Éditeur(s) : HAL CCSD Hong Kong : World Academic Publishing
Résumé : International audience
In automatic image analysis, when using natural images, it is important to select the elements in a scene that can lead to correct characterization. Extraneous elements can result in poor values in the parameter evaluation for recognition. Irrelevant elements also increase the processing time, because they can be used incorrectly by the algorithms for characterization or identification. The goal of this paper is to offer identification algorithms and characterizations that will allow effective recognition. We base our procedure on the photographer focus areas to identify those relevant elements in a scene. In this work, we propose a procedure to select the relevant shape from natural images. The treatment uses focal depth with edge detectors. The resulting points are combined with a region partition to obtain relevant shapes.
ISSN: 2309-0650

hal-01278550
https://hal.archives-ouvertes.fr/hal-01278550

Éditeur(s) : HAL CCSD
Résumé : Given the technological development of embedded satellite sensors, the potential of available satellite images increases so that the question now arises of their most efficient exploitation possible. This is the purpose of the CARTAM-SAT project to fluidize the processing workflow from satellite images to users. The thesis is part of this framework.Processing operations relating to images have evolved over the years. Low-resolution images were processed by a so-called pixel approach while the high-resolution has allowed the development of a so-called object approach. The latter focuses on analysing not about the isolated pixels, but about groups of pixels representative of concrete objects on the ground. Thus, in principle, these are groups of pixels with a domain-specific remote sensing semantics.Along with satellite imagery, knowledge representation has evolved. The standards of representation have benefited from the expansion of the web to give rise to standards like OWL. This one is widely based on description logics that allow the use of automated reasoners able to infer implicit knowledge.This thesis is at the junction of these two sciences and provides an ontological approach for analysing satellite images. The aim is to formalize different types of knowledges and conceptualizations implicitly used by image processing programs and by remote sensing experts, and then reasoning automatically on an image description to obtain one semantic interpretation.This general principle may have numerous technical variations. The implementation consisted in a prototype combining a satellite image analysis library and an ontology-based reasoner. The implementation proposed in the thesis allows to explore four technical variations of the principle that lead to discussions on the complementarity of pixel and object analysis paradigms, the representation of some of the spatial relations and the role of knowledge in relation to processing.
Étant donnée l'évolution technologique des capteurs embarqués à bord des satellites, le potentiel d'images satellitaires accessible s'accroît de telle manière que se pose maintenant la question de son exploitation la plus efficace possible. C'est l'objectif du projet CARTAM-SAT que de fluidifier la chaîne de traitement depuis les satellites jusqu'aux utilisateurs des images. La thèse s'inscrit dans ce cadre. Les traitements relatifs aux images ont évolué au cours des années. Les images basse résolution étaient traitées par une approche dite pixel alors que la haute résolution a permis le développement d'une approche dite objet. Cette dernière s'attache à analyser non plus des pixels isolés, mais des groupes de pixels représentatifs d'objets concrets sur le terrain. Ainsi, en principe, ces groupes de pixels sont dotés d'une sémantique propre au domaine de la télédétection. La représentation des connaissances a évolué parallèlement aux images satellitaires. Les standards de représentation ont profité de l'expansion du web pour donner naissance à des standards comme OWL. Celui-ci repose en grande partie sur les logiques de description qui permettent l'utilisation de raisonneurs automatiques capables d'inférer une connaissance implicite.Cette thèse se place à la jonction de ces deux sciences et propose une approche ontologique d'analyse des images satellitaires. Il s'agit de formaliser différents types de connaissances et de conceptualisations implicitement utilisés par les logiciels de traitement d'image et par les experts en télédétection, puis de raisonner automatiquement sur la description d'une image pour en obtenir une interprétation sémantique.Ce principe général est susceptible de nombreuses déclinaisons techniques. La mise en œuvre a consisté en la réalisation d'un prototype alliant une bibliothèque d'analyse d'images satellitaires et un raisonneur basé sur les ontologies. L'implémentation proposée dans la thèse permet d'explorer quatre déclinaisons techniques du principe qui mènent à des discussions sur la complémentarité des paradigmes d'analyse pixel et objet, la représentation de certaines relations spatiales et la place de la connaissance par rapport aux traitements.
https://tel.archives-ouvertes.fr/tel-00998692

