By Topic

Biometrics: Theory, Applications, and Systems, 2009. BTAS '09. IEEE 3rd International Conference on

Date 28-30 Sept. 2009

Filter Results

Displaying Results 1 - 25 of 81
  • Author list

    Page(s): 1 - 15
    Save to Project icon | Request Permissions | PDF file iconPDF (370 KB)  
    Freely Available from IEEE
  • BTAS'09 Organizing Committee

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (185 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (132 KB)  
    Freely Available from IEEE
  • An experimental study on content-based face annotation of photos

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (637 KB) |  | HTML iconHTML  

    Face annotation of photos, a key enabling technology for many exciting new applications, has been gaining broad interest. The task is different from the general face recognition problem because the dataset is not constrained - an unlabelled face may not have any corresponding match in the training set. Moreover, faces in real-life photos have a significantly wider variation range than those in the conventional face datasets. We designed and conducted a thorough experimental study to understand the efficacy of face recognition methods for annotating faces in real-world scenarios. The findings of this study should provide information for various design choices for a practical and high-accuracy face annotation system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quality based rank-level fusion in multibiometric systems

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (622 KB) |  | HTML iconHTML  

    Multibiometric systems fuse evidences from multiple biometric sources typically resulting in better recognition accuracy. These systems can consolidate information at various levels. For systems operating in the identification mode, rank level fusion presents a viable option. In this paper, several simple but powerful modifications are suggested to enhance the performance of rank-level fusion schemes in the presence of weak classifiers or low quality input images. These modifications do not require a training phase, therefore making them suitable in a wide range of applications. Experiments conducted on a multimodal database consisting of a few hundred users indicate that the suggested modifications to the highest rank and Borda count methods significantly enhance the rank-1 accuracy. Experiments also reveal that including image quality in the fusion scheme enhances the Borda count rank-1 accuracy by ~40%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized multi-ethnic face age-estimation

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB) |  | HTML iconHTML  

    Age estimation from digital pictures of the face is a very promising research field that is now receiving wide attention. As with any good research problem, face age-estimation is wrought with many challenging interactions that cannot easily be separated out. In general, aging patterns are well understood for all humans, however, these patterns become confounded by intrinsic factors of genetics, gender differences, and ethnic deviations and, equally as important, extrinsic factors of the environment and behavior choices (i.e. sun exposure, drugs, cigarettes, etc). This novel work focuses on the development of a generalized multi-ethnic age-estimation technique - the first of its kind. In addition to the novelty of this approach, the system's overall performance measure (MAE) is ldquoon parrdquo with algorithms that are tuned for a specific ethnic group. Further, the proposed system performance proves to be far more stable across age than the best published results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous latent fingerprint recognition: A preliminary study

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (509 KB) |  | HTML iconHTML  

    Recent cases such as Commonwealth v Patterson show that there is a lack of research in how to process and recognize simultaneous fingerprint impressions, especially when none of the latent prints in the cluster could be individually matched. SWGFAST released the first version of the standard on simultaneous impression examination that can help fingerprint examiners to systematically compare latent simultaneous impressions to a known ten-print card. However, when the individual is not known, the simultaneous fingerprint impressions have to be compared using a large database of reference ten-prints, making the process very challenging. This paper introduces the research problem of identifying simultaneous latent fingerprint impressions to the community and presents a semi-automatic approach to process the impressions of any individual. The approach generates a list of top matches and latent fingerprint examiners can then examine them for individualization. Using a fingerprint database that contains simultaneous latent impressions, we analyze the performance of the proposed approach obtained by matching simultaneous impressions with the gallery database. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unconstrained face recognition using MRF priors and manifold traversing

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3985 KB) |  | HTML iconHTML  

    In this paper, we explore new methods to improve the modeling of facial images under different types of variations like pose, ambient illumination and facial expression. We investigate the intuitive assumption that the parameters for the distribution of facial images change smoothly with respect to variations in the face pose angle. A Markov random field is defined to model a smooth prior over the parameter space and the maximum a posteriori solution is computed. We also propose extensions to the view-based face recognition method by learning how to traverse between different subspaces so we can synthesize facial images with different characteristics for the same person. This allow us to enroll a new user with a single 2D image. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Agent-based image iris segmentation and multiple views boundary refining

