Lille, France
Lille, France

TELECOM Lille 1 is a French public grande école . · TELECOM Lille 1 is located on the campus of Lille University of Science and Technology in Villeneuve d'Ascq near Lille. TELECOM Lille 1 is part of Institut Mines-Télécom. Wikipedia.


Time filter

Source Type

Maalej A.,Lille University of Science and Technology | Maalej A.,Telecom Lille 1 | Amor B.B.,Lille University of Science and Technology | Amor B.B.,Telecom Lille 1 | And 4 more authors.
Pattern Recognition | Year: 2011

In this paper we address the problem of 3D facial expression recognition. We propose a local geometric shape analysis of facial surfaces coupled with machine learning techniques for expression classification. A computation of the length of the geodesic path between corresponding patches, using a Riemannian framework, in a shape space provides a quantitative information about their similarities. These measures are then used as inputs to several classification methods. The experimental results demonstrate the effectiveness of the proposed approach. Using multiboosting and support vector machines (SVM) classifiers, we achieved 98.81% and 97.75% recognition average rates, respectively, for recognition of the six prototypical facial expressions on BU-3DFE database. A comparative study using the same experimental setting shows that the suggested approach outperforms previous work. © 2011 Elsevier Ltd. All rights reserved.


Ballihi L.,Laboratoire Dinformatique Fondamentale Of Lille | Ballihi L.,Mohammed V University | Ben Amor B.,Telecom Lille 1 | Daoudi M.,Telecom Lille 1 | And 2 more authors.
IEEE Transactions on Information Forensics and Security | Year: 2012

We utilize ideas from two growing but disparate ideas in computer visionshape analysis using tools from differential geometry and feature selection using machine learningto select and highlight salient geometrical facial features that contribute most in 3-D face recognition and gender classification. First, a large set of geometries curve features are extracted using level sets (circular curves) and streamlines (radial curves) of the Euclidean distance functions of the facial surface; together they approximate facial surfaces with arbitrarily high accuracy. Then, we use the well-known Adaboost algorithm for feature selection from this large set and derive a composite classifier that achieves high performance with a minimal set of features. This greatly reduced set, consisting of some level curves on the nose and some radial curves in the forehead and cheeks regions, provides a very compact signature of a 3-D face and a fast classification algorithm for face recognition and gender selection. It is also efficient in terms of data storage and transmission costs. Experimental results, carried out using the FRGCv2 dataset, yield a rank-1 face recognition rate of 98% and a gender classification rate of 86% rate. © 2012 IEEE.


Drira H.,Telecom Lille 1 | Ben Amor B.,Telecom Lille 1 | Srivastava A.,Florida State University | Daoudi M.,Telecom Lille 1 | Slama R.,Lille University of Science and Technology
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2013

We propose a novel geometric framework for analyzing 3D faces, with the specific goals of comparing, matching, and averaging their shapes. Here we represent facial surfaces by radial curves emanating from the nose tips and use elastic shape analysis of these curves to develop a Riemannian framework for analyzing shapes of full facial surfaces. This representation, along with the elastic Riemannian metric, seems natural for measuring facial deformations and is robust to challenges such as large facial expressions (especially those with open mouths), large pose variations, missing parts, and partial occlusions due to glasses, hair, and so on. This framework is shown to be promising from both—empirical and theoretical—perspectives. In terms of the empirical evaluation, our results match or improve upon the state-of-the-art methods on three prominent databases: FRGCv2, GavabDB, and Bosphorus, each posing a different type of challenge. From a theoretical perspective, this framework allows for formal statistical inferences, such as the estimation of missing facial parts using PCA on tangent spaces and computing average shapes. © 1979-2012 IEEE.


Berretti S.,University of Florence | Amor B.B.,Telecom Lille 1 | Daoudi M.,Telecom Lille 1 | Del Bimbo A.,University of Florence
Visual Computer | Year: 2011

Methods to recognize humans' facial expressions have been proposed mainly focusing on 2D still images and videos. In this paper, the problem of person-independent facial expression recognition is addressed using the 3D geometry information extracted from the 3D shape of the face. To this end, a completely automatic approach is proposed that relies on identifying a set of facial keypoints, computing SIFT feature descriptors of depth images of the face around sample points defined starting from the facial keypoints, and selecting the subset of features with maximum relevance. Training a Support Vector Machine (SVM) for each facial expression to be recognized, and combining them to form amulti-class classifier, an average recognition rate of 78.43% on the BU-3DFE database has been obtained. Comparison with competitor approaches using a common experimental setting on the BU-3DFE database shows that our solution is capable of obtaining state of the art results. The same 3D face representation framework and testing database have been also used to perform 3D facial expression retrieval (i.e., retrieve 3D scans with the same facial expression as shown © 2011 Springer-Verlag.


Mihaylova L.,University of Sheffield | Carmi A.Y.,Ben - Gurion University of the Negev | Septier F.,Telecom Lille 1 | Gning A.,University College London | And 2 more authors.
Digital Signal Processing: A Review Journal | Year: 2014

This work presents the current state-of-the-art in techniques for tracking a number of objects moving in a coordinated and interacting fashion. Groups are structured objects characterized with particular motion patterns. The group can be comprised of a small number of interacting objects (e.g. pedestrians, sport players, convoy of cars) or of hundreds or thousands of components such as crowds of people. The group object tracking is closely linked with extended object tracking but at the same time has particular features which differentiate it from extended objects. Extended objects, such as in maritime surveillance, are characterized by their kinematic states and their size or volume. Both group and extended objects give rise to a varying number of measurements and require trajectory maintenance. An emphasis is given here to sequential Monte Carlo (SMC) methods and their variants. Methods for small groups and for large groups are presented, including Markov Chain Monte Carlo (MCMC) methods, the random matrices approach and Random Finite Set Statistics methods. Efficient real-time implementations are discussed which are able to deal with the high dimensionality and provide high accuracy. Future trends and avenues are traced. © 2013 Elsevier Inc.