NNT : 2013MON20059
tel-00998692
https://tel.archives-ouvertes.fr/tel-00998692
https://tel.archives-ouvertes.fr/tel-00998692/document

Éditeur(s) : HAL CCSD Institute of Electrical and Electronics Engineers
Résumé : International audience
This paper presents our response to the first interna- tional challenge on Facial Emotion Recognition and Analysis. We propose to combine different types of features to automatically detect Action Units in facial images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and an RBF kernel. During the training step, we combine these two types of features using the recently proposed SimpleMKL algorithm. SVM outputs are then averaged to exploit temporal information in the sequence. To eval- uate our system, we perform deep experimentations on several key issues: influence of features and kernel function in histogram- based SVM approaches, influence of spatially-independent in- formation versus geometric local appearance information and benefits of combining both, sensitivity to training data and interest of temporal context adaptation. We also compare our results to those of the other participants and try to explain why our method had the best performance during the FERA challenge.
ISSN: 1083-4419

hal-00731864
http://hal.upmc.fr/hal-00731864
http://hal.upmc.fr/hal-00731864/document
http://hal.upmc.fr/hal-00731864/file/senechal12tsmc_preprint.pdf
DOI : 10.1109/TSMCB.2012.2193567

Éditeur(s) : HAL CCSD
Résumé : En traitement d'image, avant toute exploitation de résultats d'une segmentation d'image, il est souvent nécessaire de réaliser une opération de fusion. Le but est de créer une partition formée de composantes connexes, modélisant les objets présents dans l'image. La segmentation initiale des images est souvent obtenue par l'exploitation d'attributs de bas-niveau (couleur, texture, forme...). La théorie Gestalt permet de prendre en compte des informations d'un niveau supérieur qui s'appuient sur l'organisation spatiale des objets et groupement d'objets initialement segment'es. Dans cet article, nous proposons une méthode de fusion de régions. L'originalité des travaux repose sur l'ajout d'un nouveau critère qui, associé aux critères Gestalt, permet de prendre en compte les objets jugés d'intérêt par le photographe, c'est-'a-dire les objets aux contours nets. Les régions associées aux objets d'intérêts seront alors préservées alors que les régions floues ou aux contours flous, situées dans l'arrière-plan, auront tendance 'a fusionner entre elles.
Journée du GdR Mathématique de l'Optimisation et Application (MOA)
Saint-François, Guadeloupe

hal-00706538
https://hal.archives-ouvertes.fr/hal-00706538

Éditeur(s) : HAL CCSD Springer Verlag
Résumé : 17 pages, 11 figures.
International audience
The problem addressed in this paper is the automatic extraction of names from a document image. Our approach relies on the combination of two complementary analyses. First, the image-based analysis exploits visual clues to select the regions of interest in the document. Second, the textual-based analysis searches for name patterns and low-level word textual features. Both analyses are then combined at the word level through a neural network fusion scheme. Reported results on degraded documents such as facsimile and photocopied technical journals demonstrate the interest of the combined approach.
ISSN: 1433-7541

hal-00329459
https://hal.archives-ouvertes.fr/hal-00329459
DOI : 10.1007/s10044-006-0038-6

