Modeling Attacks on Photo-ID Documents and Applying Media Forensics for the Detection of Facial Morphing

Kraetzer, Christian; Makrushin, Andrey; Neubert, Tom; Hildebrandt, Mario; Dittmann, Jana

doi:10.1145/3082031.3083244

Cited by 53 publications

(44 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14] a feature space for morph detection is presented, based on the idea that the blending operation in morphing pipelines causes a reduction of face details, especially on images with a resolution with more than 2 megapixels. The reduction of face details is quantied by the number of keypoints and egdes in the face region.…”

Section: Keypoint Feature Space For Morph Detectionmentioning

confidence: 99%

“…The authors use several keypoint and edge detectors, because they assume that the impact of blending operation is dierent for each detector, some of them will react more sensible than others. The following keypoint and edge detectors were used as features for the detector in [14]: SIFT [15], SURF [1], ORB [27], FAST [26], AGAST [17], CannyEdge [2], SobelX and SobelY [13]. These eight features were extracted with functions implemented in the OpenCV programming library version 3.0 with contributions (http://opencv.org).…”

Section: Keypoint Feature Space For Morph Detectionmentioning

confidence: 99%

“…So, FS F r eq results in a 25 dimensional vector. As mentioned before, FS Spat is based on the work of Kraetzer et al in [14]. The approach is thoroughly described in Section 2.2.…”

Section: Frequency Domain Feature Space (Fs F R Eqmentioning

confidence: 99%

“…The approach is thoroughly described in Section 2.2. Basically, we primarily modify the feature normalization and the feature selection compared to [14]. The number of detected keypoint and edge features from 8 detectors (SIFT, SURF, ORB, FAST, AGAST, CannyEdge, SobelX and SobelY, see Section 2.2) are extracted on the normalized face image derived from PPM.…”

Section: Frequency Domain Feature Space (Fs F R Eqmentioning

confidence: 99%

See 3 more Smart Citations

A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD

Neubert

Kraetzer

Dittmann

2019

Proceedings of the ACM Workshop on Information Hiding and Multimedia Security

Self Cite

View full text Add to dashboard Cite

Since the face morphing attack was introduced by Ferrara et al. in 2014, the detection of face morphings has become a wide spread topic in image forensics. By now, the community is very active and has reported diverse detection approaches. So far, the evaluations are mostly performed on images without post-processing. Face images stored within electronic machine readable documents (eMRTD) are ICAO 1-passport-scaled to a resolution of 413x531 and a JPG or JP2 lesize of 15 kilobytes. This paper introduces a face morphing detection concept with 3 modules (ICAO-aligned preprocessing module, feature extraction module and classication module), tailored for such images on eMRTD. In this work we exemplary design and evaluate two feature spaces for the feature extraction module, a frequency domain and a spatial domain feature space. Our evaluation will compare both feature spaces and is carried out with 66,229 passport-scaled images (64,363 morphed face images and 1,866 authentic face images) which are completly independent from training and include all images provided for the IHMMSEC'19 special session: "Media Forensics-Fake or Real?". Furthermore, we investigate the inuence of dierent morph generation pipelines to the detection accuracies of the concept and we analyse the impact of neutral and smiling genuine faces to the morph detector performance. The evaluation determines a detection rate of 86.0% for passport-scaled morphed images with a false alarm rate of 4.4% for genuine images for the spatial domain feature space.

show abstract

Section: Keypoint Feature Space For Morph Detectionmentioning

confidence: 99%

Section: Keypoint Feature Space For Morph Detectionmentioning

confidence: 99%

“…So, FS F r eq results in a 25 dimensional vector. As mentioned before, FS Spat is based on the work of Kraetzer et al in [14]. The approach is thoroughly described in Section 2.2.…”

Section: Frequency Domain Feature Space (Fs F R Eqmentioning

confidence: 99%

Section: Frequency Domain Feature Space (Fs F R Eqmentioning

confidence: 99%

See 2 more Smart Citations

A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD

Neubert

Kraetzer

Dittmann

2019

Proceedings of the ACM Workshop on Information Hiding and Multimedia Security

Self Cite

View full text Add to dashboard Cite

show abstract

“…Further, Hildebrandt et al [12] suggest to employ generic image forgery detection techniques, in particular multi-compression anomaly detection, to reliably detect morphed facial images. Kraetzer et al [13] evaluate the feasibility of detecting facial morphs with keypoint descriptors and edge operators. However for the current state of the art detection accuracy is very limited and generalisation capabilities of detectors are yet unexplored.…”

Section: Introductionmentioning

confidence: 99%

Detecting Morphed Face Images Using Facial Landmarks

Scherhag

Budhrani

Gomez‐Barrero

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

A Novel Framework for Detection of Morphed Images Using Deep Learning Techniques

Mohammed

Waseem

2020

New Trends in Computational Vision and Bio-Inspired Computing

View full text Add to dashboard Cite

Modeling Attacks on Photo-ID Documents and Applying Media Forensics for the Detection of Facial Morphing

Cited by 53 publications

References 17 publications

A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD

A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD

Detecting Morphed Face Images Using Facial Landmarks

A Novel Framework for Detection of Morphed Images Using Deep Learning Techniques

Contact Info

Product

Resources

About