Research on Convenient and Privacy Compliant Biometric Systems
The mission of our research on Biometrics is to achieve progress towards better Biometric systems. While our work is covering numerous physiological and behavioral modality including 2D- and 3D-face recognition, iris recognition, fingerprint recognition, fingervein recognition, ear recognition and gait recognition the intention to be better has various flavors. In the first instance the research is targeting improved recognition performance, which we want to achieve by quality assessment of biometric enrolment samples. In the second instance we are concerned about development and deployment of convenient unobtrusive biometrics that can e..g. protect personal or business data that is stored on smartphones. Exploiting the embedded smartphone sensors is our strategy to deploy biometrics without any hardware costs. The third and yet very relevant instance is our work on privacy enhancing technologies such as biometric template protection and design of biometric systems according to the Privacy-by-Design principle. Our group is actively participating in international academic conferences such as ICB, BTAS and BIOSIG and contributes both to the European Association for Biometrics (EAB) and the international standardisation in ISO/IEC JTC1 SC37.
-
HQSwap: A Challenging High-Resolution Face-Swap Dataset for Improved Manipulation Detection.
The generalisation capabilities to cross and unknown scenarios are one of the main issues to solve in deepfake detection research. This work provides a new face-swap dataset generated by six algorithms, such as *Blendswap, Ghost, Simswap, Uniface, Hyperswap and Inswapper, which can be used to enhance current classifiers. Our work focuses on tackling open challenges in…
-
HDA Passport Fairness Database (eng)
Deutsche Seite here What is it about? A data set for evaluating the fairness of biometric algorithms is being created at Hochschule Darmstadt. The aim is to find out how different skin types affect the performance of existing facial recognition and iris recognition methods. The focus is on standardized passport-quality images in order to specifically…
-
Syn-Pass: HDA Synthetic Passport Database
The Syn-IDPASS contains synthetic images from 03 different countries: Poland, Portugal and Spain. The synthetic passport images, which follow the ICAO standards, were generated as „simulated bona fide images“. From the Synthetic images, the printed and screen attack versions were manually created one by one. On average, 1000 images for each country were generated. In total, each…
-
HDA Passport Fairness Database (De)
English site here Um was geht’s? An der Hochschule Darmstadt entsteht ein Datensatz zur Bewertung der Fairness biometrischer Algorithmen. Ziel ist es, herauszufinden, wie sich unterschiedliche Hauttypen auf die Leistungsfähigkeit bestehender Gesichtserkennungs- und Irisverfahren auswirken. Der Fokus liegt dabei auf standardisierten Bildern in Passfotoqualität, um gezielt analysieren zu können, bei welchen Hauttyp-Klassen es zu systematischen…
-
HDA Down Syndrome Face Database
The database was used in [1] to evaluate the biometric performance of open-source and commercial face recognition systems on people with Down syndrome. This page contains information about the used dataset, including a download link to a CSV file containing a link collection of the used dataset. Dataset information and link collection: The used dataset…
-
T-shirt Face Presentation Attack (TFPA) database
The TFPA database is a database consisting of 1,608 T-shirt attacks using 100 unique presentation attack instruments (PAIs). The T-shirt PAIs are based on synthetically generated face images, each worn by at least two subjects across eight different capturing scenarios and two capturing streams (visible + depth). Download and Copyright: The database is being made…
-
HDA Synthetic Children Face Database
The HDA-SynChildFaces database consists of synthetic face images from 1,652 subjects and a total of 188,328 images, each subject being present at various ages and with many different intra-subject variations. More information about the database can be found at https://github.com/dasec/HDA-SynChildFaces-AgeTransformation. Download and Copyright: The database is being made available for researchers from 2024 onwards. Interested…
-
HDA Semi-synthetic Tattoo Database
HDA Semi-synthetic Tattoo Database The Hochschule Darmstadt (HDA) semi-synthetic tattoo database contains 5,500 synthetic images with tattooed subjects as well as their respective three-class segmentation maps (i.e., background, skin, and tattoo). In addition, 140 real images with corresponding skin segmentation maps are provided. These images were used as base images to generate the semi-synthetic tattoo…
-
COLFISPOOF: A Database for Contactless Fingerprint Presentation Attack Detection Research
The COLFISPOOF database acquired in 2022 which contains 7,200 samples from 72 different presentation attack instrument (PAI) species. It was collected to promote research on mobile contactless fingerprint presentation attack detection (PAD). A summary of all 72 PAI species is given in the tables below. PAI material LOO group wood glue glue default color knetosil…
-
HDA Cross-Domain Face Database