Éditeur(s) : HAL CCSD
Résumé : International audience
This paper shows the information criteria (IC) performances in feature selection framework. Feature selection aims to select a representative subset among a wide set of features. We apply this approach to classify an hand segmented image. The performance is tested using various feature selection schemes (SFS, SBS, SFFS and SBFS) to select the candidate subsets. The accuracy of the approach is based on a good quality of the joint probability density approximation of the combined features. They are obtained using histogram optimized thanks to the adaptive arithmetic coding principles. Our approach is tested on different reference data. The subsets quality is evaluated using correct classification rate computed on multiple classifiers. Results show stability and convergence properties of this tool and its ability to select representative subsets (in the sense that the subset of feature is a good characterization of the classes in which the data belong). Information Criteria could be used for feature selection as a good alternative to other criteria.
CISP Proceedings
Shangay, China

hal-00634749
https://hal.archives-ouvertes.fr/hal-00634749

Éditeur(s) : HAL CCSD
Résumé : Ce travail traite de " l'identification de plantes à partir d'images numériques, par champs de gradients ", provenant de capteurs de types variés. Nous avons choisi des méthodes de type global, afin de pré-segmenter efficacement l'image d'une plante. Parmi ces méthodes, celle du Mean Shift permet de s'acquitter des tâches de paramétrisation, mais présente l'inconvénient d'une forte complexité de calcul. Nous proposons deux méthodes pour résoudre ce problème : le Mean Shift avec changement d'échelle et le Mean Shift Markovien dont le but est de limiter le traitement systématique de tous les pixels par la partie Mean Shift. L'application de ces méthodes permet d'obtenir une partition de l'image dans laquelle on recherche les groupes de pixels, matérialisant les parties d'une plante focalisée par le photographe. Pour mettre en évidence ces zones, nous exploitons : la netteté des formes, la position et la densité spatiale des objets dans une image, afin de construire des masques qui représentent les parties d'une plante. À partir de ces masques, nous extrayons un ensemble de caractéristiques issu de la botanique descriptive, regroupé en trois catégories : la colorimétrie, la morphologie et le structurel. Nos choix méthodologiques sont expérimentés sur une base de données d'images, pour obtenir un ensemble de valeurs de caractéristiques appelées descripteurs. Ces descripteurs sont fournis à un système de classeurs basé sur des algorithmes génétiques, afin d'obtenir des règles désignant chaque type de plantes. L'objectif de ces règles est d'associer un score de ressemblance à chaque image de la base de données, en fonction de l'image soumise comme requête au système de reconnaissance.
Journées d'Études et de recherche des Antilles et de la Guyane
Pointe-à-Pitre, Guadeloupe

hal-00637788
https://hal.archives-ouvertes.fr/hal-00637788

Éditeur(s) : HAL CCSD MDPI
Résumé : International audience
ISSN: 2072-4292

hal-01429052
https://hal.archives-ouvertes.fr/hal-01429052
DOI : 10.3390/rs4103244

Éditeur(s) : HAL CCSD IEEE
Résumé : International audience
This paper proposes a novel automated approach for the categorization of cells in fluorescence microscopy images. Our supervised classification method aims at recognizing patterns of unlabeled cells based on an annotated dataset. First, the cell images need to be indexed by encoding them in a feature space. For this purpose, we propose tailored bio-inspired features relying on the distribution of contrast information. Then, a supervised learning algorithm is proposed for classifying the cells. We carried out experiments on cellular images related to the diagnosis of autoimmune diseases, testing our classification method on the HEp-2 Cells dataset of Foggia et al (CBMS 2010). Results show classification precision larger than 96% on average, thus confirming promising application of our approach to the challenging application of cellular image classification for computer-aided diagnosis.
ICPR 2012
Tsukuba, Japan

hal-00958856
https://hal.archives-ouvertes.fr/hal-00958856
https://hal.archives-ouvertes.fr/hal-00958856/document
https://hal.archives-ouvertes.fr/hal-00958856/file/icpr_2012.pdf

