. He received an Engineering Emmy Award for contributions to video quality assessment theories and technologies. He is a Fellow of the IEEE, the Royal Society of Canada, Ottawa, ON, Canada, and the Canadian Academy of Engineering, Ottawa. He has more than 200 publications with over 70,000 citations. His awards include IEEE Signal Processing Society Best Paper, IEEE Signal Processing Magazine Best Paper, IEEE-SPS Sustained Impact Paper, University of Waterloo Faculty of Engineering Research Excellence Award, and Natural Sciences and Engineering Research Council Steacie Memorial Fellowship Award.
Keyword(s): Banding, Contouring Impairment, Human Visual System, Video Quality
Copyright: © 2022 SMPTE

Bibliographic Reference(s)

Z. Wang and A. C. Bovik, Modern Image Quality Assessment, Morgan & Claypool Publishers, Mar. 2006. EXTERNAL
Z. Tu, J. Lin, Y. Wang, B. Adsumilli, and A. C. Bovik, “BBAND Index: A No-Reference Banding Artifact Predictor,” Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 2712– 2716, May 2020. EXTERNAL
A. Kapoor, J. Sapra, and Z. Wang, “HD Images Dataset With Banded and Nonbanded Region Information,” [Online]. Available: https://zenodo.org/record/4513740, 2021. EXTERNAL
G. Denes, G. Ash, H. Fang, R. Mantiuk, “A Visual Model for Predicting Chromatic Banding Artifacts,” Human Vision and Electronic Imaging (HVEI), Jan. 2019. EXTERNAL
A. Rehman, K. Zeng, and Z. Wang, “Display Device-Adapted Video Quality-of-Experience Assessment,” IS&T/ SPIE Electronic Imaging: Human Vision & Electronic Imaging, Feb. 2015. EXTERNAL
Z. Li, A. Aaron, I. Katsavounidis, A. Moorthy, and M. Manohara, “Toward a Practical Perceptual Video Quality Metric,” Netflix TechBlog, Jun. 2016. EXTERNAL
P. G. J. Barten, “Formula for the Contrast Sensitivity of the Human Eye” Proc. SPIE-IS&T, 5294:231–238, Jan. 2004. EXTERNAL
Z. Wang, E. P. Simoncelli, and A. C. Bovik, “Multi-Scale Structural Similarity for Image Quality Assessment.” IEEE Asilomar Con. Signals, Syst. Comput., Nov. 2003. EXTERNAL
A. Kapoor, J. Sapra, and Z. Wang, “Capturing Banding in Images: Database Construction and Objective Assessment,” Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Jun. 2021. EXTERNAL
Z. Wang, H. Yeganeh, A. Badr, and K. Zeng, “Image and Video Banding Assessment,” U.S. Patent Application 17/225, 808, Oct. 2021. EXTERNAL
Y. Wang, S. Kum, C. Chen, and A. Kokaram, “A Perceptual Visibility Metric for Banding Artifacts.” Proc. 2016 IEEE Int. Conf. Image Process., pp. 2067–2071, Sep. 2016. EXTERNAL
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image Quality Assessment: From Error Visibility to Structural Similarity,” IEEE Trans. Image Process., 13(4):600–612, Apr. 2004. EXTERNAL
Z. Wang and A. C. Bovik, “Mean Squared Error: Love It or Leave It? – A New Look at Signal Fidelity Measures,” IEEE Signal Process. Mag., 26(1): 98–117, Jan. 2009. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2022.3155759.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Hojatollah Yeganeh, Kai Zeng, and Zhou Wang; Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 3, April 2022); SMPTE, 2022. Available at https://doi.org/10.5594/JMI.2022.3155759

Snippet:

Hojatollah Yeganeh, Kai Zeng, and Zhou Wang; Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 3, April 2022); SMPTE, 2022. Available at https://doi.org/10.5594/JMI.2022.3155759

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Hojatollah Yeganeh, Kai Zeng, and Zhou Wang; <cite>Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection</cite>, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 3, April 2022); SMPTE, 2022. Available at <a href="https://doi.org/10.5594/JMI.2022.3155759" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2022.3155759</a></span>

SMPTE's HTML Pub

Preview:

Hojatollah Yeganeh, Kai Zeng, and Zhou Wang; Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 3, April 2022); SMPTE, 2022
doi: 10.5594/JMI.2022.3155759
url: https://doi.org/10.5594/JMI.2022.3155759

Snippet:

<li>
Hojatollah Yeganeh, Kai Zeng, and Zhou Wang; <cite id="bib-10-5594-jmi-2022-3155759">Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection</cite>, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 3, April 2022); SMPTE, 2022
<span class="doi">10.5594/JMI.2022.3155759</span>
</li>