Recovering Line-networks in Images by Junction-Point Processes

Abstract : The automatic extraction of line-networks from images is a well-known computer vision issue. Appearance and shape considerations have been deeply explored in the literature to improve accuracy in presence of occlusions, shadows, and a wide variety of irrelevant objects. However most existing works have ignored the structural aspect of the problem. We present an original method which provides structurally-coherent solutions. Contrary to the pixel-based and object-based methods, our result is a graph in which each node represents either a connection or an ending in the line-network. Based on stochastic geometry, we develop a new family of point processes consisting in sampling junction-points in the input image by using a Monte Carlo mechanism. The quality of a configuration is measured by a probability density which takes into account both image consistency and shape priors. Our experiments on a variety of problems illustrate the potential of our approach in terms of accuracy, flexibility and efficiency.
Type de document :
Communication dans un congrès
Computer Vision and Pattern Recognition (CVPR), Jun 2013, Portland, United States. 2013
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger
Contributeur : Florent Lafarge <>
Soumis le : mardi 16 avril 2013 - 17:31:29
Dernière modification le : jeudi 11 janvier 2018 - 16:21:55
Document(s) archivé(s) le : mercredi 17 juillet 2013 - 04:07:54


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00814262, version 1



Dengfeng Chai, Wolfgang Forstner, Florent Lafarge. Recovering Line-networks in Images by Junction-Point Processes. Computer Vision and Pattern Recognition (CVPR), Jun 2013, Portland, United States. 2013. 〈hal-00814262〉



Consultations de la notice


Téléchargements de fichiers