PRNU-based detection of morphed face images

Debiasi, Luca; Scherhag, Ulrich; Rathgeb, Christian; Uhl, Andreas; Busch, Christoph

doi:10.1109/iwbf.2018.8401555

Cited by 52 publications

(56 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. In previous works [18][19][20][21], different statistics of spatial and spectral features extracted from the PRNU patterns of face images have been analysed for the task of morphing attack detection. The proposed detection system builds upon these works extending them by two major additions: on the one hand, a greater variety of spatial and spectral features is analysed to maximise the extracted information; on the other hand, to achieve high robustness and increased detection accuracy, a fusion of retouching detection scores obtained from each of the spatial and spectral features is performed.…”

Section: Fig 2 Example Applications Of Selected Beautification Apps mentioning

confidence: 99%

“…• A facial retouching detection system is proposed, which analyses spatial and spectral features extracted from photo response non-uniformity (PRNU) patterns across image regions. The presented scheme builds upon the works of Debiasi et al [18,19], Zhang et al [20] and Scherhag et al [21] in which an analysis of the PRNU pattern was successfully utilised to detect image manipulations resulting from face morphing [13]. These approaches are adapted and extended by a normalized scorelevel fusion of equally weighted detection scores obtained from the analysis of various spatial and spectral features of the PRNU.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PRNU‐based detection of facial retouching

et al. 2020

Self Cite

View full text Add to dashboard Cite

Nowadays, many facial images are acquired using smart phones. To ensure the best outcome, users frequently retouch these images before sharing them, e.g. via social media. Modifications resulting from used retouching algorithms might be a challenge for face recognition technologies. Towards deploying robust face recognition as well as enforcing anti-photoshop legislations, a reliable detection of retouched face images is needed. In this work, the effects of facial retouching on face recognition are investigated. A qualitative assessment of 32 beautification apps is conducted. Based on this assessment five apps are chosen which are used to create a database of 800 beautified face images. Biometric performance is measured before and after retouching using a commercial face recognition system. Subsequently, a retouching detection system based on the analysis of photo response non-uniformity (PRNU) is presented. Specifically, scores obtained from analysing spatial and spectral features extracted from PRNU patterns across image cells are fused. In a scenario, in which unaltered bona fide images are compressed to the average sizes of the retouched images using JPEG, the proposed PRNU-based detection scheme is shown to robustly distinguish between bona fide and retouched images achieving an average detection equal error rate of 13.7% across all retouching algorithms. Fig. 1 Application of a beautification app: (a) original image, (b) retouched image, and (c) main differences between (a) and (b) (a) Original, (b) Retouched, (c) Differences

show abstract

Section: Fig 2 Example Applications Of Selected Beautification Apps mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

PRNU‐based detection of facial retouching

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some researchers try to detect a possible manipulation using the last mentioned technique [35]. Others try to evaluate the noise pattern employing the photo response non-uniformity (PRNU) approach [50]) in the full image [32] or each region [33].…”

Section: Previous Workmentioning

confidence: 99%

Border Control Morphing Attack Detection with a Convolutional Neural Network De-morphing Approach

et al. 2020

View full text Add to dashboard Cite

Currently, the use of biometric identification, automated or semiautomated, is a reality. For this reason, the number of attacks has increased in such systems. One of the most common biometric attacks is the presentation attack (PA) because it is relatively easy to perform. Automated border control (ABC) is a clear target for phishers. Concerning biometric attacks, morphing is one of the most threatening attacks because authentication systems are usually unable to correctly detect them. In this attack, a fake face is generated with the morphing and blending of two different subjects (genuine and phisher), and the image result is stored in the passport. These attacks can generate risky situations in cases of border crossings where an ABC system should perform identification tasks. This research work proposes a de-morphing architecture that is founded on a convolutional neural network (CNN) architecture. This technique is based on the use of two images: the potentially morphed image stored in the passport, and the snapshot of the person located in the ABC system. The goal of the de-morphing process is to unravel the chip image. If the chip image is a morphed one, the revealing process between the in vivo image and the morphed chip image will return a different facial identity to the person located in the ABC system, and the impostor will be uncovered in situ. If the chip image is a non-morphing image, the resulting image will be similar to a genuine passenger. Therefore, the information obtained is considered at the border crossing. The equal error rate (EER) achieved is very low compared to the literature values published to date. The accomplished outcomes endorse a robust method that provides high accuracy rates without taking into account the quality of images used. This key point is crucial to plausible deployment plans in areas such as ABC. INDEX TERMS ABC, biometric systems, de-morphing, neural networks, MAD.

show abstract

“…The idea to transform images into the frequency domain to detect artifacts is well known. It is used since the mid-1990s for detection of artifacts created by watermarking embedding techniques as discribed in [4] and also for a morph detection approach in [5]. We adapt this idea to create a feature space to detect morphings on passportscaled images.…”

Section: Frequency Domain Feature Space (Fs F R Eqmentioning

confidence: 99%

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

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

PRNU-based detection of morphed face images

Cited by 52 publications

References 14 publications

PRNU‐based detection of facial retouching

PRNU‐based detection of facial retouching

Border Control Morphing Attack Detection with a Convolutional Neural Network De-morphing Approach

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

Contact Info

Product

Resources

About