Jana Dittmann

The datasets of synthetic biometric samples are created having in mind two major objectives: bypassing privacy concerns and compensating for missing sample variability in datasets of real biometric samples. If the purpose of generating samples is the evaluation of biometric systems, the foremost challenge is to generate so-called mated impressions—different fingerprints of the same finger. Note that for fingerprints, the finger’s identity is given by the co-location of minutiae points. The other challenge is to ensure the realism of generated samples. We solve both challenges by reconstructing fingerprints from pseudo-random minutiae making use of the pix2pix network. For controlling the identity of mated impressions, we derive the locations and orientations of minutiae from randomly created non-realistic synthetic fingerprints and slightly modify them in an identity-preserving way. Our previously trained pix2pix models reconstruct fingerprint images from minutiae maps, ensuring that the realistic appearance is transferred from training to synthetic samples. The main contribution of this work lies in creating and making public two synthetic fingerprint datasets of 500 virtual subjects with 8 fingers each and 10 impressions per finger, totaling 40,000 samples in each dataset. Our synthetic datasets are designed to possess characteristics of real biometric datasets. Thus, we believe they can be applied for the privacy-friendly testing of fingerprint recognition systems. In our evaluation, we use NFIQ2 for approving the visual quality and Verifinger SDK for measuring the reconstruction success.

Academic research in media forensics mainly focuses on methods for the detection of the traces or artefacts left by media manipulations in media objects. While the resulting detectors often achieve quite impressive detection performances, when tested under lab conditions, hardly any of those have yet come close to the ultimate benchmark for any forensic method, which would be courtroom readiness. This paper tries first to facilitate the different stakeholder perspectives in this field and then to partly address the apparent gap between the academic research community and the requirements imposed onto forensic practitioners. The intention is to facilitate the mutual understanding of these two classes of stakeholders and assist with first steps intended at closing this gap. To do so, first a concept for modelling media forensic investigation pipelines is derived from established guidelines. Then, the applicability of such modelling is illustrated on the example of a fusion-based media forensic investigation pipeline aimed at the detection of DeepFake videos using five exemplary detectors (hand-crafted, in one case neural network supported) and testing two different fusion operators. At the end of the paper, the benefits of such a planned realisation of AI-based investigation methods are discussed and generalising effects are mapped out.

Fingerprint traces are an important part of forensic investigations to identify potential perpetrators. With the possibility of printing traces for quality assurance purposes it is also possible to place malicious traces on crime scenes. In forensics examiners are already aware of multiple identical traces, e.g. produced by stamping fingerprints. The technique of printing fingerprints using artificial sweat allows to create different versions of the same fingerprint, similar to the residue from a finger, which is almost never 100 percent identical to another latent fingerprint. Hence, Kiltz et al.¹ introduce a first framework for the detection of such malicious traces in subjective evaluations based on dot patterns of amino acid. Hildebrandt et al.² introduce a first automated approach for the detection of printed fingerprints using high resolution scans from a chromatic white light sensor. However, the reported recognition accuracy is insufficient for forensic investigations. In this paper we propose an improved feature extraction for scans using a confocal microscope to reduce the overall analysis time and to increase the recognition accuracy. Our evaluation is based on 3000 printed and 3000 real fingerprints on the three surfaces hard disk platter, overhead foil and compact disk advancing the research from Hildebrandt et al.² Our goal is to benchmark the feature extraction and recognition of printed fingerprints for the three substrates as well as for the combination thereof. The results indicate a significant reduction of the necessary analysis time to less than one minute as well as an improved recognition rate of up to 99.7 percent for all samples on the three surfaces in comparison to the previously achieved 91.48 percent on two surfaces as reported in Hildebrandt et al.²

A machine-assisted analysis of traces from crime scenes might be possible with the advent of new high-resolution non-destructive contact-less acquisition techniques for latent fingerprints. This requires reliable techniques for the automatic extraction of fingerprint features from latent and exemplar fingerprints for matching purposes using pattern recognition approaches. Therefore, we evaluate the NIST Biometric Image Software for the feature extraction and verification of contact-lessly acquired latent fingerprints to determine potential error rates. Our exemplary test setup includes 30 latent fingerprints from 5 people in two test sets that are acquired from different surfaces using a chromatic white light sensor. The first test set includes 20 fingerprints on two different surfaces. It is used to determine the feature extraction performance. The second test set includes one latent fingerprint on 10 different surfaces and an exemplar fingerprint to determine the verification performance. This utilized sensing technique does not require a physical or chemical visibility enhancement of the fingerprint residue, thus the original trace remains unaltered for further investigations. No particular feature extraction and verification techniques have been applied to such data, yet. Hence, we see the need for appropriate algorithms that are suitable to support forensic investigations.

Annotation watermarking (sometimes also called caption or illustration watermarking) denotes a specific application of watermarks, which embeds supplementary information directly in the media, so that additional information is intrinsically linked to media content and does not get separated from the media by non-malicious processing steps such as image cropping or compression. Recently, nested object annotation watermarking (NOAWM) has been introduced as a specialized annotation watermarking domain, whereby hierarchical object information is embedded in photographic images. In earlier work, the Hierarchical Graph Concept (HGC) has been suggested as a first approach to model object relations, which are defined by users during editing processes, into a hierarchical tree structure. The original HGC method uses a code-book decomposition of the annotation tree and a block-luminance algorithm for embedding. In this article, two new approaches for embedding nested object annotations are presented and experimentally compared to the original HGC approach. The first one adopts the code-book scheme of HGC using an alternative embedding based on Wet Paper Codes in blue-channel LSB domain, whereas the second suggests a new method based on the concept of intrinsic signal inheritance by sub-band energy and phase modulation of image luminance blocks. A comparative experimental evaluation based on more than 100 test images is presented in the paper, whereby aspects of transparency and robustness with respect to the most relevant image modifications to annotations, cropping and JPEG compression, are discussed comparatively for the two code-book schemes and the novel inheritance approach.

The fusion of biometric systems, algorithms and/or traits is a well known solution to improve authentication performance of biometric systems. In this article the fusion of two instances of the same semantic is suggested, where semantics are alternative handwritten contents such as numbers or sentences, in addition to commonly used signature. In order to fuse two instances of one semantic, a biometric authentication is carried out on both by Biometric Hash algorithm up to matching score computation. The fusion is done by combination of matching scores to a joint score as basis for authentication decision. Three individual fusion strategies are used to study to which degree the authentication performance can be improved or degraded. Therefore one pragmatic and two optimistically weighting approaches for biometric fusion are used. The best fusion result is even better than the corresponding best individual result by approximately 17%.

A stroke point matching by dynamic time warping (DTW) and strokes wise segment alignment by using spline interpolation for time and coordinate signals are presented in this paper. The algorithm uses both the features and signals based verification methodologies. The top-level in signature representation deals with the global geometric shape. This method will verify not only the signature shape but also some of its important features. In the first stage, we verify the signature based on the signature feature. In the second stage, we will verify time profile and coordinate signals of the signature by new segment warping functional approach. Local temporal shifts existing in signature can be reduced through segment warping technique. The decision about the authenticity of the specimen is influenced by correlation measurements and statistical distance measurements. The on-line data has been acquired with the help of a digitized tablet PC. Also we verify our algorithm in SVC 2004 database. In the proposed signature-verification algorithm, an input signal of the signature undergoes preprocessing procedures including smoothing, rotation, shifting and size normalization.