Is seeing still believing: a critical review of the factors that allow humans and machines to discriminate between real and generated images in the context of News & Factual content

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Conference Paper
Content Type: Original Research
Volume: 2017, No. 10, pp. 1–22
Abstract: The growing photorealistic capabilities of 3-D Animation and CGI poses potential issues for Broadcasters, Regulators, Governments and viewers. What happens if a news story is broadcast, or available on a website, which is CGI or a combination of CGI and camera-acquired images? Can we rely our human visual perception to be able to discriminate between CGI and “real’ moving images? There are already instances of video where there is polarized debate as to the degree of CGI present in published content, a prime example being the ISIS video of the burning of a person. An analysis of the artefacts seen in the video that gave rise to the truthfulness debate are presented. The factors that humans use to discriminate, or to evaluate the realness of photographs includes shadow softness, surface smoothness, scene complexity and composition, and number of light sources. Initial studies showed a human ability to discriminate, however, recent studies have shown that the ability to discriminate is getting more difficult, although with training the ability improves. Computer Vision research has evaluated image features and descriptors that discriminate between photographs and CGI. No such studies with quantitative data or experimental methodologies seem to exist for evaluating the CGI moving image by humans or computers. Possible temporal assessment factors for human discrimination (motion parameters) for computer vision (optical flow), and for artificial intelligence (semantic scene analysis) are presented.
Publication Date: 2017-10-23
DOI: 10.5594/M001803
ISBN: Print: 978-1-61482-959-1
Link: https://doi.org/10.5594/M001803
Author(s): Martyn GatesRavensbourne, UK
Keyword(s): Faked News, Visual Perception, Computer Vision, Computer-generated Imagery (CGI), Photorealism, ISIS, Compression Artifacts, CGI Artifacts, Optic Flow, Semantic Scene Analysis, Artificial Intelligence
Copyright: © 2017 Society of Motion Picture and Television Engineers, Inc.

Bibliographic Reference(s)

