Search For:

Displaying 1-31 out of 31 total
Non-rigid 3D shape classification using bag-of-feature techniques
Found in: Multimedia and Expo, IEEE International Conference on
By Hedi Tabia,Olivier Colot,Mohamed Daoudi,Jean-Philippe Vandeborre
Issue Date:July 2011
pp. 1-6
In this paper, we present a new method for 3D-shape categorization using Bag-of-Feature techniques (BoF). This method is based on vector quantization of invariant descriptors of 3D-object patches. We analyze the performance of two wellknown classifiers: th...
 
A New 3D-Matching Method of Nonrigid and Partially Similar Models Using Curve Analysis
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hedi Tabia, Mohamed Daoudi, Jean-Philippe Vandeborre, Olivier Colot
Issue Date:April 2011
pp. 852-858
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 pap...
 
3D-Shape Retrieval Using Curves and HMM
Found in: Pattern Recognition, International Conference on
By Hedi Tabia, Olivier Colot, Mohamed Daoudi, Jean-Philippe Vandeborre
Issue Date:August 2010
pp. 3147-3150
In this paper, we propose a new approach for 3D-shape matching. This approach encloses an off-line step and an on-line step. In the off-line one, an alphabet, of which any shape can be composed, is constructed. First, 3D-objects are subdivided into a set o...
 
Local 3D Shape Analysis for Facial Expression Recognition
Found in: Pattern Recognition, International Conference on
By Ahmed Maalej, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Stefano Berretti
Issue Date:August 2010
pp. 4129-4132
We investigate the problem of facial expression recognition using 3D face data. Our approach is based on local shape analysis of several relevant regions of a given face scan. These regions or patches from facial surfaces are extracted and represented by s...
 
A Set of Selected SIFT Features for 3D Facial Expression Recognition
Found in: Pattern Recognition, International Conference on
By Stefano Berretti, Alberto Del Bimbo, Pietro Pala, Boulbaba Ben Amor, Mohamed Daoudi
Issue Date:August 2010
pp. 4125-4128
In this paper, the problem of person-independent facial expression recognition is addressed on 3D shapes. To this end, an original approach is proposed that computes SIFT descriptors on a set of facial landmarks of depth images, and then selects the subset...
 
SHape REtrieval contest 2008: 3D face scans
Found in: Shape Modeling and Applications, International Conference on
By Frank B. ter Haar, Mohamed Daoudi, Remco C. Veltkamp
Issue Date:June 2008
pp. 225-226
No summary available.
   
A Framework of Calculus on Facial Surfaces
Found in: Image Analysis and Processing Workshops, International Conference of
By Chafik Samir, Mohamed Daoudi, Anuj Srivastava
Issue Date:September 2007
pp. 27-32
Facial surfaces play an important role in different ap- plications such as computer graphics and biometric. A few works have been proposed to study the space of facial surfaces. In this paper, we represent a facial surface as a path on the space of closed ...
 
Topology driven 3D mesh hierarchical segmentation
Found in: Shape Modeling and Applications, International Conference on
By Julien Tierny, Jean-Philippe Vandeborre, Mohamed Daoudi
Issue Date:June 2007
pp. 215-220
<p>In this paper, we propose to address the semanticoriented 3D mesh hierarchical segmentation problem, using enhanced topological skeletons [18]. This high level information drives both the feature boundary computation as well as the feature hierarc...
 
Dynamic Reconstruction from Noise Contaminated Data with Sparse Bayesian Recurrent Neural Networks
Found in: Asia International Conference on Modelling & Simulation
By Derrick T. Mirikitani, Incheon Park, Mohammed Daoudi
Issue Date:March 2007
pp. 409-414
Dynamic reconstruction is fundamental to building models of nonlinear processes with unknown governing equations. Dynamic reconstruction attempts to reconstruct the underlying dynamics of the system under consideration from a series of scalar measurements ...
 
On 3D Retrieval from Photos
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Tarik Filali Ansary, Jean-Phillipe Vandeborre, Mohamed Daoudi
Issue Date:June 2006
pp. 687-694
In this paper, we propose a method for 3D-model retrieval from one or more photos. This method provides an
 
Invariant High Level Reeb Graphs of 3D Polygonal Meshes
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Julien Tierny, Jean-Philippe Vandeborre, Mohamed Daoudi
Issue Date:June 2006
pp. 105-112
Many applications in computer graphics need high level shape descriptions, in order to benefit from a global understanding of shapes. <p>Topological approaches enable pertinent surface decompositions, providing structural descriptions of 3D polygonal...
 
