Christophe Ducottet

University of Lyon, Lyons, Rhône-Alpes, France

Are you Christophe Ducottet?

Claim your profile

Publications (47)25.45 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: With multimedia information retrieval, combining different modalities - text, image, audio or video provides additional information and generally improves the overall system performance. For this purpose, the linear combination method is presented as simple, flexible and effective. However, it requires to choose the weight assigned to each modality. This issue is still an open problem and is addressed in this paper. Our approach, based on Fisher Linear Discriminant Analysis, aims to learn these weights for multimedia documents composed of text and images. Text and images are both represented with the classical bag-of-words model. Our method was tested over the ImageCLEF datasets 2008 and 2009. Results demonstrate that our combination approach not only outperforms the use of the single textual modality but provides a nearly optimal learning of the weights with an efficient computation. Moreover, it is pointed out that the method allows to combine more than two modalities without increasing the complexity and thus the computing time.
    Pattern Recognition. 01/2014; 47(1):260-269.
  • Rahat Khan, Cecile Barat, Damien Muselet, Christophe Ducottet
    [Show abstract] [Hide abstract]
    ABSTRACT: In the context of category level scene classification, the bag-of-visual-words model (BoVW) is widely used for image representation. This model is appearance based and does not contain any information regarding the arrangement of the visual words in the 2D image space. To overcome this problem, recent approaches try to capture information about either the absolute or the relative spatial location of visual words. In the first category, the so-called Spatial Pyramid Representation (SPR) is very popular thanks to its simplicity and good results. Alternatively, adding information about occurrences of relative spatial configurations of visual words was proven to be effective but at the cost of higher computational complexity, specifically when relative distance and angles are taken into account. In this paper, we introduce a novel way to incorporate both distance and angle information in the BoVW representation. The novelty is first to provide a computationally efficient representation adding relative spatial information between visual words and second to use a soft pairwise voting scheme based on the distance in the descriptor space. Experiments on challenging data sets MSRC-2, 15Scene, Caltech101, Caltech256 and Pascal VOC 2007 demonstrate that our method outperforms or is competitive with concurrent ones. We also show that it provides important complementary information to the spatial pyramid matching and can improve the overall performance.
    Computer Vision and Image Understanding 01/2014; · 1.23 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Color description is a challenging task because of large variations in RGB values which occur due to scene accidental events, such as shadows, shading, specularities, illuminant color changes, and changes in viewing geometry. Traditionally, this challenge has been addressed by capturing the variations in physics-based models, and deriving invariants for the undesired variations. The drawback of this approach is that sets of distinguishable colors in the original color space are mapped to the same value in the photometric invariant space. This results in a drop of discriminative power of the color description. In this paper we take an information theoretic approach to color description. We cluster color values together based on their discriminative power in a classification problem. The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data sets than the one at hand, can obtain competing performance. Experiments show that the proposed descriptor outperforms existing photometric invariants. Furthermore, we show that combined with shape description these color descriptors obtain excellent results on four challenging datasets, namely, PASCAL VOC 2007, Flowers-102, Stanford dogs-120 and Birds-200.
    Computer Vision and Pattern Recognition (CVPR); 01/2013
  • Source
    Rahat Khan, Cecile Barat, Damien Muselet, Christophe Ducottet
    British Machine Vision Conference; 01/2012
  • Source
    Cécile Barat, Christophe Ducottet, Michel Jourlin
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper focuses on non-linear pattern matching transforms based on mathematical morphology for gray level image processing. Our contribution is on two fronts. First, we unify the existing and a priori unconnected approaches to this problem by establishing their theoretical links with topology. Setting them within the same context allows to highlight their differences and similarities, and to derive new variants. Second, we develop the concept of virtual double-sided image probing (VDIP), a broad framework for non-linear pattern matching in grayscale images. VDIP extends our work on the multiple object matching using probing (MOMP) transform we previously defined to locate multiple grayscale patterns simultaneously. We show that available methods as well as the topological approach can be generalized within the VDIP framework. They can be formulated as particular variants of a general transform designed for virtual probing. Furthermore, a morphological metric, called SVDIP (single VDIP), is deduced from the VDIP concept. Some results are presented and compared with those obtained with classical methods.
