Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Communication dans un congrès

Snoopertext: A multiresolution system for text detection in complex visual scenes

Abstract : Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shape-based classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results.
Type de document :
Communication dans un congrès
Liste complète des métadonnées
Contributeur : Bibliothèque MINES ParisTech Connectez-vous pour contacter le contributeur
Soumis le : samedi 15 juin 2013 - 11:10:39
Dernière modification le : samedi 22 octobre 2022 - 05:10:57

Lien texte intégral



Rodrigo Minetto, Nicolas Thome, Matthieu Cord, Jonathan Fabrizio, Beatriz Marcotegui. Snoopertext: A multiresolution system for text detection in complex visual scenes. ICIP 2010 - 17th IEEE International Conference on Image Processing, Sep 2010, Hong-Kong, Hong Kong SAR China. pp.3861-3864, ⟨10.1109/ICIP.2010.5651761⟩. ⟨hal-00834466⟩



Consultations de la notice