Determining Characteristic Views of a 3D Object by Visual Hulls and Hausdorff Distance
Found in: 3D Digital Imaging and Modeling, International Conference on
By Adrien Theetten, Jean-Philippe Vandeborre, Mohamed Daoudi
Issue Date:June 2005
pp. 439-446
<p>Nowadays, with the exponential growing of 3D object representations in private databases or on the web, it is all the more required to match these objects from some views. To improve the results of their matching, we work on the characteristic vie...
 
A Bayesian Framework for 3D Models Retrieval Based on Characteristic Views
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Tarik Filali Ansary, Jean-Philippe Vandeborre, Said Mahmoudi, Mohamed Daoudi
Issue Date:September 2004
pp. 139-146
The management of big databases of three-dimensional models (used in CAD applications, visualization, games, etc.) is a very important domain. The ability to characterize and easily retrieve models is a key issue for the designers and the final users. In t...
 
A Bayesian Approach for 3D Models Retrieval Based on Characteristic Views
Found in: Pattern Recognition, International Conference on
By Tarik Filali Ansary, Jean-Philippe Vandeborre, Mohamed Daoudi
Issue Date:August 2004
pp. 898-901
The management of big databases of three-dimensional models (used in CAD applications, visualization, games, etc.) is a very important domain. The ability to characterize and easily retrieve models are a key issues for the designers and the final users. In...
 
Statistical Models for Skin Detection
Found in: Computer Vision and Pattern Recognition Workshop
By Bruno Jedynak, Huicheng Zheng, Mohamed Daoudi
Issue Date:June 2003
pp. 92
We consider a sequence of three models for skin detection built from a large collection of labelled images. Each model is a maximum entropy model with respect to constraints concerning marginal distributions. Our models are nested. The first model is well ...
 
An Interprocedural Amorphous Slicer for WSL
Found in: Source Code Analysis and Manipulation, IEEE International Workshop on
By Mark Harman, Lin Hu, Malcolm Munro, Xingyuan Zhang, Sebastian Danicic, Mohammed Daoudi, Lahcen Ouarbya
Issue Date:October 2002
pp. 105
This paper presents a simple interprocedural algorithm for amorphous slicing and illustrates the way in which interprocedural amorplhous slicing improves upon interprocedural syntax-preserving slicing. The paper also presents results from an empirical stud...
 
3D Models Retrieval by Using Characteristic Views
Found in: Pattern Recognition, International Conference on
By Saïd Mahmoudi, Mohamed Daoudi
Issue Date:August 2002
pp. 20457
In this work we introduce a new method for indexing 3D models. This method is based on the characterization of 3D objects by a set of 7 characteristic views, including three principals, and four secondaries. The primary, secondary, and tertiary viewing dir...
 
A Practical Approach for 3D Model Indexing by combining Local and Global Invariants
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Jean-Philippe Vandeborre, Vincent Couillet, Mohamed Daoudi
Issue Date:June 2002
pp. 644
In this paper we present a three-dimensional model retrieval system. In our approach, a three-dimensional model is described by three invariant descriptors: a curvature index which consists ofa histogram of the principal curvatures of each face of the mesh...
 
New Multiscale Planar Shape Invariant Representation under a General Affine Transformations
Found in: Pattern Recognition, International Conference on
By Mohamed Daoudi, Stanislaw Matusiak
Issue Date:September 2000
pp. 3794
In this paper, we introduce a new set of invariant and local descriptors, which are independent under a General Affine group transformation's (GA (20): rotation, uniform scaling, translation, and stretching) of planar curves: a new Invariant in Affine Scal...
 
Extremal human curves: A new human body shape and pose descriptor
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Rim Slama,Hazem Wannous,Mohamed Daoudi
Issue Date:April 2013
pp. 1-6
Automatic estimation of 3D shape similarity from video is a very important factor for human action analysis, but also a challenging task due to variations in body topology and the high dimensionality of the pose configuration space. We consider the problem...
   
Fully automatic 3D facial expression recognition using differential mean curvature maps and histograms of oriented gradients
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Pierre Lemaire,Mohsen Ardabilian,Liming Chen,Mohamed Daoudi
Issue Date:April 2013
pp. 1-7
In this paper, we propose an holistic, fully automatic approach to 3D Facial Expression Recognition (FER). A novel facial representation, namely Differential Mean Curvature Maps (DMCMs), is proposed to capture both global and local facial surface deformati...
   