Éditeur(s) : HAL CCSD Springer
Résumé : Third International Workshop, MLMI 2012, Held in Conjunction with MICCAI 2012
International audience
Universal Nearest Neighbours (unn) is a classifier recently proposed, which can also effectively estimates the posterior probability of each classification act. This algorithm, intrinsically binary, requires the use of a decomposition method to cope with multiclass problems, thus reducing their complexity in less complex binary subtasks. Then, a reconstruction rule provides the final classification. In this paper we show that the application of unn algorithm in conjunction with a reconstruction rule based on the posterior probabilities provides a classification scheme robust among different biomedical image datasets. To this aim, we compare unn performance with those achieved by Support Vector Machine with two different kernels and by a k Nearest Neighbours classifier, and applying two different reconstruction rules for each of the aforementioned classification paradigms. The results on one private and five public biomedical datasets show satisfactory performance.
Machine Learning in Medical Imaging
Nice, France

hal-00958909
https://hal.archives-ouvertes.fr/hal-00958909
https://hal.archives-ouvertes.fr/hal-00958909/document
https://hal.archives-ouvertes.fr/hal-00958909/file/Miccai.pdf
DOI : 10.1007/978-3-642-35428-1_15

Éditeur(s) : HAL CCSD
Résumé : This paper presents the experimental results obtained for an automatic detection of ships in High Resolution optical satellite images. Our images are panchromatic SPOT 5 images, whose resolution is 5m per pixel. Our detection method is part of an industrial project of maritime surveillance. It is based on the Bayesian decision theory and does not need any preprocessing.The detection is composed of three stages. The first one is a pre-detection of targets that gives us candidates. The second one is a precise segmentation of each candidate. The third one is a classification of candidates into three classes : real small targets, real big targets and false alarms. The two first stages are based on the bayesian theory, using a very simple image model that leads to very fast algorithms. For now, the classification is based on multivariate decision tree. Finally, the overall results of the method are given for a set of images, as close as possible to the operational conditions and show the performances of the proposed method (detection of almost all the ships, false alarms due to crests of waves and an acceptable computing time).
Journée Nationale de Photogrammétrie et Télédétection

hal-00601854
https://hal.archives-ouvertes.fr/hal-00601854

Éditeur(s) : HAL CCSD
Résumé : International audience
We propose in this article a color image segmentation technique based on an optimization of the Mean Shift method. It consists in classifying clusters of data points of a digital image, it does not require any preliminary designation of the number of classes and of their centers. The Mean Shift method applied to a digital color image creates a new image made up of aggregates of points belonging to a finished number of color classes. The complexity of this method based on a global approach of the image is in O(NxN), N being the number of pixels of the image. Our idea consists in applying a change of scale to the image to be segmented, to reduce the quantity of information and, in using a median filter to decrease the number of colors to minimize the complexity of the latter. The comparative study which we present shows that the optimization which we proposed gives better, reliable results than the classic use of the Mean Shift method.
Complex, Intelligent and Software Intensive Systems, International Conference
Cracovie, Poland

hal-00508427
https://hal.archives-ouvertes.fr/hal-00508427
DOI : 10.1109/CISIS.2010.62

Éditeur(s) : HAL CCSD
Résumé : International audience
The segmentation of digital images of plants is a tricky operation. In the example of a plant image on a unhomogeneous background, i.e. taken in its environment, the colorimetric diversity of the elements of a scene or the large number of forms can amplify the phenomena of over-segmentation. Global segmentation methods such as Mean Shift are then in this case the ones which will give the best results. These methods take into account the totality of the pixels of an image before classifying a point. On the other hand, complexity is increased, because it is necessary to go through the whole image treated, in order to find the mode of the point which one wishes to classify. In this article, we plan to couple the global segmentation with a local method which would take over in the event of obvious classification of a given point. The Mean Shift method is used for this purpose in association with Markov's chains.
Applied Imagery Pattern Recognition (AIPR)
Washington DC, United States

hal-00637143
https://hal.archives-ouvertes.fr/hal-00637143
DOI : 10.1109/AIPR.2011.6176338

