Perceptual discrimination of computer generated and photographic faces

Farid, Hany; Bravo, Mary J.

doi:10.1016/j.diin.2011.06.003

Cited by 71 publications

(42 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is therefore perhaps not surprising that the average observer now struggles to distinguish a photographic from a modern-day computer-generated portrait of a person. Observer accuracy in recognizing modern-day computer-generated images is significantly worse than it was 5 years ago [Farid and Bravo 2012]. However, a significant bias to classify an image as photographic still persists among human observers after 5 years time, which can be quite problematic in a legal setting where this distinction can dramatically change the nature of a criminal charge.…”

Section: Discussionmentioning

confidence: 92%

See 1 more Smart Citation

Assessing and Improving the Identification of Computer-Generated Portraits

Holmes

Banks

Farid

2016

ACM Trans. Appl. Percept.

Self Cite

View full text Add to dashboard Cite

Modern computer graphics are capable of generating highly photorealistic images. Although this can be considered a success for the computer graphics community, it has given rise to complex forensic and legal issues. A compelling example comes from the need to distinguish between computer-generated and photographic images as it pertains to the legality and prosecution of child pornography in the United States. We performed psychophysical experiments to determine the accuracy with which observers are capable of distinguishing computer-generated from photographic images. We find that observers have considerable difficulty performing this task-more difficulty than we observed 5 years ago when computer-generated imagery was not as photorealistic. We also find that observers are more likely to report that an image is photographic rather than computer generated, and that resolution has surprisingly little effect on performance. Finally, we find that a small amount of training greatly improves accuracy.

show abstract

Section: Discussionmentioning

confidence: 92%

“…As described in Farid and Bravo [2012], observer accuracy for images rendered prior to 2010 yielded considerably higher accuracy (d = 2.46) but similar bias (β = 2.37). Despite the overall reduction in accuracy in the intervening years, 12.4% of our participants had a d greater than 2.50.…”

Section: :9mentioning

confidence: 90%

Assessing and Improving the Identification of Computer-Generated Portraits

Holmes

Banks

Farid

2016

ACM Trans. Appl. Percept.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The x and y axes are the two parameters C and γ of SVM respectively and lines of different colours represent the accuracy by different contours using these two parameters during the process of cross validation. The algorithm performance is evaluated in terms of sensitivity, specificity and total detection accuracy (T) and computed from Eqns (7)(8)(9).…”

Section: Methodsmentioning

confidence: 99%

“…Feature based methods are further classified as (1) transform domain methods and (2) methods based on physical characteristics of the imaging equipment 7 . Perceptual methods are based on human observers to examine PRCG and photographic images 8 . In case of large number of images, this method becomes unusable.…”

Section: Introductionmentioning

confidence: 99%

Computer Graphic and Photographic Image Classification using Local Image Descriptors

Birajdar¹,

Mankar²

2017

Def. Sc. Jl.

View full text Add to dashboard Cite

With the tremendous development of computer graphic rendering technology, photorealistic computer graphic images are difficult to differentiate from photo graphic images. In this article, a method is proposed based on discrete wavelet transform based binary statistical image features to distinguish computer graphic from photo graphic images using the support vector machine classifier. Textural descriptors extracted using binary statistical image features are different for computer graphic and photo graphic which are based on learning of natural image statistic filters. Input RGB image is first converted into grayscale and decomposed into sub-bands using Haar discrete wavelet transform and then binary statistical image features are extracted. Fuzzy entropy based feature subset selection is employed to choose relevant features. Experimental results using Columbia database show that the method achieves good detection accuracy.

show abstract

“…In much work, such as, 5 the impact of image modification is presumed, and the question addressed is whether humans can perceive modifications. Other work looks at the impact of modification, but does not directly address perceptions of deception.…”

Section: Human Perceptions Of Image Deceptivenessmentioning

confidence: 99%

Assessing the impact of image manipulation on users' perceptions of deception

et al. 2014

View full text Add to dashboard Cite

Generally, we expect images to be an honest reflection of reality. However, this assumption is undermined by the new image editing technology, which allows for easy manipulation and distortion of digital contents. Our understanding of the implications related to the use of a manipulated data is lagging behind. In this paper we propose to exploit crowdsourcing tools in order to analyze the impact of different types of manipulation on users' perceptions of deception. Our goal is to gain significant insights about how different types of manipulations impact users' perceptions and how the context in which a modified image is used influences human perception of image deceptiveness. Through an extensive crowdsourcing user study, we aim at demonstrating that the problem of predicting user-perceived deception can be approached by automatic methods. Analysis of results collected on Amazon Mechanical Turk platform highlights how deception is related to the level of modifications applied to the image and to the context within modified pictures are used. To the best of our knowledge, this work represents the first attempt to address to the image editing debate using automatic approaches and going beyond investigation of forgeries.

show abstract

Perceptual discrimination of computer generated and photographic faces

Cited by 71 publications

References 11 publications

Assessing and Improving the Identification of Computer-Generated Portraits

Assessing and Improving the Identification of Computer-Generated Portraits

Computer Graphic and Photographic Image Classification using Local Image Descriptors

Assessing the impact of image manipulation on users' perceptions of deception

Contact Info

Product

Resources

About