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (586 KB) |  | HTML iconHTML  

    The paper presents two different methods to deal with the problem of iris segmentation: an agent-based method capable to localize the center of the pupil and a method to process the iris boundaries by a multiple views approach. In the first method, an agent corresponds to the coordinates of a specific point of analysis in the input image. A population of agents is deployed in the input image, then, each agent collects local information concerning the intensity patterns visible in its region of interest. By iterations, an agent changes its position accordingly to the local properties, moving towards the estimation of the pupil center. If no available information is present in its region of interest, the agent will move itself along a random walk. After few iterations, the population tends to spread and then concentrate in the inner portion of the pupil. Once the center of the pupil has been located, the inner and outer iris boundaries are refined by an approach based on multiple views analysis. This method starts with a set of points that can be considered as an approximation of the pupil center. For each point, a detailed estimation of the iris boundaries is computed, and the final description of the iris boundaries is obtained by merging all the obtained descriptions. The two methods were tested using CASIA v.3 and UBIRIS v.2 images. Experiments show that the proposed approaches are feasible, also in eye images taken in noisy or non-ideal conditions, achieving a total error segmentation accuracy up to 97%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards 3D-aided profile-based face recognition

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1521 KB) |  | HTML iconHTML  

    In this paper, we present a fully automatic system for face recognition based on a silhouette of the face profile. Previous research has demonstrated the high discriminative potential of this biometric. However, for the successful employment of this characteristic one is confronted with many challenges, such as the sensitivity of a profile's geometry to face rotation and the difficulty of accurate profile extraction from images. We propose to explore the feature space of profiles under various rotations with the aid of a 3D face model. In the enrollment mode, 3D data of subjects are acquired and used to create profiles under different rotations. The features extracted from these profiles are used to train a classifier. In the identification mode, the profiles are extracted from side view images using a modified active shape model approach. We validate the accuracy of the extractor and the robustness of classification algorithms using data from a publicly available database. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel approach to design of user re-authentication systems

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB) |  | HTML iconHTML  

    In the Internet age, security is a major concern as identity thefts often cause detrimental effects. Masquerading is an important factor for identity theft and current authentication systems using traditional methods woefully lack mechanisms to detect and prevent it. This paper presents an application independent, continual, non-intrusive, fast and easily deployable user re-authentication system based on behavioral biometrics. These behavioral attributes are extracted from the keyboard and mouse operations of the user. They are used to identify and non-intrusively authenticate the user periodically. To extract suitable user attributes, we propose a novel heuristic that uses the percentage of mouse-to-keyboard interaction ratio and interaction quotient (IQ). In the re-authentication process, every time, the current behavior of the user is compared with the stored ldquoexpectedrdquo behavior. All deviations are noted and after a certain deviation threshold is reached, the system logs the user out of the current session. The underlying heuristic prevents imposters from misusing the system. Experimental results show that the proposed heuristic can greatly improve the accuracy of application-based and application independent systems to 96.4% and 82.2% respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face alignment by minimizing the closest classification distance

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB) |  | HTML iconHTML  

    In this paper, we present a face registration approach, in which alignment is done by minimizing the closest distance at the classification step. This method eliminates the need of a feature localization step that exists in traditional face recognition systems and formulates alignment as an optimization process during classification. In other words, instead of performing a separate facial feature localization step and localizing facial features according to some type of feature matching score, in the proposed method, alignment is done by directly optimizing the classification score. Moreover, a feature detector can still be integrated to the system. In this case, the output of the feature detector is used as the initial point of the optimization process. Results of extensive experiments have shown that the proposed approach leads very high correct recognition rates, especially in the case of partial face occlusion, where it is not possible to precisely detect the facial feature locations. It has been also found that, in the case of using a facial feature detector, the approach can tolerate localization errors of up to 18% of the interocular distance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cost curve analysis of biometric system performance

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (752 KB) |  | HTML iconHTML  

    Biometric classification algorithms typically offer a range of performance characteristics which balance false non-match and false match rates. Nevertheless, the threshold which meets application requirements is usually selected without explicit consideration of cost implications of misclassification. This paper presents the analysis of recognition performance of multiple face and fingerprint algorithms using cost curves. Cost curves allow the introduction of misclassification costs and prior probabilities of proportions of genuine and impostor classes in the selection of biometric system thresholds. The inclusion of misclassification costs and prior probabilities is important since they can either change with time, or with the location where the biometric system is deployed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On assessing the robustness of pen coordinates, pen pressure and pen inclination to time variability with personal entropy

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (302 KB) |  | HTML iconHTML  

    In this work, we study different combinations of the five time functions captured by a digitizer in presence or not of time variability. To this end, we propose two criteria independent of the classification step: personal entropy, introduced in our previous works and an intra-class variability measure based on dynamic time warping. We confront both criteria to system performance using a hidden Markov model (HMM) and dynamic time warping (DTW). Moreover, we introduce the concept of short-term time variability, proposed on MCYT-100, and long-term time variability studied with BIOMET database. Our experiments clarify conflicting results in the literature and confirm some other: pen inclination angles are very unstable in presence or not of time variability; the only combination which is robust to time variability is that containing only coordinates; finally, pen pressure is not recommended in the long-term context, although it may give better results in terms of performance (according to the classifier used) in the short-term context. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online learning in biometrics: A case study in face classifier update

