- KonferenzbeitragImage metric-based biometric comparators: a supplement to feature vector-based Hamming distance?(BIOSIG 2012, 2012) Hofbauer, Heinz; Rathgeb, Christian; Uhl, Andreas; Wild, Peter; Brömme, Arslan; Busch, ChristophIn accordance with the ISO/IEC FDIS 19794-6 standard an iris-biometric fusion of image metric-based and Hamming distance (HD) comparison scores is presented. In order to demonstrate the applicability of a knowledge transfer from image quality assessment to iris recognition, Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Local Edge Gradients metric (LEG), Edge Similarity Score (ESS), Local Feature Based Visual Security (LFBVS), and Visual Information Fidelity (VIF) are applied to iris textures, i.e. query textures are interpreted as noisy representations of registered ones. Obtained scores are fused with traditional HD scores obtained from iris-codes generated by different feature extraction algorithms. Experimental evaluations on the CASIA-v3 iris database confirm the soundness of the proposed approach.
- KonferenzbeitragEvaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport(BIOSIG 2012, 2012) Spreeuwers, Luuk J.; Hendrikse, Anne J.; Gerritsen, Kier-Co J.; Brömme, Arslan; Busch, ChristophAutomatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99% at a False Accept Rate (FAR) of 0.1% or even lower.
- KonferenzbeitragExploiting data-rich regions of interest in static signature verification(BIOSIG 2012, 2012) Johnson, Emma P. S.; Guest, Richard M.; Brömme, Arslan; Busch, ChristophThe identification and subsequent utilisation of regions of interest within biometric sample images can provide useful information that can benefit recognition performance. If a specific area of a biometric sample is data-rich in terms of feature quantity or quality then these regions of specific interest can be exploited, for example in terms of processing algorithm selection and information weighting. Also, if intra-area stability/feature repeatability can be obtained a-priori this information may be used to enhance biometric systems. The objective of the work documented in this paper is to develop a best practice framework for the utilisation of sub regions of interest within biometric signature images to enable an optimisation of systems. Our hypothesis is that by sub-dividing a signature image, information richness within sub-divisions can be exploited by weighting grid zones. Signature images were divided using 14 experimental template patterns. Using the GPDS-960 off-line signature corpus, the verification performance achieved using each weighted method was compared against a non-gridded baseline implementation. Significant improvements were noted for a number of the defined grid zones indicating the potential for the approach.
- KonferenzbeitragHow a local quality measure can help improving iris recognition(BIOSIG 2012, 2012) Cremer, Sandra; Dorizzi, Bernadette; Garcia-Salicetti, Sonia; Lempérière, Nadège; Brömme, Arslan; Busch, ChristophThe most common iris recognition systems extract features from the iris after segmentation and normalization steps. In this paper, we propose a new strategy to select the regions of normalized iris images that will be used for feature extraction. It consists in sorting different sub-images of the normalized images according to a GMM-based local quality measure we have elaborated and selecting the N best sub-images for feature extraction. The proportion of the initial image that is kept for feature extraction has been set in order to compromise between minimizing the amount of noise taken into account for feature extraction and maximizing the amount of information available for matching. By proceeding this way, we privilege the regions for which our quality measure gives the highest values, namely regions of the iris that are highly textured and free from occlusion, and minimize the risks of extracting features in occluded regions to which our quality measure gives the lowest values. We also control the amount of information we use for matching by including, if necessary, regions that are given intermediate values by our quality measure and are free from occlusion but barely textured. Experiments were performed on three different databases: ND-IRIS- 0405, Casia-IrisV3-Interval and Casia-IrisV3-Twins, and show a significant improvement of recognition performance when using our strategy to select regions for feature extraction instead of using a binary segmentation mask and considering all unmasked regions equally.