Éditeur(s) : HAL CCSD BioMed Central
Résumé : International audience
BACKGROUND: Sampling design is a key issue when establishing species inventories and characterizing habitats within highly heterogeneous landscapes. Sampling efforts in such environments may be constrained and many field studies only rely on subjective and/or qualitative approaches to design collection strategy. The region of Cacao, in French Guiana, provides an excellent study site to understand the presence and abundance of Anopheles mosquitoes, their species dynamics and the transmission risk of malaria across various environments. We propose an objective methodology to define a stratified sampling design. Following thorough environmental characterization, a factorial analysis of mixed groups allows the data to be reduced and non-collinear principal components to be identified while balancing the influences of the different environmental factors. Such components defined new variables which could then be used in a robust k-means clustering procedure. Then, we identified five clusters that corresponded to our sampling strata and selected sampling sites in each stratum. RESULTS: We validated our method by comparing the species overlap of entomological collections from selected sites and the environmental similarities of the same sites. The Morisita index was significantly correlated (Pearson linear correlation) with environmental similarity based on i) the balanced environmental variable groups considered jointly (p = 0.001) and ii) land cover/use (p-value<0.001). The Jaccard index was significantly correlated with land cover/use-based environmental similarity (p-value = 0.001). CONCLUSIONS: The results validate our sampling approach. Land cover/use maps (based on high spatial resolution satellite images) were shown to be particularly useful when studying the presence, density and diversity of Anopheles mosquitoes at local scales and in very heterogeneous landscapes.
BMC Ecology

pasteur-00914104
https://hal-riip.archives-ouvertes.fr/pasteur-00914104
https://hal-riip.archives-ouvertes.fr/pasteur-00914104/document
DOI : 10.1186/1472-6785-13-45
PUBMED : 24289184

Éditeur(s) : HAL CCSD
Résumé : International audience
https://hal.archives-ouvertes.fr/hal-01436542

hal-01436542
https://hal.archives-ouvertes.fr/hal-01436542
DOI : 10.1109/IGARSS.2011.6049595

Éditeur(s) : HAL CCSD
Résumé : International audience
In this paper, we investigate image segmentation by region merging. Given any similarity measure between regions , satisfying some weak constraints, we give a general predicate for answering if two regions are to be merged or not during the segmentation process. Our predicate is generic and has six properties. The first one is its inde-pendance with respect to the similarity measure, that leads to a user-independant and adaptative predicate. Second, it is non-parametric, and does not rely on any assumption concerning the image. Third, due to its weak constraints, knowledge may be included in the predicate to fit better to the user's behaviour. Fourth, provided the similarity is well-chosen by the user, we are able to upperbound one type of error made during the image segmentation. Fifth, it does not rely on a particular segmentation algorithm and can be used with almost all region-merging algorithms in various application domains. Sixth, it is calculated quickly, and can lead with appropriated algorithms to very efficient segmentation.
10th IEEE International Conference on Tools with Artificial Intelligence
Taipei, Taiwan

lirmm-01168371
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01168371
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01168371/document
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01168371/file/FioNocICTAI98_Image%20Segmentation%20Using.pdf
DOI : 10.1109/TAI.1998.744885

Éditeur(s) : HAL CCSD IEEE
Résumé : International audience
Recent works display that large scale image classification problems rule out computationally demanding methods. On such problems, simple approaches like k-NN are affordable contenders, with still room space for statistical improvements under the algorithmic constraints. A recent work showed how to leverage k-NN to yield a formal boosting algorithm. This method, however, has numerical issues that make it not suited for large scale problems. We propose here an Adaptive Newton-Raphson scheme to leverage k-NN, N³, which does not suffer these issues. We show that it is a boosting algorithm, with several key algorithmic and statistical properties. In particular, it may be sufficient to boost a subsample to reach desired bounds for the loss at hand in the boosting framework. Experiments are provided on the SUN, and Caltech databases. They confirm that boosting a subsample -- sometimes containing few examples only -- is sufficient to reach the convergence regime of N³. Under such conditions, N³ challenges the accuracy of contenders with lower computational cost and lower memory requirement.
IEEE International Workshop on Machine Learning for Signal Processing
Southampton, United Kingdom