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (199 KB) |  | HTML iconHTML  

    In large scale applications, hundreds of new subjects may be regularly enrolled in a biometric system. To account for the variations in data distribution caused by these new enrollments, biometric systems require regular re-training which usually results in a very large computational overhead. This paper formally introduces the concept of online learning in biometrics. We demonstrate its application in classifier update algorithms to re-train classifier decision boundaries. Specifically, the algorithm employs online learning technique in a 2nu-granular soft support vector machine for rapidly training and updating face recognition systems. The proposed online classifier is used in a face recognition application for classifying genuine and impostor match scores impacted by different covariates. Experiments on a heterogeneous face database of 1,194 subjects show that the proposed online classifier not only improves the verification accuracy but also significantly reduces the computational cost. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploring multispectral iris recognition beyond 900nm

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1707 KB) |  | HTML iconHTML  

    Most iris recognition systems acquire images of the eye in the 700 nm-900 nm range of the electromagnetic spectrum. In this work, the iris is examined at wavelengths beyond 900 nm. The purpose is to understand the iris structure at longer wavelengths and to determine the possibility of performing cross-spectral iris matching. An acquisition system is first designed for imaging the iris at narrow spectral bands in the 950 nm-1650 nm range. Next, the left and right images of the iris are acquired from 25 subjects in order to conduct the analysis. Finally, the possibility of performing cross-spectral matching and multispectral fusion at the match score level is investigated. Experimental results suggest: (a) the feasibility of acquiring iris images in wavelengths beyond 900 nm using InGaAs detectors; (b) the possibility of observing different structures in the iris anatomy at various wavelengths; and (c) the potential of performing cross-spectral matching and multispectral fusion for enhanced iris recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparing verification performance of kids and adults for Fingerprint, Palmprint, Hand-geometry and Digitprint biometrics

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1436 KB) |  | HTML iconHTML  

    With the large scale deployment of biometrics for access control in private and public places, systems are faced the challenge of processing a diverse range of people. Most systems have been well evaluated for adults, however, their application in schools, or for private door access control, raises the question, whether there exists significant difference in performance between age groups in general and between kids and adults in particular. This paper targets an evaluation of the impact of children as biometric users on recognition accuracy for a series of hand-based modalities: Fingerprint, Palmprint, Hand-geometry and Digitprint. Furthermore, we try to analyze reasons for child-aging effects on performance at both feature and instance level using our database of 301 kids and 86 adults. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pose manifold curvature is typically less near frontal face views

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3076 KB) |  | HTML iconHTML  

    This research presents a study of the geometry of the face manifold as a person changes their horizontal pose from one profile to another. Although, a lot of research has gone into aspects of determining an ideal pose for pose invariant face recognition, less has been done to present the manifold of the faces presented by these pose variations. The novelty of our approach lies in the presentation of a finely sampled profile-to-profile dataset that is analyzed using Locally Linear Embedding (LLE) to estimate the curvature of these manifolds. Our results indicate that the profile-to-profile manifold is less curved, hence more linear, in the region around the frontal view than for any other region of the manifold, i.e. pose. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparsity inspired selection and recognition of iris images

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (339 KB) |  | HTML iconHTML  

    Iris images acquired from a partially cooperating subject often suffer from blur, occlusion due to eyelids, and specular reflections. The performance of existing iris recognition systems degrade significantly on these images. Hence it is essential to select good images from the incoming iris video stream, before they are input to the recognition algorithm. In this paper, we propose a sparsity based algorithm for selection of good iris images and their subsequent recognition. Unlike most existing algorithms for iris image selection, our method can handle segmentation errors and a wider range of acquisition artifacts common in iris image capture. We perform selection and recognition in a single step which is more efficient than devising separate specialized algorithms for the two. Recognition from partially cooperating users is a significant step towards deploying iris systems in a wide variety of applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Periocular biometrics in the visible spectrum: A feasibility study

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (414 KB) |  | HTML iconHTML  

    Periocular biometric refers to the facial region in the immediate vicinity of the eye. Acquisition of the periocular biometric does not require high user cooperation and close capture distance unlike other ocular biometrics (e.g., iris, retina, and sclera). We study the feasibility of using periocular images of an individual as a biometric trait. Global and local information are extracted from the periocular region using texture and point operators resulting in a feature set that can be used for matching. The effect of fusing these feature sets is also studied. The experimental results show a 77% rank-1 recognition accuracy using 958 images captured from 30 different subjects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Satellite communications as a viable method for biometric record transfer in field biometric devices