Gender and 3D facial symmetry: What's the relationship?
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Baiqiang Xia,Boulbaba Ben Amor,Hassen Drira,Mohamed Daoudi,Lahoucine Ballihi
Issue Date:April 2013
pp. 1-6
Although it is valuable information that human faces are approximately symmetric, in the literature of facial attributes recognition, little consideration has been given to the relationship between gender, age, ethnicity, etc. and facial asymmetry. In this...
   
Invariant Content-Based Image Retrieval Using a Complete Set of Fourier-Mellin Descriptors
Found in: Multimedia Computing and Systems, International Conference on
By Stephane Derrode, Mohamed Daoudi, Faouzi Ghorbel
Issue Date:June 1999
pp. 877
Image retrieval from a large database is an important and emerging search area. This retrieval requires the choice of a suitable set of image features, a method to extract them correctly, and a measure of the similarity between features that can be compare...
 
A parts-based approach for automatic 3D shape categorization using belief functions
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Hedi Tabia, Jean-Philippe Vandeborre, Mohamed Daoudi, Olivier Colot
Issue Date:March 2013
pp. 1-16
Grouping 3D objects into (semantically) meaningful categories is a challenging and important problem in 3D mining and shape processing. Here, we present a novel approach to categorize 3D objects. The method described in this article, is a belief-function-b...
     
Fully automatic 3D facial expression recognition using a region-based approach
Found in: Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding (J-HGBU '11)
By Boulbaba Ben Amor, Liming Chen, Mohamed Daoudi, Mohsen Ardabilian, Pierre Lemaire
Issue Date:December 2011
pp. 53-58
In this paper, we address the problem of automatic 3D facial expression recognition. Automatic 3D Facial Expression Recognition techniques are generally limited in that they require manual, precise landmark points. Here, we propose a framework capable of h...
     
Joint ACM workshop on human gesture and behavior understanding: (J-HGBU'11)
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Alberto Del Bimbo, Alessandro Vinciarelli, Alex Pentland, Maja Pantic, Mohamed Daoudi, Rita Cucchiara
Issue Date:November 2011
pp. 615-616
The ability to understand social signals of a person we are communicating with is the core of social intelligence. Social Intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in l...
     
Elastic radial curves to model 3D facial deformations
Found in: Proceedings of the ACM workshop on 3D object retrieval (3DOR '10)
By Anuj Srivastava, Boulbaba Ben Amor, Hassen Drira, Mohamed Daoudi
Issue Date:October 2010
pp. 75-80
In this paper we study the challenging problem of 3D face recognition in presence of facial expressions. Therefore, the facial surfaces are represented by an indexed collections of radial curves on them, emanating from the nose tips. Facial shapes comparis...
     
Local visual patch for 3d shape retrieval
Found in: Proceedings of the ACM workshop on 3D object retrieval (3DOR '10)
By Hedi Tabia, Jean Philippe Vandeborre, Mohamed Daoudi, Olivier Colot
Issue Date:October 2010
pp. 3-8
We present a novel method for 3D-object retrieval using Bag of Feature (BoF) approaches [8]. The method starts by selecting and then describing a set of points from the 3D-object. The proposed descriptor is an indexed collection of closed curves in R3 on t...
     
ACM workshop on 3d object retrieval: 3DOR'10 chair's welcome
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Michela Spagnuolo, Mohamed Daoudi, Remco Veltkamp
Issue Date:October 2010
pp. 1731-1732
3D media has emerged rapidly as a new type of content within the multimedia domain. The recent acceleration of 3D content production, witnessed across all fields up to user-generated content, is causing a huge amount of traffic and data stored and transmit...
     
3D-Model search engine from photos
Found in: Proceedings of the 6th ACM international conference on Image and video retrieval (CIVR '07)
By Jean-Phillipe Vandeborre, Mohamed Daoudi, Tarik Filali Ansary
Issue Date:July 2007
pp. 89-92
In this paper, we present the FOX-MIIRE 3D-Model Search Engine. Our search engine is based on Adaptive Views Vlustering (AVC) algorithm [4]. The AVC method uses statistical model distribution scores to select the optimal number of views to characterise a 3...
     
Image indexing & retrieval using intermediate features
Found in: Proceedings of the ninth ACM international conference on Multimedia (MULTIMEDIA '01)
By Bruno Jedynak, Mohamad Obeid, Mohamed Daoudi
Issue Date:September 2001
pp. 531-533
Visual information retrieval systems use low-level features such as color, texture and shape for image queries. Users usually have a more abstract notion of what will satisfy them. Using low-level features to correspond to high-level abstractions is one as...
     
 1