Federico M. Sukno

The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB)

A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence is presented. It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1 over the Internet, 2 in an office environment with desktop PC, and 3 in indoor/outdoor environments with mobile portable hardware. The three scenarios include a common part of audio/video data. Also, signature and fingerprint data have been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data were acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions. Additional features of the BioSecure Multimodal Database (BMDB) are: two acquisition sessions, several sensors in certain modalities, balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity, availability of demographic data, and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB allow us to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.

Active Shape Models with Invariant Optimal Features: Application to Facial Analysis

This work is framed in the field of statistical face analysis. In particular, the problem of accurate segmentation of prominent features of the face in frontal view images is addressed. We propose a method that generalizes linear active shape models (ASMs)l which have already been used for this task. The technique is built upon the development of a nonlinear intensity model, incorporating a reduced set of differential invariant features as local image descriptors. These features are invariant to rigid transformations, and a subset of them is chosen by sequential feature selection for each landmark and resolution level. The new approach overcomes the unimodality and Gaussianity assumptions of classical ASMs regarding the distribution of the intensity values across the training set. Our methodology has demonstrated a significant improvement in segmentation precision as compared to the linear ASM and optimal features ASM (a nonlinear extension of the pioneer algorithm) in the tests performed on AR, XM2VTS, and EQUINOX databases.

A High-Resolution Atlas and Statistical Model of the Human Heart From Multislice CT

Atlases and statistical models play important roles in the personalization and simulation of cardiac physiology. For the study of the heart, however, the construction of comprehensive atlases and spatio-temporal models is faced with a number of challenges, in particular the need to handle large and highly variable image datasets, the multi-region nature of the heart, and the presence of complex as well as small cardiovascular structures. In this paper, we present a detailed atlas and spatio-temporal statistical model of the human heart based on a large population of 3D+time multi-slice computed tomography sequences, and the framework for its construction. It uses spatial normalization based on nonrigid image registration to synthesize a population mean image and establish the spatial relationships between the mean and the subjects in the population. Temporal image registration is then applied to resolve each subject-specific cardiac motion and the resulting transformations are used to warp a surface mesh representation of the atlas to fit the images of the remaining cardiac phases in each subject. Subsequently, we demonstrate the construction of a spatio-temporal statistical model of shape such that the inter-subject and dynamic sources of variation are suitably separated. The framework is applied to a 3D+time data set of 138 subjects. The data is drawn from a variety of pathologies, which benefits its generalization to new subjects and physiological studies. The obtained level of detail and the extendability of the atlas present an advantage over most cardiac models published previously.

Automatic Construction of 3D-ASM Intensity Models by Simulating Image Acquisition: Application to Myocardial Gated SPECT Studies

Active shape models bear a great promise for model-based medical image analysis. Their practical use, though, is undermined due to the need to train such models on large image databases. Automatic building of point distribution models (PDMs) has been successfully addressed and a number of autolandmarking techniques are currently available. However, the need for strategies to automatically build intensity models around each landmark has been largely overlooked in the literature. This work demonstrates the potential of creating intensity models automatically by simulating image generation. We show that it is possible to reuse a 3D PDM built from computed tomography (CT) to segment gated single photon emission computed tomography (gSPECT) studies. Training is performed on a realistic virtual population where image acquisition and formation have been modeled using the SIMIND Monte Carlo simulator and ASPIRE image reconstruction software, respectively. The dataset comprised 208 digital phantoms (4D-NCAT) and 20 clinical studies. The evaluation is accomplished by comparing point-to-surface and volume errors against a proper gold standard. Results show that gSPECT studies can be successfully segmented by models trained under this scheme with subvoxel accuracy. The accuracy in estimated LV function parameters, such as end diastolic volume, end systolic volume, and ejection fraction, ranged from 90.0% to 94.5% for the virtual population and from 87.0% to 89.5% for the clinical population.

Automatic cardiac MRI segmentation using a biventricular deformable medial model

We present a novel approach for automatic segmentation of the myocardium in short-axis MRI using deformable medial models with an explicit representation of thickness. Segmentation is constrained by a Markov prior on myocardial thickness. Best practices from Active Shape Modeling (global PCA shape prior, statistical appearance model, local search) are adapted to the medial model. Segmentation performance is evaluated by comparing to manual segmentation in a heterogeneous adult MRI dataset. Average boundary displacement error is under 1.4 mm for left and right ventricles, comparing favorably with published work.