Benhabiles H.,Lille University of Science and Technology | Lavoue G.,University of Lyon | Vandeborre J.-P.,Lille University of Science and Technology | Vandeborre J.-P.,Telecom Lille 1 | And 2 more authors.
Computer Graphics Forum | Year: 2011

This paper presents a 3D-mesh segmentation algorithm based on a learning approach. A large database ofmanually segmented 3D-meshes is used to learn a boundary edge function. The function is learned using a classifier which automatically selects from a pool of geometric features the most relevant ones to detect candidate boundary edges. We propose a processing pipeline that produces smooth closed boundaries using this edge function. This pipeline successively selects a set of candidate boundary contours, closes them and optimizes them using a snake movement. Our algorithm was evaluated quantitatively using two different segmentation benchmarks and was shown to outperform most recent algorithms from the state-of-the-art. © 2011 The Authors.


Zhang Z.,Telecom Lille 1 | Nait-Abdesselam F.,Lille University of Science and Technology
Wireless Networks | Year: 2010

As one of the backup measures of intrusion prevention techniques, intrusion detection plays a paramount role in the second defense line of computer networks. Intrusion detection in wireless mesh networks (WMNs) is especially challenging and requires particular design concerns due to their special infrastructure and communication mode. In this paper, we propose a novel anomaly detection system, termed RADAR, to detect and handle anomalous mesh nodes in wireless mesh networks. Specifically, reputation is introduced to characterize and quantify a node's behavior in terms of fine-grained performance metrics of interest. The dual-core detection engine of RADAR then explores spatio-temporal property of such behavior to manifest the deviation between that of normal and anomalous nodes. Although the current RADAR prototype is only implemented with routing protocols, the design architecture allows it to be easily extended to cross-layer anomaly detection where anomalous events occur at different layers and can be resulted by either intentional intrusion or accidental network failure. The simulation results demonstrate that RADAR can achieve high detection accuracy, low computational complexity, and low false positive rate. © 2010 Springer Science+Business Media, LLC.


Tabia H.,Lille University of Science and Technology | Daoudi M.,Telecom Lille 1 | Vandeborre J.-P.,Telecom Lille 1 | Colot O.,Lille University of Science and Technology
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2011

The 3D-shape matching problem plays a crucial role in many applications, such as indexing or modeling, by example. Here, we present a novel approach to matching 3D objects in the presence of nonrigid transformation and partially similar models. In this paper, we use the representation of surfaces by 3D curves extracted around feature points. Indeed, surfaces are represented with a collection of closed curves, and tools from shape analysis of curves are applied to analyze and to compare curves. The belief functions are used to define a global distance between 3D objects. The experimental results obtained on the TOSCA and the SHREC07 data sets show that the system performs efficiently in retrieving similar 3D models. © 2006 IEEE.


Septier F.,Telecom Lille 1 | Peters G.W.,University College London
IEEE Journal on Selected Topics in Signal Processing | Year: 2016

Nonlinear non-Gaussian state-space models arise in numerous applications in statistics and signal processing. In this context, one of the most successful and popular approximation techniques is the Sequential Monte Carlo (SMC) algorithm, also known as particle filtering. Nevertheless, this method tends to be inefficient when applied to high dimensional problems. In this paper, we focus on another class of sequential inference methods, namely the Sequential Markov Chain Monte Carlo (SMCMC) techniques, which represent a promising alternative to SMC methods. After providing a unifying framework for the class of SMCMC approaches, we propose novel efficient strategies based on the principle of Langevin diffusion and Hamiltonian dynamics in order to cope with the increasing number of high-dimensional applications. Simulation results show that the proposed algorithms achieve significantly better performance compared to existing algorithms. © 2015 IEEE.


Wang S.,Xidian University | Zhang Z.,Telecom Lille 1 | Kadobayashi Y.,NAIST
Computers and Security | Year: 2013

The increasing complexity of today's computer systems, together with the rapid emergence of novel vulnerabilities, make security hardening a formidable challenge for security administrators. Although a large variety of tools and techniques are available for vulnerability analysis, the majority work at system or network level without explicit association with human and organizational factors. This article presents a middleware approach to bridge the gap between system-level vulnerabilities and organization-level security metrics, ultimately contributing to cost-benefit security hardening. In particular, our approach systematically integrates attack graph, a commonly used effective approach to representing and analyzing network vulnerabilities, and Hidden Markov Model (HMM) together, for exploring the probabilistic relation between system observations and states. More specifically, we modify and apply dependency attack graph to represent network assets and vulnerabilities (observations), which are then fed to HMM for estimating attack states, whereas their transitions are driven by a set of predefined cost factors associated with potential attacks and countermeasures. A heuristic searching algorithm is employed to automatically infer the optimal security hardening through cost-benefit analysis. We use a synthetic network scenario to illustrate our approach and evaluate its performance through a set of simulations. © 2012 Elsevier Ltd. All rights reserved.

Loading Telecom Lille 1 collaborators
Loading Telecom Lille 1 collaborators