Toward speech text recognition for comic books

Vers la reconnaissance automatique du texte de bandes dessinées

Christophe Rigaud (1) , Srikanta Pal (1) , Jean-Christophe Burie (1) , Jean-Marc Ogier (1)

1 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

Speech text in comic books is placed and written in a particular manner by the letterers which raises unusual challenges for text recognition. We first detail these challenges and present different approaches to solve them. We compare the performances of generic versus specifically trained OCR systems for typewritten and handwritten text lines from French comic books. This work is evaluated over a subset of public (eBDtheque) and private (Sequencity) datasets. We demonstrate that generic OCR systems perform best on typewritten-like and lowercase fonts while specifically trained OCR can be very powerful on skewed, uppercase and even cursive fonts.

Mots clés: CCS Concepts •Information systems → Content analysis and fea- ture selection; Keywords Handwritten text recognition; comics image analysis

Domaines: Traitement des images [eess.IV]; Traitement du texte et du document

Christophe Rigaud, Srikanta Pal, Jean-Christophe Burie, Jean-Marc Ogier. Toward speech text recognition for comic books. Proceedings of the 1st International Workshop on coMics ANalysis, Processing and Understanding, Dec 2016, Cancun, Mexico. ⟨10.1145/3011549.3011557⟩. ⟨hal-01719530⟩