3-D Facial Landmark Localization With Asymmetry Patterns and Shape Regression from Incomplete Local Features

We present a method for the automatic localization of facial landmarks that integrates nonrigid deformation with the ability to handle missing points. The algorithm generates sets of candidate locations from feature detectors and performs combinatorial search constrained by a flexible shape model. A key assumption of our approach is that for some landmarks there might not be an accurate candidate in the input set. This is tackled by detecting partial subsets of landmarks and inferring those that are missing, so that the probability of the flexible model is maximized. The ability of the model to work with incomplete information makes it possible to limit the number of candidates that need to be retained, drastically reducing the number of combinations to be tested with respect to the alternative of trying to always detect the complete set of landmarks. We demonstrate the accuracy of the proposed method in the face recognition grand challenge database, where we obtain average errors of approximately 3.5 mm when targeting 14 prominent facial landmarks. For the majority of these our method produces the most accurate results reported to date in this database. Handling of occlusions and surfaces with missing parts is demonstrated with tests on the Bosphorus database, where we achieve an overall error of 4.81 and 4.25 mm for data with and without occlusions, respectively. To investigate potential limits in the accuracy that could be reached, we also report experiments on a database of 144 facial scans acquired in the context of clinical research, with manual annotations performed by experts, where we obtain an overall error of 2.3 mm, with averages per landmark below 3.4 mm for all 14 targeted points and within 2 mm for half of them. The coordinates of automatically located landmarks are made available on-line.

Active shape models with invariant optimal features (IOF-ASMs)

This paper is framed in the field of statistical face analysis. In particular, the problem of accurate segmentation of prominent features of the face in frontal view images is addressed. Our method constitutes an extension of Cootes et al. [6] linear Active Shape Model (ASM) approach, which has already been used in this task [9]. The technique is built upon the development of a non-linear appearance model, incorporating a reduced set of differential invariant features as local image descriptors. These features are invariant to rigid transformations, and a subset of them is chosen by Sequential Feature Selection (SFS) for each landmark and resolution level. The new approach overcomes the unimodality and gaussianity assumptions of classical ASMs regarding the distribution of the intensity values across the training set. Validation of the method is presented against the linear ASM and its predecesor, the Optimal Features ASM (OF-ASM) [14] using the AR and XM2VTS databases as testbed.

A Confidence-Based Update Rule for Self-updating Human Face Recognition Systems

The aim of this paper is to present an automatic update rule to make a face recognition system adapt itself to the continuously changing appearance of users. The main idea is that every time the system interacts with a user, it adapts itself to include his or her current appearance, and thus, it always stays up-to-date. We propose a novel quality measure, which is used to decide whether the information just learnt from a user can be used to aggregate to what the system already knows. In the absence of databases that suit our needs, we present a publicly available database with 14,279 images of 35 users and 74 impostors acquired in a span of 5 months. Experiments on this database show that the proposed measure is adequate for a system to learn the current appearance of users in a non-supervised manner.

Similarity-based Fisherfaces

In this article, a face recognition algorithm aimed at mimicking the human ability to differentiate people is proposed. For each individual, we first compute a projection line that maximizes his or her dissimilarity to all other people in the user database. Facial identity is thus encoded in the dissimilarity pattern composed by all the projection coefficients of an individual against all other enrolled user identities. Facial recognition is achieved by calculating the dissimilarity pattern of an unknown individual with that of each enrolled user. As the proposed algorithm is composed of different one-dimensional projection lines, it easily allows adding or removing users by simply adding or removing the corresponding projection lines in the system. Ideally, to minimize the influence of these additions/removals, the user group should be representative enough of the general population. Experiments on three widely used databases (XM2VTS, AR and Equinox) show consistently good results. The proposed algorithm achieves Equal Error Rate (EER) and Half-Total Error Rate (HTER) values in the ranges of 0.41-1.67% and 0.1-1.95%, respectively. Our approach yields results comparable to the top two winners in recent contests reported in the literature.

A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction

Computational atlases based on nonrigid registration have found much use in the medical imaging community. To avoid bias to any single element of the training set, there are two main approaches: using a (random) subject to serve as an initial reference and posteriorly removing bias, and a true groupwise registration with a constraint of zero average transformation for direct computation of the atlas. Major drawbacks are the possible selection of an outlier on one side, and an initialization with an invalid instance on the other. In both cases there is great potential for affecting registration performance, and producing a final average image in which the structure of interest deviates from the central anatomy of the population under study. We propose an inexpensive means of reference selection based on a groupwise correspondence measure, which avoids the selection of an outlier and is independent from the atlas construction approach that follows. Thus, it improves tractability of reference selection and robustness of automated atlas construction. We illustrate the method using a set of 20 cardiac multislice computed tomography volumes.