    Pattern Recognition 10/2010; · 2.58 Impact Factor
  • Source
    C. Moulin, C. Barat, C. Ducottet
    [Show abstract] [Hide abstract]
    ABSTRACT: Image representation using bag of visual words approach is commonly used in image classification. Features are extracted from images and clustered into a visual vocabulary. Images can then be represented as a normalized histogram of visual words similarly to textual documents represented as a weighted vector of terms. As a result, text categorization techniques are applicable to image classification. In this paper, our contribution is twofold. First, we propose a suitable Term-Frequency and Inverse Document Frequency weighting scheme to characterize the importance of visual words. Second, we present a method to fuse different bag-of-words obtained with different vocabularies. We show that using our tf.idf normalization and the fusion leads to better classification rates than other normalization methods, other fusion schemes or other approaches evaluated on the SIMPLIcity collection.
    Content-Based Multimedia Indexing (CBMI), 2010 International Workshop on; 07/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: As an alternative to vector representations, a recent trend in image classification suggests to integrate additional structural information in the description of images in order to enhance classification accuracy. Rather than being represented in a p-dimensional space, images can typically be encoded in the form of strings, trees or graphs and are usually compared either by computing suited metrics such as the (string or tree)-edit distance, or by testing subgraph isomorphism. In this paper, we propose a new way for representing images in the form of strings whose symbols are weighted according to a TF-IDF-based weighting scheme, inspired from information retrieval. To be able to handle such real-valued weights, we first introduce a new weighted string edit distance that keeps the properties of a distance. In particular, we prove that the triangle inequality is preserved which allows the computation of the edit distance in quadratic time by dynamic programming. We show on an image classification task that our new weighted edit distance not only significantly outperforms the standard edit distance but also seems very competitive in comparison with standard histogram distances-based approaches.
    Lecture Notes in Computer Science 01/2010; 6321:72-86. · 0.51 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Bedload sediment transport of two-size coarse spherical particle mixtures in a turbulent supercritical flow was analyzed with image and particle tracking velocimetry algorithms in a two-dimensional flume. The image processing procedure is entirely presented. Experimental results, including the size, the position, the trajectory, the state of movement (rest, rolling, and saltation), and the neighborhood configuration of each bead, were compared with a previous one-size experiment. Analysis of the solid discharge along the vertical displayed only one peak of rolling in the two-size bed, whereas three peaks of rolling appeared in the one-size case due to a larger collective motion. The same contrast is evidenced in spatio-temporal diagrams where the two-size mixtures are characterized by the predominance of saltation and a smaller number of transitions between rest and rolling. The segregation of fine particles in a bed formed by larger particles was analyzed taking into account the neighborhood configurations.