hal-00959125
https://hal.archives-ouvertes.fr/hal-00959125
https://hal.archives-ouvertes.fr/hal-00959125/document
https://hal.archives-ouvertes.fr/hal-00959125/file/BNNB_mlsp2013.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
The k-nearest neighbors (k-NN) classification rule is still an essential tool for computer vision applications, such as scene recognition. However, k-NN still features some major drawbacks, which mainly reside in the uniform voting among the nearest prototypes in the feature space. In this paper, we propose a new method that is able to learn the "relevance" of prototypes, thus classifying test data using a weighted k-NN rule. In particular, our algorithm, called Multi-class Leveraged k-nearest neighbor (MLNN), learns the prototype weights in a boosting framework, by minimizing a surrogate exponential risk over training data. We propose two main contributions for improving computational speed and accuracy. On the one hand, we implement learning in an inherently multiclass way, thus providing significant computation time reduction over one-versus-all approaches. Furthermore, the leveraging weights enable effective data selection, thus reducing the cost of k-NN search at classification time. On the other hand, we propose a kernel generalization of our approach to take into account real-valued similarities between data in the feature space, thus enabling more accurate estimation of the local class density. We tested MLNN on three datasets of natural images. Results show that MLNN significantly outperforms classic k-NN and weighted k-NN voting. Furthermore, using an adaptive Gaussian kernel provides significant performance improvement. Finally, the best results are obtained when using MLNN with an appropriate learned metric distance.
Proceedings of the 10th Asian Conference on Computer Vision, ACCV 2010, November 8-12, 2010, Queenstown, New Zealand
Queenstown, New Zealand

hal-00664606
https://hal.inria.fr/hal-00664606
https://hal.inria.fr/hal-00664606/document
https://hal.inria.fr/hal-00664606/file/mlnn_accvfinal.pdf

Éditeur(s) : HAL CCSD CNRS-Editions
Résumé : Toute l'histoire des techniques de communication est intimement liée à l'histoire de l'éducation. Avant le cahier, la craie et le tableau, on savait, dans l'antiquité, recourir à diverses techniques pour construire des dispositifs socio-techniques susceptibles de faciliter l'apprentissage (Marrou, 1948). Les possibilités offertes par l'image et ses moyens successifs de diffusion ont été de même fondamentales dans la diffusion des connaissances. Ce fut d'abord l'image artisanale (vitraux et enluminures utilisés pour l'édification...). Puis l'image imprimée dès le début du seizième siècle (planches, éclatés, cartes...) et l'image projetée (de la lanterne magique aux diapositives). A partir du vingtième siècle, l'image audiovisuelle et la production industrielle (photographie, radio, cinéma, télévision...) ont croisé les systèmes éducatifs comme l'ont fait depuis une vingtaine d'années les techniques de numérisation des documents (sonores, iconiques et graphiques), les logiciels d'apprentissage, de simulation et de production, la transmission à travers des réseaux numériques, et les nouvelles formes de documents informatisés (hypertexte, écrit sur écran...)...
ISSN: 0767-9513

Droits : info:eu-repo/semantics/OpenAccess
edutice-00001307
https://edutice.archives-ouvertes.fr/edutice-00001307
https://edutice.archives-ouvertes.fr/edutice-00001307/document
https://edutice.archives-ouvertes.fr/edutice-00001307/file/hermes_SIC.pdf

Éditeur(s) : HAL CCSD Springer International Publishing AG.
Résumé : International audience
Underwater Seascapes. From geographical to ecological perspectives

hal-01429034
https://hal.archives-ouvertes.fr/hal-01429034
DOI : 10.1007/978-3-319-03440-9_16