Mohsen Ardabilian Fard

Ecole Centrale de Lyon – LIRIS UMR 5205 CNRS

Research

Homepege

Teaching

Contact

My Research activity at LIRIS 

3D Textured Sequence Acquisition

Current 3D face imaging solutions are often based on structured light camera/projector systems to overcome the relatively uniform appearance of skin. Our research work on 3D textured sequence acquisition  led in a cost effective 3D video acquisition solution with a 3D space-time super-resolution scheme, using a calibrated multi-camera stereo rig coupled with a non calibrated projector device, which is particularly suited to 3D face scanning, i.e. rapid, easily movable and robust to ambient lighting conditions. The proposed solution is a hybrid stereovision and phase-shifting approach, using two shifted patterns and a texture image, which not only takes advantage of the assets of stereovision and structured light but also overcomes their weaknesses. The super-resolution scheme corrects the 3D information and completes the 3D scanned view despite the presence of small non-rigid deformations as facial expressions. The experimental results further validated the effectiveness of the proposed approach.

Keyword: 3D acquisition, Super-Resolution, Space-Time

3D Face Processing and Analysis

Facial surface processing and analysis is one of the most important steps for 3D face recognition algorithms. Automatic anthropometric facial features localization also plays an important role for face localization, face expression recognition, face registration etc., thus its automatic localization is a crucial step for 3D face processing algorithms. In this work we focused on precise and rotation invariant landmarks localization, which are later used directly for face recognition. The landmarks are localized combining local surface properties expressed in terms of differential geometry tools and global facial generic model, used for face validation. Since curvatures, which are differential geometry properties, are sensitive to surface noise, one of our main contributions is a modification of curvatures calculation method. The modification incorporates the surface noise into the calculation method and helps to control smoothness of the curvatures. Therefore the main facial points can be reliably and precisely localized (100% nose tip localization using 8 mm precision) under the influence of rotations and surface noise. The modification of the curvatures calculation method was also tested under different face model resolutions, resulting in stable curvature values. Finally, since curvatures analysis leads to many facial landmark candidates, the validation of which is time consuming, facial landmarks localization based on learning technique was proposed. The learning technique helps to reject incorrect landmark candidates with a high probability, thus accelerating landmarks localization.

Face recognition using 3D models is a relatively new subject, which has been proposed to overcome shortcomings of 2D face recognition modality. However, 3D face recognition algorithms are likely more complicated. Additionally, since 3D face models describe facial surface geometry, they are more sensitive to facial expression changes. Our contribution is reducing dimensionality of the input data by mapping 3D facial models on to 2D domain using non-rigid, conformal mapping techniques. Having 2D images which represent facial models, all previously developed 2D face recognition algorithms can be used. In our work, conformal shape images of 3D facial surfaces were fed in to 2D2 PCA, achieving more than 86% recognition rate rank-one using the FRGC data set. The effectiveness of all the methods has been evaluated using the FRGC and Bosphorus datasets.

Keywords: 3D face landmarking, 3D face recognition, curvatures classification, conformal mapping.

3D Face Recognition based on Sparse Representation

The face is one of the best biometrics for person identification and verification related applications, because it is natural, non-intrusive, and socially well accepted. Unfortunately, all human faces are similar to each other and hence over low distinctiveness as compared with other biometrics, e.g., fingerprints and irises. Furthermore, when employing facial texture images, intra-class variations due to factors as diverse as illumination and pose changes are usually greater than inter-class ones, making 2D face recognition far from reliable in the real condition. Recently, 3D face data have been extensively investigated by the research community to deal with the unsolved issues in 2D face recognition, i.e., illumination and pose changes data, including only 3D shape based face recognition, textured 3D face recognition as well as asymmetric 3D-2D face recognition. In only 3D shape-based face recognition, since 3D face data, such as facial point clouds and facial scans, are theoretically insensitive to lighting variations and generally allow easy pose correction using an ICP-based registration step, the key problem mainly lies in how to represent 3D facial surfaces accurately and achieve matching that is robust to facial expression changes. We design an effective and efficient approach in only 3D shape based face recognition. For facial description, we propose a novel geometric representation based on extended Local Binary Pattern (eLBP) depth maps, and it can comprehensively describe local geometry changes of 3D facial surfaces; while a SIFT-based local matching process further improved by facial component and configuration constraints is proposed to associate keypoints between corresponding facial representations of different facial scans belonging to the same subject. Evaluated on the FRGC v2.0 and Gavab databases, the proposed approach proves its effectiveness. Furthermore, due to the use of local matching, it does not require registration for nearly frontal facial scans and only needs a coarse alignment for the ones with severe pose variations, in contrast to most of the related tasks that are based on a time-consuming _ne registration step.