    Experiments in Fluids 01/2010; · 1.57 Impact Factor
  • Source
    Advanced Engineering Materials 12/2009; 12(1‐2):20 - 29. · 1.61 Impact Factor
  • Source
    Estelle Parra-Denis, Christophe Ducottet, Dominique Jeulin
    [Show abstract] [Hide abstract]
    ABSTRACT: The problem of 3D shape characterisation has been intensively studied lately, because computing power is greatly increasing and image acquisition is more efficient, with new real 3D image acquisition methods like microtomography. The material studied in this work is a 5xxx aluminium alloy. It contains intermetallic particles which control both formability and surface aspect. During the industrial process used to transform slabs into plates, particles are broken and redistributed in the sheet space. In this paper, the shape of the intermetallic particles originating from the solidification process of aluminium alloys is studied. These particles are observed as being very complex. Modelling their shape requires a single approach based on 3D morphological analysis. A description of the shape of each intermetallic particle is given, using parameters and distribution measures. This paper also presents an original way to study the evolution of particles at different stages of deformation of the material and the evolution of its orientations. Biographical notes: Estelle Parra-Denis received her PhD degree in 2007 and her MS in Physical Science in 2002 from Saint-Etienne University, France. Her thesis on image analysis was on the characterisation of the complex shape of three-dimensional intermetallic particles extracted from aluminium alloys, to enable understanding of particles' ability to break up during the hot rolling process. She is currently working as a Research Engineer at the Centre of Mathematical Morphology. She has coauthored two publications in international journals and six publications in international conferences. Her research interests concern image analysis (mathematical morphology, image registration and three-dimensional image studies) applied to material characterisation and biomedical imaging. Christophe Ducottet graduated from Ecole Nationale Supérieure de Physique de Marseille, France in 1990 and received his PhD degree from Saint-Etienne University, France in 1994. He is currently a Professor at Saint-Etienne University with teaching activities at TELECOM Saint-Etienne and research activities at Hubert Curien Laboratory, UMR CNRS 5516. He has coauthored 15 publications in international journals and 25 publications in international conferences. His research interests concern image processing (feature extraction, morphological analysis, digital holography) in connection with applications in fluid mechanics, biomedical imaging and material characterisation. Professor Dominique Jeulin is the Director of Research and a Professor at Mines ParisTech, France. He teaches ParisTech courses on models of random structures, physics and mechanics of random media, and he is in charge of the doctoral formation in mathematical morphology. Since 1986, he has been leading the 'Physics of Heterogeneous Media' group, with activities in three laboratories of Mines ParisTech: Morphologie Mathématique (Fontainebleau), Géostatistique (Fontainebleau) and Materials (Evry), where he is Scientific Adviser. He has been involved in image analysis and materials science for over 30 years. He is co-author of over 360 publications, including several books. His current interest covers the theoretical prediction of physical properties of random media, models and simulations of random media, 3D image analysis and applications to materials science, biology and vision.
    Int. J. Microstructure and Materials Properties Int. J. Microstructure and Materials Properties. 01/2009; 4(4):217-230.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper reports our multimedia information retrieval experiments carried out for the ImageCLEF track 2009. In 2008, we proposed a multimedia document model defined as a vector of textual and visual terms weighted using a tf.idf approch [5]. For our second participation, our goal was to improve this previous model in the following ways: 1) use of additional information for the textual part (legend and image bounding text extracted from the original documents, 2) use of different image detectors and descriptors, 3) new text / image combination approach. Results allow to evaluate the benefits of these different improvements.
    ECDL 2009 - Workshop CLEF. 01/2009;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The potential of in-line digital holography to locate and measure the size of particles distributed throughout a volume (in one shot) has been established. These measurements are fundamental for the study of particle trajectories in fluid flow. The most important issues in digital holography today are poor depth positioning accuracy, transverse field-of-view limitations, border artifacts and computational burdens. We recently suggested an ‘inverse problem' approach to address some of these issues for the processing of particle digital holograms. The described algorithm improves axial positioning accuracy, gives particle diameters with sub-micrometer accuracy, eliminates border effects and increases the size of the studied volume. This approach for processing particle holograms pushes back some classical constraints. For example, the Nyquist criterion is no longer a restriction for the recording step and the studied volume is no longer confined to the field of view delimited by the sensor borders. In this paper we present a review of the limitations commonly found in digital holography. We then discuss the benefits of the ‘inverse problem' approach and the influence of some experimental parameters in this framework.
    Measurement Science and Technology 05/2008; · 1.44 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We address the twin-image problem that arises in holography due to the lack of phase information in intensity measurements. This problem is of great importance in in-line holography where spatial elimination of the twin image cannot be carried out as in off-axis holography. A unifying description of existing digital suppression methods is given in the light of deconvolution techniques. Holograms of objects spread in 3D cannot be processed through available approaches. We suggest an iterative algorithm and demonstrate its efficacy on both simulated and real data. This method is suitable to enhance the reconstructed images from a digital hologram of small objects.
