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 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 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 : 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
Résumé : International audience
Proceedings of the 15th International Conference of the Graphonomics Society - IGS 2011
Cancun, Mexico

hal-00604380
https://hal.archives-ouvertes.fr/hal-00604380

Éditeur(s) : HAL CCSD
Résumé : International audience
The fusion of regions from segmentation is often a required step in order to analyze objects in the scene. It allows to group under a same closure property the partitions of an image, which denote the same object. In this way, several studies have been made. Most of the algorithms are based on global information to evaluate the relevance of region combinations and fusion. In this paper, we propose a merging process based on Gestalt vision's theory. The particularity of our method is to preserve photographer's region of interest thanks to the definition of a new criterion based on Di Zenzo gradient. Thus, region fusion preserves photographer's relevant objects of the scene. The performance of the proposed method is evaluated using various natural images, including Berkeley image database and its accuracy is shown.
Color and Imaging Conference
San Jose, CA, United States

hal-00637144
https://hal.archives-ouvertes.fr/hal-00637144

Éditeur(s) : HAL CCSD Institute of Electrical and Electronics Engineers
Résumé : International audience
Tailoring nearest neighbors algorithms to boosting is an important problem. Recent papers study an approach, UNN, which provably minimizes particular convex surrogates under weak assumptions. However, numerical issues make it necessary to experimentally tweak parts of the UNN algorithm, at the possible expense of the algorithm's convergence and performance. In this paper, we propose a lightweight alternative algorithm optimizing proper scoring rules from a very broad set, and establish formal convergence rates under the boosting framework that surprisingly compete with those known for UNN. It is an adaptive Newton-Raphson algorithm, which belongs to the same lineage as the popular Gentle Adaboost. To the best of our knowledge, no such boosting-compliant convergence rates were previously known for these algorithms. We provide experiments on a dozen domains, including the challenging Caltech and SUN computer vision databases. They display that GNNB significantly outperforms UNN, both in terms of convergence rate and quality of the solution obtained, and GNNB provides a simple and efficient contender to techniques that can be used on very large domains, like stochastic gradient descent -- for which little is known to date. Experiments include a divide-and-conquer improvement of GNNB which exploits the link with proper scoring rules optimization.
ISSN: 0162-8828

hal-00958809
https://hal.archives-ouvertes.fr/hal-00958809
https://hal.archives-ouvertes.fr/hal-00958809/document
https://hal.archives-ouvertes.fr/hal-00958809/file/PAMI.pdf
DOI : 10.1109/TPAMI.2014.2307877

Éditeur(s) : HAL CCSD
Résumé : National audience
Dans cet article nous présentons les résultats opérationnels obtenus pour la pré-détection de bateaux de pêche dans des images satellites optiques haute résolution. Les images utilisées sont de type SPOT 5 panchromatique de résolution 5m. La méthode utilisée s'appuie sur les techniques Bayésiennes classiques de détection, et ne comporte aucun pré-traitement. Au cours de cet article, nous décrivons précisément la méthode utilisée, ainsi que le réglage des deux seuls paramètres de la méthode qui sont le seuil de détection et la taille de la fenêtre d'analyse. Ces paramètres sont fixés à partir des courbes ROC (Receiver Operating Characteristic) obtenues sur les jeux de tests dont nous disposons. La méthode est enfin testée sur un jeu complet et réaliste d'images. La méthode doit être à terme intégrée dans une application industrielle.
ORASIS'09 - Congrès des jeunes chercheurs en vision par ordinateur
Trégastel, France, France

Droits : info:eu-repo/semantics/OpenAccess
inria-00404625
https://hal.inria.fr/inria-00404625
https://hal.inria.fr/inria-00404625/document
https://hal.inria.fr/inria-00404625/file/23.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Drawing and handwriting are communicational skills that are fundamental in geopolitical, ideological and technological evolutions of all time. drawingand handwriting are still useful in defining innovative applications in numerous fields. In this regard, researchers have to solve new problems like those related to the manner in which drawing and handwriting become an efficient way to command various connected objects; or to validate graphomotor skills as evident and objective sources of data useful in the study of human beings, their capabilities and their limits from birth to decline.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

Droits : http://creativecommons.org/licenses/by-nc-nd/
ISBN : 979-10-95177-01-2
hal-01166509
https://hal.univ-antilles.fr/hal-01166509
https://hal.univ-antilles.fr/hal-01166509/document
https://hal.univ-antilles.fr/hal-01166509/file/IGS2015proceedingsvHal-1.pdf