Image Quality Assessment

Seshadrinathan, Kalpana; Pappas, Thrasyvoulos N.; Safranek, R.J.; Chen, Junqing; Wang, Zhou; Sheikh, H.R.; Bovik, Alan C.

doi:10.1016/b978-0-12-374457-9.00021-4

Cited by 36 publications

(19 citation statements)

References 75 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of HVS-based image quality indices include [23], [24], [25], [26], [27]; see [28] for a review. It is believed that two kinds of temporal mechanisms exist in the early stages of processing in the HVS, one lowpass and one bandpass, known as the sustained and transient mechanisms [29], [30].…”

Section: Introductionmentioning

confidence: 99%

Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos

Seshadrinathan

Bovik

2010

IEEE Trans. on Image Process.

645

402

View full text Add to dashboard Cite

Abstract-There has recently been a great deal of interest in the development of algorithms that objectively measure the integrity of video signals. Since video signals are being delivered to human end users in an increasingly wide array of applications and products, it is important that automatic methods of video quality assessment (VQA) be available that can assist in controlling the quality of video being delivered to this critical audience. Naturally, the quality of motion representation in videos plays an important role in the perception of video quality, yet existing VQA algorithms make little direct use of motion information, thus limiting their effectiveness. We seek to ameliorate this by developing a general, spatio-spectrally localized multiscale framework for evaluating dynamic video fidelity that integrates both spatial and temporal (and spatio-temporal) aspects of distortion assessment. Video quality is evaluated not only in space and time, but also in space-time, by evaluating motion quality along computed motion trajectories. Using this framework, we develop a full reference VQA algorithm for which we coin the term the MOtion-based Video Integrity Evaluation index, or MOVIE index. It is found that the MOVIE index delivers VQA scores that correlate quite closely with human subjective judgment, using the Video Quality Expert Group (VQEG) FRTV Phase 1 database as a test bed. Indeed, the MOVIE index is found to be quite competitive with, and even outperform, algorithms developed and submitted to the VQEG FRTV Phase 1 study, as well as more recent VQA algorithms tested on this database.

show abstract

Section: Introductionmentioning

confidence: 99%

Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos

Seshadrinathan

Bovik

2010

IEEE Trans. on Image Process.

645

402

View full text Add to dashboard Cite

show abstract

“…Arousal ratings do not possess a directional component that links to valence, so it is possible that images that are particularly unpleasant or particularly pleasant may possess the same arousal value (e.g., exciting and pleasant, or exciting and unpleasant), potentially nullifying any effect. In contrast to the finding in (1)(2)(3)(4)(5) and mean subjective quality rating (1-10); B, box plot showing the relationship between objective quality setting (q1-q5) and mean subjective quality rating (1-10). Plus symbols denote outliers.…”

Section: Discussionmentioning

confidence: 68%

“…Mean subjective quality ratings averaged over stimulus images and participants for each of the five objective quality settings (JPEG compression level, q1-q5), shown in .30), respectively, highlighting that participants did not employ the entire subjective quality range (1)(2)(3)(4)(5)(6)(7)(8)(9)(10), but that the mean subjective quality rating does increase monotonically as the objective quality setting rises, confirming participants' generally successful discrimination between objective quality settings. This is exemplified by a significant "large" [43] correlation between objective quality setting and mean subjective quality assessment [r 0.54 (2548), ptwo-tailed < 0.001].…”

Section: Resultsmentioning

confidence: 83%

“…Mean subjective quality rating over time (trial number). Thin black curves represent the ratings for each presentation sequence (1)(2)(3)(4)(5); the thick black curve represents the mean rating.…”

Section: Discussionmentioning

confidence: 99%

“…To evaluate the effectiveness of such algorithms, along with algorithms used in applications such as image restoration, enhancement, and watermarking, and to evaluate transmission, display and broadcast systems, both objective and subjective image quality assessment (IQA) and video quality assessment (VQA) procedures are used. For a review of modern techniques for images and video, see [1,2], respectively. Subjective quality assessment methods require that human participants rate individual images or video sequences in a presentation series, and are consequently both expensive and time consuming to administer and cannot be applied in real time to make automatic output-contingent adjustments [3,4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Influence of affective image content on subjective quality assessment

Linde

Doe

2012

J. Opt. Soc. Am. A

View full text Add to dashboard Cite

Image quality assessment (IQA) enables distortions introduced into an image (e.g., through lossy compression or broadcast) to be measured and evaluated for severity. It is unclear to what degree affective image content may influence this process. In this study, participants (n 25) were found to be unable to disentangle affective image content from objective image quality in a standard IQA procedure (single stimulus numerical categorical scale). We propose that this issue is worthy of consideration, particularly in single stimulus IQA techniques, in which a small number of handpicked images, not necessarily representative of the gamut of affect seen in true broadcasting, and unrated for affective content, serve as stimuli.

show abstract