HDA Cross-Domain Face Database The Hochschule Darmstadt (HDA) cross-domain face database contains 1,400 face images from three different domains including avatars (A), caricatures (C), and sketches (S): Download and Copyright: The database is being made available for researchers from 2023 onwards. Interested researchers can download this database upon request. Please send an email to christian.rathgeb@h-da.de. Any…
-
HDA Doppelgänger Face Database
HDA Doppelgänger Face Database The Hochschule Darmstadt (HDA) doppelgänger database contains 400 pairs of doppelgänger images collected from multiple web sources. Download and Copyright: The database is being made available for researchers from 2021 onwards. Interested researchers can download this database upon request. Please send an email to christian.rathgeb@h-da.de. Any commercial use/distribution of this database is…
-
HDA Facial Makeup Presentation Attack Database
HDA Facial Makeup Presentation Attack Database Hochschule Darmstadt (HDA) facial makeup presentation attack database (HDA_MPA_DB) contains web-collected facial images of individuals with and without makeup in several contexts: Bona fide makeup application. Identity concealment M-PAs. Impersonation M-PAs. Download and Copyright The database is being made available for researchers from 2021 onwards. Interested researchers can download…
-
HDA Facial Tattoo and Painting Database
HDA Facial Tattoo and Painting Database The Hochschule Darmstadt (HDA) facial tattoo and paintings database contains 500 pairs of facial images of individuals with and without facial tattoos or paintings. The database was collected from multiple online sources. Download and Copyright: The database is being made available for researchers from 2020 onwards. Interested researchers can…
-
HDA Plastic Surgery Face Database
HDA Plastic Surgery Face Database The Hochschule Darmstadt (HDA) plastic surgery database contains facial images taken before and after five types of popular face surgeries: Eyebrow correction Eyelid correction Facelift Facial bones correction Nose correction The HDA plastic surgery face database was collected from multiple web sources. Download and Copyright: The database is being made…
-
Presentation Attack Detection for Finger Recognition
Presentation Attack Detection for Finger Recognition Score files of the experiments using finger vein images for fingerprint presentation attack detection (PAD). Download The score files can be downloaded here. Attribution In case you are comparing your results to ours, please cite and reference our works for PLBP [1] or Luminosity, MC mean, and MC histogram…
-
MCIS
MCIS – Multi-Class Iris Segmentation A database providing semantic segmentation labels for 500 images of the NICE.I database. Download The database can be downloaded using the following link. To obtain the password for the database send a signed license agreement to dosorioroig@gmail.com and christian.rathgeb@h-da.de (in cc). Attribution Any publications using MCIS must cite and reference…
-
Measuring Unlinkability in Biometric Template Protection Systems
Measuring Unlinkability in Biometric Template Protection Systems Implementation of local and global unlinkability metrics for biometric template protection schemes proposed by Gomez-Barrero et al. [TIFS18] Code Free and unrestricted for academic and teaching use, but not for commercial purposes. Available at GitHub. Attribution More details in: [TIFS18] Marta Gomez-Barrero, Javier Galbally, Christian Rathgeb, Christoph Busch, “General Framework…
-
Multi-Biometric Template Protection Based on Bloom Filters
Multi-Biometric Template Protection Based on Bloom Filters Implementation of the feature level fusion of Bloom filter based protected templates proposed by Gomez-Barrero et al. [IF18] Code Free and unrestricted for academic and teaching use, but not for commercial purposes. Available at GitHub: The multi-biometric scheme to fuse two (or more) Bloom filter protected templates can be…
-
SIC-Gen
SIC-Gen: Synthetic Iris-Code generator A method for generation of large-scale synthetic Iris-Code databases proposed by Drozdowski et al. [1]. Code Free and unrestricted for academic and teaching use, but not for commercial purposes. Available at github. Attribution Any publications using SIC-Gen must cite and reference the conference paper [1], in which the method was proposed.…
-
da/sec WDSET02 multisensor fingerprint database
WDSET02 da/sec WDSET02 multisensor fingerprint database WDSET02 is a multisensor fingerprint database obtained using optical sensors for the acquisition of fingerprints subjected to four levels of moisture. The moisture level of the finger is determined by a skin moisture measuring apparatus prior to the acquisition process. The fingerprint dataset contains 6600 fingerprint samples acquired from 33 subjects…
-
MBASSy – Modular Biometric Authentication Service System
MBASSy (Modular Biometric Authentication Service System) Since the introduction of the iPhone, the number of smartphone users is steadily increasing. Because a variety of personal or business data is stored on smartphones, an increased need for information protection arises compared to traditional mobile phones. Current authentication solutions on these devices use knowledge-based methods, where the…
