Understanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection
Hojatollah Yeganeh, Kai Zeng, Zhou Wang
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.
Print ISSN
1545-0279
Electronic ISSN
2160-2492
Published
2022-04
Content type
Original Research
Keywords
Banding impairment, contouring impairment, human visual system (HVS), perceived video quality