International Journal of Pattern Recognition , 31, 1921-1936. EXTERNAL
The Max Planck Institute for Intelligent Systems. (2017). Stereo and Optical Flow. Retrieved August 4, 2017, from The Max Planck Institute for Intelligent Systems: https://ps.is.tuebingen.mpg.de/research_fields/stereo-and-flow EXTERNAL
Wedel, A., & et al. (2006). Realtime Depth Estimation and Obstacle Detection from Monocular Video. Lecture Notes in Computer Science , 4174, 475–484. EXTERNAL
Liveleak. (2015, February). LiveLeak. Retrieved April 4, 2015, from Jordanian pilot fake burning debunked!!: http://www.liveleak.com/view?i=df2_1423081561&comments=1 EXTERNAL
Holmes, O., Banks, M. S., & Farid, H. (2016). Assessing and Improving the Identification of Computer-Generated Portraits. ACM Transactions on Applied Perception , 13 (2), 7:1-7:12. EXTERNAL
Szummer, M., & Picard, R. W. (1998). Indoor-outdoor image classification. IEEE International Workshop on Content-based Access of Image and Video Databases, in conjunction with Athitsos, V., Swain, M. J., & Frankel, C. (1997). Distinguishing photographs and graphics on the World Wide Web. Workshop on Content-Based Access of Image and Video Libraries (CBAIVL ’97). Puerto Rico. EXTERNAL
AT&T. (2002). 1924: Fax service. Retrieved December 3, 2013, from AT&T Labs: http://www.corp.att.com/attlabs/reputation/timeline/24fax.html EXTERNAL
Haines, O. (2016, May 13). An Introduction to Simultaneous Localisation and Mapping. Retrieved April 4, 2017, from Kudan Computer Vision: https://www.kudan.eu/kudan-news/an-introduction-to-slam/necessarily reflect the official position of the Society of Motion Picture and Television Engineers (SMPTE), and its printing and Lim, S., Apostolopoulos, J. G., & Gamal, A. E. (2006). Optical flow estimation using temporally oversampled video. IEEE Transactions on Image Processing , 14 (8), 1074 - 1087. EXTERNAL
Kaneva, B., Torralba, A., & Freeman, W. T. (2011). Evaluation of Image Features Using a Photorealistic Virtual World. International Conference on Computer Vision (ICCV). EXTERNAL
Jenkins, K. (2006). The 85 Pentagon Area Surveillance Cameras. Retrieved 2017, from 9-11tv.org: http://www.9-11tv.org/the-pentagon-plane-puzzle/85-pentagon-area-surveillance-camerasWalski, B. (2003). British Soldier in Basra. Retrieved May 29, 2014, from Museum of Hoaxes: http://www.museumofhoaxes.com/hoax/photo_database/image/british_soldier_in_basrahoaxes.org. (2015). British Soldier in Basra. Retrieved from hoaxes.org: http://hoaxes.org/photo_database/image/british_soldier_in_basranecessarily reflect the official position of the Society of Motion Picture and Television Engineers (SMPTE), and its printing and Flybring, J. (2009, November 4). The 2003 Brian Walski scandal. Retrieved 2017, from JohanFlybring: https://johanflybringcmp.wordpress.com/page/2/video-purportedly-shows-jordanian-pilot-being-burned-aliveRademacher, P. et al. (2001). Measuring the Perception of Visual Realism in Images. (S. G. alia, Ed.) Rendering Techniques . EXTERNAL
Hanson, A., Learned-Miller, E., & Narayana, M. (2013). Coherent Motion Segmentation in Moving Camera Videos. ICCV . EXTERNAL
Kalva, H., & Lee, J.-B. (2008). Video Coding Techniques and Standards. (B. Furht, Editor) Retrieved January 5, 2014, from Encyclopedia of Multimedia: SpringerReference: http://www.springerreference.com/docs/html/chapterdbid/73083.html EXTERNAL
Pinson, M., & Wolf, S. (2003, July 11). Comparing subjective video quality testing methodologies. Retrieved May 25, 2015, from VideoClarity: http://www.videoclarity.com/PDF/WPSubjectiveTestingMethodsReviewed.pdf EXTERNAL
Cutzu, F., Hammond, R., & Leykin, A. (2003). Estimating the photorealism of images: Distinguishing paintings from photographs. Bloomington, IN, USA. EXTERNAL
Masaoka, K., Nishida, M., Sugawara, M., Nakasu, E., & Nojiri, Y. (2013, March). Sensation of Realness From High-Resolution Images of Real Objects. IEEE Transactions on Broadcasting , 59 (01), pp. 72-83. EXTERNAL
MSU Graphics & Media Lab (Video Group). (2014). MSU Subjective Comparison of Modern Video Codecs. Retrieved May 25, 2015, from Compression.ru: necessarily reflect the official position of the Society of Motion Picture and Television Engineers (SMPTE), and its printing and http://www.compression.ru/video/codec_comparison/01_subject_codec_comparison/subject_codec_comparison_part1.htm EXTERNAL
Vailaya, A., Jain, A. K., & Zhang, H.-J. (1998). On image classification: City vs. landsacpes. EXTERNAL
FoxNews.com. (2015, February 3). New ISIS Video Shows Jordanian Pilot Being Burned Alive. Retrieved 2017, from www.foxnews.com: http://nation.foxnews.com/2015/02/03/new-isis- EXTERNAL
Narita, N., & Kanazawa, M. (2013). Analysis of Psychological Factors for HDTV/3-D HDTV and Evaluation Method of Their Overall Impressions. IEEE Transactions on Broadcasting , 59 (01), 13-19. EXTERNAL
Salmon, R. (2013, September 12). Higher Frame Rates for Television. (M. Gates, Interviewer) EXTERNAL
Ackerman, H., Liao, W., & Rosenhahn, B. (2017). Semantic Scene Analysis. Retrieved August 30, 2017, from Institut für Informationsverarbeitung: http://www.tnt.uni-hannover.de/project/Semantic_Scene_Analysis/Wictor, T. (2015, February 5). The Jordanian pilot was not burned alive. Retrieved May 25, 2015, from Thomas Wictor: http://www.thomaswictor.com/the-jordanian-pilot-was-not-burned-alive/Loman, W. (2015, February 4). The Muath Al-Kaseasbeh Immolation Video: ISIS™ Uniforms Look a Lot Like Jordanian Military. Retrieved May 25, 2015, from Willy Loman: https://willyloman.wordpress.com/2015/02/04/the-muath-al-kaseasbeh-immolation-video-isis-uniforms-look-a-lot-like-jordanian-military/Liveleak. (2015, February). LiveLeak. Retrieved April 4, 2015, from Jordanian pilot fake burning DEBUNKED!!: http://www.liveleak.com/view?i=df2_1423081561&comments=1 EXTERNAL
Chalmers, A. (2012, February). Warwick leader in High Dynamic Range video to demo at world’s biggest media tradeshow. Retrieved January 5, 2014, from Warwick University: http://www2.warwick.ac.uk/fac/sci/wmg/mediacentre/wmgnews/?newsItem=094d43a235632b2d013580734c1551c3Selmanovic, E. (2013). Stereoscopic high dynamic range imaging. Retrieved January 5, 2014, from Warwick University: http://wrap.warwick.ac.uk/58125/ EXTERNAL
R-REC-BT.500-13 — Recommendation ITU-R BT.500-13, “Methodology for the Subjective Assessment of the Quality of Television Pictures,” International Telecommunication Union, Radiocommunication Sector, Geneva, 2012. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-M001803.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:

Martyn Gates; Is seeing still believing: a critical review of the factors that allow humans and machines to discriminate between real and generated images in the context of News & Factual content, SMPTE Meetings and Conferences ( October 2017); SMPTE, 2017, ISBN: 978-1-61482-959-1. Available at https://doi.org/10.5594/M001803

Snippet:

Martyn Gates; Is seeing still believing: a critical review of the factors that allow humans and machines to discriminate between real and generated images in the context of News &amp; Factual content, SMPTE Meetings and Conferences ( October 2017); SMPTE, 2017, ISBN: 978-1-61482-959-1. Available at https://doi.org/10.5594/M001803

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Martyn Gates; <cite>Is seeing still believing: a critical review of the factors that allow humans and machines to discriminate between real and generated images in the context of News &amp; Factual content</cite>, SMPTE Meetings and Conferences ( October 2017); SMPTE, 2017, ISBN: 978-1-61482-959-1. Available at <a href="https://doi.org/10.5594/M001803" target="_blank" rel="noopener">https://doi.org/10.5594/M001803</a></span>

SMPTE's HTML Pub

Preview:

Snippet:

<li>
Martyn Gates; <cite id="bib-10-5594-m001803">Is seeing still believing: a critical review of the factors that allow humans and machines to discriminate between real and generated images in the context of News &amp; Factual content</cite>, SMPTE Meetings and Conferences ( October 2017); SMPTE, 2017, ISBN: 978-1-61482-959-1
<span class="doi">10.5594/M001803</span>
</li>