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB) |  | HTML iconHTML  

    The use of biometrics, and their associated handheld field devices, as an identification and verification technique is growing at a considerable rate. Governments and private organizations are making significant investments to identify and research new types of biometrics while pushing the industry to provide scanners capable of weathering field missions. In parallel, similar levels of investment are being made to build centralized databases that have the capability to query millions of records in a matter of seconds. While these investments push the biometric industry forward, lesser time has been invested into linking biometric scanners with a remote database. Commercially available scanners rely heavily on the evolution of the cellular industry or a satellite connected portable laptop to provide the necessary bandwidths required to transmit biometric records from the scanner to the remote database. This paper explores the use of satellite communications in handheld field sensors as a global communications link between biometric scanners and a remote database. The present work discusses and evaluates biometric type, file size, and satellite bandwidth for satellite communications on handheld field biometric devices. The paper concludes by identifying an emerging product, not yet commercially available, that integrates satellite technology into a product already capable of linking legacy wireless capable scanners with a remote database. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A 3-D assisted generative model for facial texture super-resolution

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1396 KB) |  | HTML iconHTML  

    This paper describes an example-based Bayesian method for 3D-assisted pose-independent facial texture super-resolution. The method utilizes a 3D morphable model to map facial texture from a 2D face image to a pose- and shape-normalized texture map and vice versa. The center piece of this method is a generative model to describe the process of forming an image from a pose- and shape-normalized texture map. The goal is to reconstruct a high-resolution texture map given an low-resolution face image. The prior knowledge about the sought high-resolution texture is incorporated into the Bayesian framework by using a recognition-based prior that encourages the gradient values of the texture map to be close to some predicted values. We develop the generative model and formulate the problem as MAP estimation. The results show that this framework is capable of performing pose-independent face recognition even when the sample set only contains exemplar face images with frontal pose. We present results in frontal and non-frontal poses. We also demonstrate that the technique can be utilized to improve face recognition results when the probe images have a lower resolution compared to the gallery images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical analysis of fingerprint sensor interoperability performance

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (253 KB) |  | HTML iconHTML  

    The proliferation of networked authentication systems has put focus on the issue of interoperability. Fingerprint sensors are based on a variety of different technologies that introduce inconsistent distortions and variations in the feature set of the captured image, which makes the goal of interoperability challenging. The motivation of this research was to examine the effect of fingerprint sensor interoperability on the performance of a minutiae based matcher. A statistical analysis framework for testing interoperability was formulated to test similarity of minutiae count, image quality and similarity of performance between native and interoperable datasets. False non-match rate (FNMR) was used as the performance metric in this research. Interoperability performance analysis was conducted on each sensor dataset and also by grouping datasets based on the acquisition technology and interaction type of the acquisition sensor. The lowest interoperable FNMR observed was 0.12%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral minutiae representations of fingerprints enhanced by quality data

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (866 KB) |  | HTML iconHTML  

    Many fingerprint recognition systems are based on minutiae matching. However, the recognition accuracy of minutiae-based matching algorithms is highly dependent on the fingerprint minutiae quality. Therefore, in this paper, we introduce a quality integrated spectral minutiae algorithm, in which the minutiae quality information is incorporated to enhance the performance of the spectral minutiae fingerprint recognition system. In our algorithm, two types of quality data are used. The first one is the minutiae reliability, expressing the probability that a given point is indeed a minutia; the second one is the minutiae location accuracy, quantifying the error on the minutiae location. We integrate these two types of quality information into the spectral minutiae representation algorithm and achieve a decrease in the equal error rate of over 20% in the experiment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fingerprint recognition performance in rugged outdoors and cold weather conditions

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (592 KB) |  | HTML iconHTML  

    This paper reports on tests of the performance of fingerprint recognition technology in rugged outdoor conditions, with an especial concentration on the performance in cold weather. We analyze: (1) chip versus optical fingerprint scanner technology, (2) recognition performance and image quality, and (3) user/device interaction. A outdoor fingerprint door access system was designed to capture fingerprint images and video data of user interactions. Using this device, data were captured over a period of two years, and a user survey performed. Data were analyzed in terms of biometric error rates and fingerprint quality (NFIQ) as a function of temperature and humidity. Results suggest: (1) biometric performance has no significant dependence on temperature and humidity (-30C to +20C), (2) both chip based and optical fingerprint scanners have some flaws in rugged and cold weather applications, and (3) overall fingerprint biometric technology has a good level of usability in this application. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.