Franck Davoine
University of Technology of Compiègne
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Franck Davoine.
Signal Processing-image Communication | 2004
Bouchra Abboud; Franck Davoine; Mô Dang
This article addresses the issue of expressive face modelling using an active appearance model for facial expression recognition and synthesis. We consider the six universal emotional categories namely joy, anger, fear, disgust, sadness and surprise. After a description of the active appearance model (computed with 3 or only one PCA), we address the active appearance model contribution to automatic facial expression recognition. Then we propose a new method for analysis and synthesis allowing, from a single photo, to cancel the facial expression on a given face and to artificially synthesize novel expressions on this same face. In this last framework, we propose two facial expression modelling approaches.
Signal Processing-image Communication | 2002
Séverine Dubuisson; Franck Davoine; Mylène Masson
The design of a recognition system requires careful attention to pattern representation and classifier design. Some statistical approaches choose those features, in a d-dimensional initial space, which allow sample vectors belonging to different categories to occupy compact and disjoint regions in a low-dimensional subspace. The effectiveness of the representation subspace is then determined by how well samples from different classes can be separated. In this paper, we propose a feature selection process that sorts the principal components, generated by principal component analysis, in the order of their importance to solve a specific recognition task. This method provides a low-dimensional representation subspace which has been optimized to improve the classification accuracy. We focus on the problem of facial expression recognition to demonstrate this technique. We also propose a decision tree-based classifier that provides a ‘‘coarse-to-fine’’ classification of new samples by successive projections onto more and more precise representation subspaces. Results confirm, first, that the choice of the representation strongly influences the classification results, second that a classifier has to be designed for a specific representation. r 2002 Elsevier Science B.V. All rights reserved.
international conference on pattern recognition | 2004
Bouchra Abboud; Franck Davoine
Facial expression interpretation, recognition and analysis is a key issue in visual communication and man to machine interaction. We address the issues of facial expression recognition and synthesis and compare the proposed bilinear factorization based representations with previously investigated methods such as linear discriminant analysis and linear regression. We conclude that bilinear factorization outperforms these techniques in terms of correct recognition rates and synthesis photorealism especially when the number of training samples is restrained.
Lecture Notes in Computer Science | 2001
Séverine Dubuisson; Franck Davoine; Jean Pierre Cocquerez
In this paper, we present an automatic algorithm for facial expression recognition. We first propose a method for automatic facial feature extraction, based on the analysis of outputs of local Gabor filters. Such analysis is done using a spatial adaptive triangulation of the magnitude of the filtered images. Then, we propose a classification procedure for facial expression recognition, considering the internal part of registered still faces. Principal Component Analysis allows to represent faces in a low-dimensional space, defined by basis functions that are adapted to training sets of facial expressions. We show how to select the best basis functions for facial expression recognition, providing a good linear discrimination: results prove the robustness of the recognition method.
international conference on image processing | 2005
Hussein Joumaa; Franck Davoine
Independent component analysis (ICA) techniques have been recently used in different watermarking schemes. However, performance of an ICA video watermarking scheme in comparison with those using classical domains, such as the discrete Fourier transform (DCT) domain, is still not clear. In this paper, we attempt to fill this gap. Therefore, we propose a video watermarking scheme, using an informed trellis, applied in two transformed domains obtained by using respectively the DCT transform and an ICA coding technique. We show that, for both domains, the scheme offers a good robustness against MPEG-2 compression, as well as an important capacity level. We consider in this paper data hiding in digital TV channels where data are compressed using MPEG-2.
Lecture Notes in Computer Science | 2004
Zhong Jin; Franck Davoine; Zhen Lou
This paper studied PCA mixture model in high dimensional space. A novel EM learning approach by using perturbation was proposed for the PCA mixture model. Experiments showed the novel perturbation EM algorithm is more effective in learning PCA mixture model than an existing constrained EM algorithm.
International Journal of Computer Vision | 2008
Fadi Dornaika; Franck Davoine
IEE Proceedings - Vision, Image, and Signal Processing | 2005
Bouchra Abboud; Franck Davoine
european signal processing conference | 2000
Franck Davoine
Lecture Notes in Computer Science | 2006
Zhong Jin; Franck Davoine; Zhen Lou; Jingyu Yang