This paper presents an approach for spotting textual fields in colored forms. We proceed by locating these fields thanks to their neighboring context which is modeled with a structural representation. First, informative zones are extracted. Second, forms are represented by graphs in which nodes represent colored rectangles while edges represent neighboring links. Finally, the context of the que...

This paper presents a software dedicated to semisynthetic old document image generation and its associated ground truth. This work is thus part of the data generation for document processing algorithm performance evaluation. This software allows a user to specify the content and layout of images to generate (fonts, illustrations, line spacing). Several degradation models were incorporated into ...

We study in this paper the problem of using multiple-instance semi-supervised learning to solve image Relevance feedback problem. Many multiple-instance learning algorithms have been proposed to tackle this problem; most of them only have a global representation of images. In this paper, we present a semi-supervised version of multiple instance learning. By taking into account both the multiple...

Collaborative filtering (CF) systems help a user find the information satisfying his needs by using other users’ judgements. These systems are mainly used in Web sites to provide recommendations. In general, CF systems ask users to provide a judgement to a number of items of their choice, expressed as a rating. The goal of the system is then to compare different user’s tastes to predict the unk...

Social networks make it possible to share rapidly and massively information. Yet, one of their major drawback comes from the absence of verification of the piece of information, especially with viral messages. This is the issue addressed by the participants to the Verification Multimedia Use task of Mediaeval 2016. They used several approaches and clues from different modalities (text, image, s...

This paper deals with topic segmentation of TV broadcasts using their transcription obtained by automatic speech recognition. Topic segmentation has been studied for several years, and most often the techniques proposed rely on information retrieval techniques to compute similarities between segments. In this paper, we propose a new segmentation approach inspired by mathematical morphology stud...

Résumé : Choisir les descripteurs d’une image en vue de son indexation n’est pas aisé, du fait de la variété des choix présentés dans la littérature. Nous développons à cet effet une méthodologie permettant de comparer différents ensembles de caractéristiques extraits d’une même base d’images. Cette méthodologie repose sur des algorithmes supervisés et non supervisés de sélection de caractérist...

Dans cet article, nous proposons une méthode de détection et de suivi d’un objet dans une séquence d’images basée sur le contour actif. Une fonctionnelle d’énergies est attachée au contour actif. Après une initialisation du contour actif dans la première image de la séquence, la minimisation des énergies attachées est utilisé afin de détecter le contour. Puis une initialisation automatique du c...

Social networks mirror public opinion. Thus, they are of great interest for opinion mining and sentiment analysis. In most cases, sentiment is classified according to a polarity criterion or a linear gradation. Is it possible to learn more complex patterns with limited itemsets? In this article, we investigate brand equity. The goal is to analyze how social groups perceive a given brand. Brand ...

We introduce an extension of bag-of-words image representations to encode spatial layout. Using the Fisher kernel framework we derive a representation that encodes the spatial mean and the variance of image regions associated with visual words. We extend this representation by using a Gaussian mixture model to encode spatial layout, and show that this model is related to a soft-assign version o...