http://dl.gi.de/handle/20.500.12116/20079 2026-07-21T13:43:39Z http://dl.gi.de/handle/20.500.12116/17696 Video-based fingerphoto recognition with anti-spoofing techniques with smartphone cameras Stein, Chris; Bouatou, Vincent; Busch, Christoph Brömme, Arslan; Busch, Christoph This work is concerned with the acquisition of fingerprints samples on smartphones with the built-in smartphone camera. A novel approach to capture multiple fingerphotos in a videostream with a smartphone camera and the processing of the photos for the finger recognition is discussed in this paper. The proposed technique offers a convenient and efficient way to capture multiple samples of a biometric instance in a short time frame. Due the fact that fingerphotos can be easily replicated with low effort (e.g. print outs with an ordinary printer) and thus are vulnerable to presentation attacks, anti-spoofing algorithms were developed to detect such spoof attempts. The algorithms for the detection and segmentation of the finger as well the preprocessing of the photo with graphical operations and anti-spoofing were implemented in a prototype as application for the Android operating system. User tests are performed to evaluate the usability and to create a database of biometric samples for offline evaluation of the recognition performance. Further tests are done with diverse artefacts such as printed finger images, fake fingers of gelatin, gummy and silicon as well finger replay videos to measure the resistance of the developed solution against presentation attacks. 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17694 Quality driven iris recognition improvement Cremer, Sandra; Lemperiere, Nadege; Dorizzi, Bernadette; Garcia-Salicetti, Sonia Brömme, Arslan; Busch, Christoph The purpose of the work presented in this paper is to adapt the feature extraction and matching steps of iris recognition to the quality of the input images. To this end we define a GMM-based global quality metric associated to a pair of normalized iris images. It quantifies the amount of artifact in these images as well as the amount of texture in artifact-free regions. First we use this metric to adjust, for each pair of irises, the proportion of the normalized image selected on a local quality criteria for feature extraction. This approach is tested with two matching techniques: one performs a bit to bit comparison of binary feature vectors and the other one computes local cross-correlations between real valued vectors. We show that our approach is effective with both techniques. Then we use our metric to choose the matching technique that is best adapted to each image pair in order to make a good compromise between accuracy and speed. 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17693 Absolute fingerprint pre-alignment in minutiae-based cryptosystems Tams, Benjamin Brömme, Arslan; Busch, Christoph Most biometric cryptosystems that have been proposed to protect fingerprint minutiae make use of public alignment helper data. This, however, has the inadvertent effect of information leakage about the protected templates. A countermeasure to avoid auxiliary alignment data is to protect absolutely pre-aligned fingerprints. As a proof of concept, we run performance evaluations of a minutiae fuzzy vault with an automatic method for absolute pre-alignment. Therefore, we propose a new method for estimating a fingerprint's directed reference point by modeling the local orientation around the core as a tented arch.1 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17692 Simulated annealing attack on certain fingerprint authentication systems Pashalidis, Andreas Brömme, Arslan; Busch, Christoph This paper describes a simple and generic attack against minutiae-based fingerprint authentication systems. The aim of the attack is to construct a fingerprint minutiae template, compliant to ISO/IEC standards, that matches a fixed but unknown target fingerprint. Our attack is expected to be most effective against systems that employ vicinity-based matching algorithms, i.e. systems that divide fingerprints into multiple regions and then compute similarity over these regions. The effectiveness of our attack is experimentally demonstrated against the recently proposed `Protected Minutiae Cylinder Code' (PMCC) scheme. 2013-01-01T00:00:00Z