- KonferenzbeitragFingerphoto recognition with smartphone cameras(BIOSIG 2012, 2012) Stein, Chris; Nickel, Claudia; Busch, Christoph; Brömme, Arslan; Busch, ChristophThis paper is concerned with the authentication of people on smartphones using fingerphoto recognition. In this work, fingerphotos are captured with the built-in camera of the smartphone. The proposed authentication method is analyzed for feasibility and implemented in a prototype as application for the Android operating system. Algorithms for the capture process are developed to ensure a minimum of quality of the captured photos to enable a reliable fingerphoto recognition. Several methods for preprocessing of the captured samples are analyzed and performant solutions to evaluate the photos are developed to enhance the recognition rates. This is achieved by evaluating a wide range of different parameters and configurations of the algorithms as well as various combinations of preprocessing chains for the captured samples. The operations for preprocessing are selected with respect to their computational effort to guarantee that they can be executed on a smartphone with limited computation and memory capacity. The developed prototype is evaluated in user tests with two different smartphones. Additionally, a biometric database containing photos of the two test devices from 41 test subjects is created. These fingerphotos are used to evaluate and optimize the procedures.
- Editiertes BuchBIOSIG 2012(2012) Brömme, Arslan; Busch, Christoph
- KonferenzbeitragCommon mistakes on face recognition based on video(BIOSIG 2012, 2012) Despiegel, Vincent; Gentric, Stéphane; Brömme, Arslan; Busch, ChristophAutomatic border control e gates relies on face recognition in video streams. Two family of methods could be imagined to define a common workflow: encode all that is possible or select the best image of the stream according to a quality assessment. In gates, giving an answer as soon as possible by encoding each and every possible image seems to lead to faster gates. Is it really the case?
- KonferenzbeitragCurvelet transform-based features extraction for fingerprint identification(BIOSIG 2012, 2012) Guesmi, Hanene; Trichili, Hanene; Alimi, Adel M.; Solaiman, Basel; Brömme, Arslan; Busch, ChristophThe performance of the fingerprint identification process highly depends on its extractor of fingerprint features. So, to reduce the dimensionality of the fingerprint image and improve the identification rate, a fingerprint features extraction method based on Curvelet transform is proposed and presented in this paper. Thus, our paper focuses on presenting of our Curvelet-based fingerprint features extraction method. This method consists of two steps: decompose the fingerprint into set of sub-bands by the Curvelet transform and automatic extraction of the most discriminative statistical features of these sub-bands. An extensive experimental evaluation shows that the proposed method is effective and encouraging.
- KonferenzbeitragMulti-modal and multi-instance fusion for biometric cryptosystems(BIOSIG 2012, 2012) Merkle, Johannes; Kevenaar, Tom; Korte, Ulrike; Brömme, Arslan; Busch, ChristophBiometric cryptosystems allow cryptographic privacy protection for biometric reference data without storing a secret key. However, their security is inherently limited by the discriminative information content of the biometric feature data. Given the currently exploitable entropy of biometric features, one of the most promising approaches to achieve high privacy levels is to combine several biometric modalities or several instances of the same biometric modality. In this contribution, we theoretically analyze multibiometric fusion strategies for biometric cryptosystems with respect to their impact on security and recognition accuracy. We also introduce hash level as a new fusion level. Furthermore, we give a more detailed analysis for the most prominent schemes, the Fuzzy Commitment Scheme and the Fuzzy Vault.
- KonferenzbeitragBiometrics for an ageing society – societal and ethical factors in biometrics and ageing(BIOSIG 2012, 2012) Rebera, Andrew P.; Guihen, Barry; Brömme, Arslan; Busch, ChristophBy the middle of the twenty-first century around one third of the European population will be aged 65 or over. This poses two main challenges to biometrics. First, the quality of an image capturable from an older person is likely to be inferior to that of a younger person, leading to increased failure to capture or failure to enroll rates. Second, since biometric features alter over time, `within-person variation' and `template ageing' lead to significant system performance degradation. As society ages the need for solutions becomes increasingly urgent. This paper addresses a major societal and ethical issue this need provokes.