Mobile document image acquisition integrates many distortions which must be corrected or detected on the device, before the document becomes unavailable or paying data transmission fees. In this paper, we propose a system to correct perspective and illumination issues, and estimate the sharpness of the image for OCR recognition. The correction step relies on fast and accurate border detection f...

In this paper we present a new hybrid page segmentation approach based on connected component and region analysis. We first describe our stroke descriptor that detects text and line component candidates using the skeleton of the binarized document image. Then, the active contour Chan and Vese model is applied to segment the rest of the image into photo and background regions. This classificatio...

The problem of unsupervised and semi-supervised clustering is extensively studied in machine learning. In order to involve user in image data clustering, (Lai et al., 2014) proposed a new approache for interactive semi-supervised clustering that translates the feedback of user (expressed at the level of individual images) into pairwise constraints between groups of images, these groupes being c...

In this article, we propose a new model of images representation. This work contributes to the subject of the general framework for image indexing and retrieval on the WEB .We describe a method to construct and quantify images from a semantic model, based on graphs, using a set of descriptors. This quantification of the skeleton graph is used for indexing images. In the case of images, the retr...

RÉSUMÉ. Dans cet article, nous proposons un système d’extraction de mots clés dans des documents manuscrits. Notre approche est basée sur la reconnaissance des lignes de texte à l’aide d’un modèle HMM capable de rejeter les mots n’appartenant pas à un lexique prédéfini. Afin d’être plus discriminant, nous avons remplacé les mélanges de gaussiennes des HMM par un réseau de neurones profond pour ...

Mots clés: Modélisation géométrique parfrontì eres Modélisation géométriquè a base topologique des objets 3D non-variétés Subdivisions, compexes cellulaires Acquisition, recalage et reconstruction Maillages, courbures discrètes Préservation de l'héritage culturel References [1] S. Gueorguieva. New techniques for deformation of solids defined by sweeping .

A Segmenter-POS Labeller and a Chunker for French We propose a demo of two softwares : a Segmenter-POS Labeller for French and a Chunker for texts treated by the first program. Both have been learned from the French Tree Bank. MOTS-CLÉS : étiquetage POS, chunking, apprentissage automatique, French Tree Bank, CRF.

Problems encountered within the e-democracy are closely related to the web 2.0 phenomenon. To be able to manage the flow of generated data, models and tools become a necessity. In this paper, we present the "Annotation" as a practical and effective model on which we will base our argument. MOTS-CLÉS : débat, annotation, argumentation, opposition, opinion.

The aim of this paper is to analyze the influence of presentations formats of information on the learning of computerized documents. Recent advances in technology have prompted new ways of presenting information: dynamic illustrations, simultaneous use of aural and written information for example. Consequences of theses formats on understanding are exposed. MOTS-CLÉS : apprentissage, compréhens...