Top-Down and Bottom-Up Cues for Scene Text Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Top-Down and Bottom-Up Cues for Scene Text Recognition

Résumé

Scene text recognition has gained significant attention from the computer vision community in recent years. Recognizing such text is a challenging problem, even more so than the recognition of scanned documents. In this work, we focus on the problem of recognizing text extracted from street images. We present a framework that exploits both bottom-up and top-down cues. The bottom-up cues are derived from individual character detections from the image. We build a Conditional Random Field model on these detections to jointly model the strength of the detections and the interactions between them. We impose top-down cues obtained from a lexicon-based prior, i.e. language statistics, on the model. The optimal word represented by the text image is obtained by minimizing the energy function corresponding to the random field model. We show significant improvements in accuracies on two challenging public datasets, namely Street View Text (over 15%) and ICDAR 2003 (nearly 10%).
Fichier principal
Vignette du fichier
mishra12.pdf (398.94 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Fichier non déposé

Dates et versions

hal-00818178 , version 1 (03-11-2014)

Identifiants

Citer

Anand Mishra, Karteek Alahari, C.V. Jawahar. Top-Down and Bottom-Up Cues for Scene Text Recognition. CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, United States. ⟨10.1109/CVPR.2012.6247990⟩. ⟨hal-00818178⟩
449 Consultations
1518 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More