Crowdsourcing-based evaluation of privacy in HDR images

Korshunov, Pavel; Nemoto, Hiromi; Skodras, Athanassios; Ebrahimi, Touradj

doi:10.1117/12.2054541

Cited by 22 publications

(24 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, it pursues the representation of the entire dynamic range and color gamut perceived by human visual system (HVS). HDR imaging can be exploited to improve quality of experience in multimedia applications [1] and to enhance intelligibility in security applications where lighting conditions cannot be controlled [2].…”

Section: Introductionmentioning

confidence: 99%

Benchmarking of objective quality metrics for HDR image quality assessment

Hanhart

Bernardo

Pereira

et al. 2015

J Image Video Proc.

Self Cite

View full text Add to dashboard Cite

Recent advances in high dynamic range (HDR) capture and display technologies have attracted a lot of interest from scientific, professional, and artistic communities. As in any technology, the evaluation of HDR systems in terms of quality of experience is essential. Subjective evaluations are time consuming and expensive, and thus objective quality assessment tools are needed as well. In this paper, we report and analyze the results of an extensive benchmarking of objective quality metrics for HDR image quality assessment. In total, 35 objective metrics were benchmarked on a database of 20 HDR contents encoded with 3 compression algorithms at 4 bit rates, leading to a total of 240 compressed HDR images, using subjective quality scores as ground truth. Performance indexes were computed to assess the accuracy, monotonicity, and consistency of the metric estimation of subjective scores. Statistical analysis was performed on the performance indexes to discriminate small differences between metrics. Results demonstrated that metrics designed for HDR content, i.e., HDR-VDP-2 and HDR-VQM, are the most reliable predictors of perceived quality. Finally, our findings suggested that the performance of most full-reference metrics can be improved by considering non-linearities of the human visual system, while further efforts are necessary to improve performance of no-reference quality metrics for HDR content.

show abstract

Section: Introductionmentioning

confidence: 99%

Benchmarking of objective quality metrics for HDR image quality assessment

Hanhart

Bernardo

Pereira

et al. 2015

J Image Video Proc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The closest related studies are [11] and [19], which investigate the impact of HDR on a more general aspect of privacy intrusiveness. However, we focus specifically on the face recognition task, which is a typical example of visual cognitive tasks, aiming to investigate whether HDR imaging improves the recognition accuracy of both human and computer vision.…”

Section: Hdr Imagingmentioning

confidence: 99%

“…In particular, the cost effectiveness and access to a large pool of test subjects makes crowdsourcing an attractive alternative to lab-based evaluations. Therefore, researchers in quality assessment increasingly use crowdsourcing in various research areas, including rebuffering in streaming video [7], aesthetics of images [20], emotional reaction caused by image content [8], and privacy issues in HDR images [11].…”

Section: Crowdsourcingmentioning

confidence: 99%

“…The dataset is made freely available to public for research purposes 1 . To evaluate the change in human recognition accuracy when they see a tone-mapped HDR version of an image instead of LDR, we conducted an extensive crowdsourcing study, since this approach was shown as a viable alternative to lab-based subjective assessments [10,11]. For this purpose, an open source framework QualityCrowd2 [9] 2 was adapted and crowdsourcing workers were employed from Microworkers 3 platform.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of Tone-mapping Algorithms on Subjective and Objective Face Recognition in HDR Images

Korshunov

Bernardo

Pinheiro

et al. 2015

Proceedings of the Fourth International Workshop on Crowdsourcing for Multimedia

Self Cite

View full text Add to dashboard Cite

Crowdsourcing is a popular tool for conducting subjective evaluations in uncontrolled environments and at low cost. In this paper, a crowdsourcing study is conducted to investigate the impact of High Dynamic Range (HDR) imaging on subjective face recognition accuracy. For that purpose, a dataset of HDR images of people depicted in high-contrast lighting conditions was created and their faces were manually cropped to construct a probe set of faces. Crowdsourcing-based face recognition was conducted for five differently tone-mapped versions of HDR faces and were compared to face recognition in a typical Low Dynamic Range alternative. A similar experiment was also conducted using three automatic face recognition algorithms. The comparative analysis results of face recognition by human subjects through crowdsourcing and machine vision face recognition show that HDR imaging affects the recognition results of human and computer vision approaches differently.

show abstract

“…But since these datasets were not designed with privacy issues in mind, they are not suitable for evaluation of privacy related aspects. To the authors knowledge, only a couple of datasets for evaluation of privacy exists, one is PEViD, 2 which is not an HDR dataset, and another is a dataset of HDR images for privacy, 3 which does not contain video content and hence is not suitable for evaluation of typical video surveillance scenes.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of privacy in high dynamic range video sequences

et al. 2014

Self Cite

View full text Add to dashboard Cite

The ability of high dynamic range (HDR) to capture details in environments with high contrast has a significant impact on privacy in video surveillance. However, the extent to which HDR imaging affects privacy, when compared to a typical low dynamic range (LDR) imaging, is neither well studied nor well understood. To achieve such an objective, a suitable dataset of images and video sequences is needed. Therefore, we have created a publicly available dataset of HDR video for privacy evaluation PEViD-HDR, which is an HDR extension of an existing Privacy Evaluation Video Dataset (PEViD). PEViD-HDR video dataset can help in the evaluations of privacy protection tools, as well as for showing the importance of HDR imaging in video surveillance applications and its influence on the privacy-intelligibility trade-off. We conducted a preliminary subjective experiment demonstrating the usability of the created dataset for evaluation of privacy issues in video. The results confirm that a tone-mapped HDR video contains more privacy sensitive information and details compared to a typical LDR video.

show abstract

Crowdsourcing-based evaluation of privacy in HDR images

Cited by 22 publications

References 28 publications

Benchmarking of objective quality metrics for HDR image quality assessment

Benchmarking of objective quality metrics for HDR image quality assessment

Impact of Tone-mapping Algorithms on Subjective and Objective Face Recognition in HDR Images

Evaluation of privacy in high dynamic range video sequences

Contact Info

Product

Resources

About