Sami Romdhani


Address: University of Basel
Computer Science Department
Bernoullistrasse 16
CH - 4056 Basel, Switzerland
Phone:+41-61-267.0549
Fax:+41-61-267.0559
Email: sami.romdhani at unibas.ch

Publications
CV
Research Interests

Look at this video that shows an example of my research that was broadcasted by the french channel, LCI, on November 2006, as part of their report on the Microsoft Innovation Day.

3D Face Image Analysis Demo
Click to see examples of applications (3D rotations, image transfer, caricatures, gender transformations, expression transfer from another face picture) that our system can perform automatically from one face image.

If you are interested, I can run my system and produce a similar document with your own photo. Just send it by email.


Face Image Analysis using a Multiple Feature Fitting Strategy
Sami Romdhani, PhD Thesis, January 2005.

The main contribution of this thesis is a novel algorithm for fitting a Three-Dimensional Morphable Model of faces to a 2D input image. This fitting algorithm enables the estimation of the 3D shape, the texture, the 3D pose and the light direction from a single input image.

Generally, the algorithms tackling the problem of 3D shape estimation from image data use only the pixels intensity as input to drive the estimation process. This was previously achieved using either a simple model, such as the Lambertian reflectance model, leading to a linear fitting algorithm. Alternatively, this problem was addressed using a more precise model and minimizing a non-convex cost function with many local minima. One way to reduce the local minima problem is to use a stochastic optimization algorithm. However, the convergence properties (such as the radius of convergence) of such algorithms, are limited. Here, as well as the pixel intensity, we use various image features such as the edges or the location of the specular highlights. The 3D shape, texture and imaging parameters are then estimated by maximizing the posterior of the parameters given these image features. The overall cost function obtained is smoother and, hence, a stochastic optimization algorithm is not needed to avoid the local minima problem. This leads to the Multi-Features Fitting algorithm that has a wider radius of convergence and a higher level of precision.

The new Multi-Feature Fitting algorithm is applied for such tasks as face identification, facial expression transfer from one image to another image (of different individuals) and face tracking across 3D pose and expression variations.

The second contribution of this thesis is a careful comparison of well known fitting algorithms used in the context of face modelling and recognition. It is shown that these algorithms achieve high run time efficiency at the cost of accuracy and generality (few face images may be analysed).

The third and last contribution is the Matlab Morphable Model toolbox, a set of software tools developed in the Matlab programing environment. It allows (i) the generation of 3D faces from model parameters, (ii) the rendering of 3D faces, (iii) the fitting of an input image using the Multi-Features Fitting algorithm and (iv) identification from model parameters. The toolbox has a modular design that allows anyone to builds on it and, for instance, to improve the fitting algorithm by incorporating new features in the cost function.




Journal Paper

  Face Recognition Using 3-D Models: Pose and Illumination
Sami Romdhani, Jeff Ho, Thomas Vetter, David J. Kriegman
In Proceedings of the IEEE, 94(11):1977-1999, November 2006.

  Efficient face detection by a cascaded support-vector machine expansion
Sami Romdhani, Philip Torr, Bernhard Schölkopf, Andrew Blake
In Proceedings of The Royal Society A, 460(2501):3283-3297, November 2004.


Tutorial

  Face Modelling and Recognition Tutorial
Thomas Vetter, and Sami Romdhani
Held at the European Conference on Computer Vision, 2004.


Book Chapter

  3D Morphable Face Model, a Unified Approach for Analysis and Synthesis of Images
Sami Romdhani, Jean-Sebastien Pierrard and Thomas Vetter
In Face Processing: Advanced Modeling and Methods, Edited by Wenyi Zhao and Rama Chellappa, Elsevier, 2005
pdf [523k].

  Morphable Models of Faces
Sami Romdhani, Volker Blanz, Curzio Basso and Thomas Vetter
In the Handbook of Face Recognition, Edited by Stan Li and Anil Jain, Springer-Verlag, January 2004
pdf [1.8M], ps [2.4M].


