A Novel Method for Subjective Picture Quality Assessment and Further Studies of HDTV Formats

Abstract

Abstract-This paper proposes a novel method for the assessment of picture quality, called Triple Stimulus Continuous Evaluation Scale (TSCES), to allow the direct comparison of different HDTV formats. The method uses an upper picture quality anchor and a lower picture quality anchor with defined impairments. The HDTV format under test is evaluated in a subjective comparison with the upper and lower anchors. The method utilizes three displays in a particular vertical arrangement. In an initial series of tests with the novel method, the HDTV formats 1080p/50, 1080i/25, and 720p/50 were compared at various bit-rates and with seven different content types on three identical 1920 1080 pixel displays. It was found that the new method provided stable and consistent results. The method was tested with 1080p/50, 1080i/25, and 720p/50 HDTV images that had been coded with H.264/AVC High profile. The result of the assessment was that the progressive HDTV formats found higher appreciation by the assessors than the interlaced HDTV format. A system chain proposal is given for future media production and delivery to take advantage of this outcome. Recommendations for future research conclude the paper.Index Terms-Compression in broadcasting, flat panel displays, high-definition television, subjective testing of image quality.

Subjective assessment of HDTV content: comparison of quality across HDTV formats

“…In addition to their findings, they also contributed free HD source shot in 720p/50, 1080p/50 and 1080i/25 content that has been widely utilized in the field 3,4,5,6,7 Recent results 4,7 report on subjective results suggests that 720p/50 performs better than 1080i/25, with further objective and subjective tests 5,6 generalizing the prediction that similarly encoded progressive HDTV formats will degrade better than interlaced formats.…”

Evaluating experiment design with unrepeated scenes for video quality subjective assessment

“…The conventional experiment design is described by Pinson et al [22] and used by most published experiments. Variants tend to expand upon the idea of comparing different versions of a single SRC, e.g., using three different monitors at the same time [5]. These designs may increase precision, yet further decrease realism.…”

No-Reference Image Quality Analysis for Compressed Video Sequences

“…Assuming a Rayleigh distribution for , the RMS-value can be obtained as (2) where X and Y represent the width and height of the image in pixels. In order to reduce the influence of object boundaries, gradient values above a certain level should be ignored when computing .…”