    Measurement Science and Technology 05/2008; · 1.44 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper reports our multimedia information retrieval experiments carried out for the ImageCLEF track. We propose a new multimedia model combining textual and/or visual information which enables to perform textual, visual, or multimedia queries. We experiment the model on ImageCLEF data and we compare the results obtained using the different modalities. Our multimedia document model is based on a vector of textual and visual terms. Textual terms correspond to textual words while the visual ones are computed using local colour features. We obtain good results using only the textual part and we show that the visual information is useful in some particular cases.
    01/2008;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The goal of this paper is to describe a methodology for characterizing 3D complex shapes using morphological features. First, we provide 3D morphological measurements for understanding complex shapes. Second, we explain the analysis method based on principal component analysis. We illustrate our approach on populations of intermetallic particles of aluminium alloys investigated using X-ray microtomography. In that case, the analysis provides a description of shapes with a limited number of parameters, with a morphological interpretation for each of them. We finally demonstrate the practical interest of our work by comparing two populations extracted from the same aluminium sample at two deformation stages of a hot rolling process.
    Materials Characterization - MATER CHARACT. 01/2008; 59(3):338-343.
  • Workshop on Digital Holographic Reconstruction and Optical Tomography for Engineering Applications. 01/2007;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A method to analyze bed load with image processing was developed. The motion of coarse spherical particles on a mobile bed entrained by a shallow turbulent flow down a steep channel was filmed with a high-speed camera. The water free surface and the particle positions were detected combining classical image processing algorithms. We developed a particle-tracking algorithm to calculate all particle trajectories and motion regimes, rolling or saltation. At constant slope, the contribution of the rolling particles to the solid discharge only slightly differed when the particle supply was increased. At a slope of 10%, it represented about 40%. In contrast, rolling became the major regime when the slope increased, at a slope of 15% it represented up to 80% of the total solid discharge.
    Experiments in Fluids 07/2006; 41(1):1-11. · 1.57 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Digital holography, which consists of both acquiring the hologram image in a digital camera and numerically reconstructing the information, offers new and faster ways to make the most of a hologram. We describe a new method to determine the rough size of particles in an in-line hologram. This method relies on a property that is specific to interference patterns in Fresnel holograms: Self-correlation of a hologram provides access to size information. The proposed method is both simple and fast and gives results with acceptable precision. It suppresses all the problems related to the numerical depth of focus when large depth volumes are analyzed.
    Applied Optics 03/2006; 45(5):944-52. · 1.69 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: RESUME : Le but de cet article est de décrire une méthodologie pour caractériser par des mesures morphologiques des formes complexes tridimensionnelles. Dans un premier temps, nous proposons de paramètres morphologiques 3D pour expliciter la nature complexe de forme. Ensuite nous expliquons la méthode d'analyse des données utilisée basée sur l'analyse en composantes principales. Nous illustrons notre approche sur une population de particules intermétalliques contenues dans les alliages d'aluminium de type 5xxx (Les images sont obtenues par la méthode de micro tomographie aux rayons X). Dans le cadre de cette étude, l'analyse fournit une description de forme des objets par un nombre limité de paramètres dont l'interprétation morphologique est réalisée pour chacun. Nous montrons finalement l'intérêt pratique de notre travail en comparant pour le même matériau 2 états de déformation de l'alliage correspondant à 2 étapes du processus de laminage à chaud.
    MATERIAUX. 01/2006;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In-line digital holography conciles the applicative interest of a simple optical set-up with the speed, low cost and potential of digital reconstruction. We address the twin-image problem that arises in holography due to the lack of phase information in intensity measurements. This problem is of great importance in in-line holography where spatial elimination of the twin-image cannot be carried out as in off-axis holography. Applications in digital holography of particle fields greatly depend on its suppression to reach greater particle concentrations, keeping a sufficient signal to noise ratio in reconstructed images. We describe in this paper methods to improve numerically the reconstructed images by twin-image reduction. ©2005 COPYRIGHT SPIE
    Proc SPIE 08/2005;