Conference Papers

  3D Probabilistic Feature Point Model for Object Detection and Recognition
S. Romdhani and T. Vetter
IEEE Conference on Computer Vision and Pattern Recognition, 2007
pdf [1.7M]

  Optimal Step Nonrigid ICP Algorithms for Surface Registration
B. Amberg, S. Romdhani and T. Vetter
IEEE Conference on Computer Vision and Pattern Recognition, 2007
pdf [3.2M]

  Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points
Reinhard Knothe, Sami Romdhani and Thomas Vetter
IEEE International Conference on Automatic Face and Gesture Recognition, 2006
pdf [2.2M]

  Color Active Appearance Model Analysis using a 3D Morphable Model
N. Faggian, S. Romdhani, J. Sherrah and A. Paplinski
Digital Image Computing: Techniques and Applications, 2005
pdf [4.8M]

  Over-Complete Wavelet Approximation of a Support Vector Machine for Efficient Classification
Matthias Raetsch, Sami Romdhani, Gerd Teschke, and Thomas Vetter
DAGM, 2005
pdf [512k]

  Estimating 3D Shape and Texture Using Pixel Intensity, Edges, Specular Highlights, Texture Constraints and a Prior
Sami Romdhani, and Thomas Vetter
IEEE Conference on Computer Vision and Pattern Recognition, 2005
pdf [434k]

  Efficient Face Detection by a Cascaded Support Vector Machine using Haar-like Features
Matthias Raetsch, Sami Romdhani, and Thomas Vetter
DAGM, 2004
pdf [400k]

  Efficient, Robust and Accurate Fitting of a 3D Morphable Model
Sami Romdhani and Thomas Vetter
Proceedings of the IEEE International Conference on Computer Vision 2003.

  Face Identification by Fitting a 3D Morphable Model using Linear Shape and Texture Error Functions
Sami Romdhani, Volker Blanz, and Thomas Vetter
Computer Vision - ECCV 2002, May 2002, LNCS 2353, pp. 3-19.

  Face Identification across different Poses and Illuminations with a 3D Morphable Model
Volker Blanz, Sami Romdhani, and Thomas Vetter
Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2002, pp. 202 - 207.
pdf [585k], ps.gz [1.1M],

  Computationally Efficient Face Detection
Sami Romdhani, Philip Torr, Bernhard Schölkopf, and Andrew Blake
Proceedings of the 8th International Conference on Computer Vision, July 2001, Vol II: 695-700
Download: pdf [1.6M], ps.gz [2.6M],

  On utilising Template and Feature-based Correspondence in Multi-View Appearance Models
Sami Romdhani, Alexandra Psarrou, and Shaogang Gong
Computer Vision - ECCV 2000, Vol I: 799-813
Download: ps.gz [1.4M]

  A Generic Face Appearance Model of Shape and Texture under very large Pose Variations from Profile to Profile Views
Sami Romdhani, Alexandra Psarrou, and Shaogang Gong
Proceedings of the 15th International Conference on Pattern Recognition, 2000, Vol I: 1060-1063

  Tracking Deformable Face Models across Multiple Views
Sami Romdhani, Alexandra Psarrou, and Shaogang Gong
Proceeding of the fourth asian conference on computer vision, Vol II: 1022-1027

  Learning a single active shape model for faces across views
Sami Romdhani, Alexandra Psarrou, and Shaogang Gong
First International Workshop on Recognition, Analysis and Tracking of Faces and Gestures in Real-time Systems, 1999

  Multi-View Nonlinear Active Shape Model using Kernel PCA
Sami Romdhani, Alexandra Psarrou, and Shaogang Gong
Proceedings of the tenth British Machine Vision Conference, September 1999
Best Scientific Paper Award
Download: ps.gz [1.4M]

Technical Report

  Selective vs. Global Recovery of Rigid and Non-Rigid Motion
Sami Romdhani, Nikolaos Canterakis, and Thomas Vetter
Technical Report Nr 3 - July 2003 - University of Basel, Computer Science Dept
pdf [261k], ps.gz [195k].


COPYRIGHT NOTICE: All the documents on this server have been submitted by their authors to scholarly journals or conferences as indicated, for the purpose of non-commercial dissemination of scientific work. The manuscripts are put on-line to facilitate this purpose. These manuscripts are copyrighted by the authors or the journals in which they were published. You may copy a manuscript for scholarly, non-commercial purposes, such as research or instruction, provided that you agree to respect these copyrights.

COPYRIGHT NOTICE FOR IEEE PUBLICATIONS: Copyright 1999 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: + Intl. 908-562-3966.