Considering that most of the current 3D imaging systems deliver 3D face models along with their aligned texture counterpart, a major trend in the literature is to adopt both the 3D shape and 2D texture based modalities, arguing that the joint use of both clues can generally provides more accurate and robust performance than utilizing only either of the single modality. Two important factors in this issue are facial representation on both types of data as well as result fusion. We propose a biological vision-based facial representation, named Oriented Gradient Maps (OGMs), which can be applied to both facial range and texture images. The OGMs simulate the response of complex neurons to gradient information within a given neighborhood and have properties of being highly distinctive and robust to affine illumination and geometric transformations. The previously proposed matching process is then adopted to calculate similarity measurements between probe and gallery faces. Because the biological vision-based facial representation produces an OGM for each quantized orientation of facial range and texture images, we finally use a score level fusion strategy that optimizes weights by a genetic algorithm in a learning process. The experimental results achieved on the FRGC v2.0 and 3DTEC datasets display the effectiveness of the proposed biological vision-based facial description and the optimized weighted sum fusion.

Indeed, (textured) 3D face recognition techniques also have their own downsides, and are currently limited by their high expense in data acquisition and computation. Here, we present a novel framework, asymmetric 3D-2D face recognition, enrolling in textured 3D face models while performing identification only using 2D facial texture images. The motivation is to limit the use of 3D data where they really help to improve face recognition accuracy. The proposed method consists of a new preprocessing pipeline to enhance robustness to illumination and pose changes, an OGM-based facial representation to describe both local shape and texton variations of range and texture faces, as well as a twofold classification step which combines the matching between two facial texture images and the one between a facial range and texture image. The experiments carried out on the FRGC v2.0 database illustrate that the proposed method outperforms 2D intensity image based ones, and achieves comparable results as 3D data based ones do. Furthermore, it avoids the cost and inconvenience of facial data acquisition and computation in 3D based approaches.

Keywords: 2D, 3D and multi-modal face recognition, asymmetric face recognition, and facial representation.

Localization and quality enhancement for automatic vehicle license plates recognition of in video sequences

La lecture automatique de plaques d’immatriculation de véhicule est considérée comme une approche de surveillance de masse. Elle permet, grâce à la détection/localisation ainsi que la reconnaissance optique, d’identifier un véhicule dans les images ou les séquences d’images. De nombreuses applications comme le suivi du trafic, la détection de véhicules volés, le télépéage ou la gestion d’entrée/sorite des parkings utilise ce procédé. Or malgré d’important progrès enregistré depuis l’apparition des premiers prototypes en 1979 accompagné d’un taux de reconnaissance parfois impressionnant, notamment grâce aux avancés en recherche scientifique et en technologie des capteurs, les contraintes imposés pour le bon fonctionnement de tels systèmes en limitent les portées. En effet, l’utilisation optimale des techniques de localisation et de reconnaissance de plaque d’immatriculation dans les scénarii opérationnels nécessite des conditions d’éclairage contrôlées ainsi qu’une limitation de la pose, de vitesse ou tout simplement de type de plaque. La lecture automatique de plaques d’immatriculation reste alors un problème de recherche ouvert. Notre objectif est de proposer une approche robuste et non-contraignante de détection/localisation de plaques d’immatriculation, ainsi qu’une méthode d’amélioration de qualité d’image renforçant le taux de localisation.  Notre contribution est triple. D’abord une nouvelle approche robuste de localisation de plaque d’immatriculation dans des images ou des séquences d’images est proposée. Puis, l’amélioration de la qualité des plaques localisées est abordée par une adaptation de technique de super-résolution. Finalement, un modèle unifié de localisation et de super-résolution est présenté permettant d’augmenter le taux de localisation tout en diminuant la complexité temporelle des deux approches combinées.

Keywords: Realtime License Plate Localization, Fast Connective Hough Transform, Bayesien Super-Resolution, Joint Localization/Super-Resolution.