This note introduces a visual attention model of text localization in real-world scenes. The core of the model built upon the proto-object concept is discussed. It is shown how such dynamic mid-level representation of the scene can be derived in the framework of an action-perception loop engaging salience, text information value computation, and eye guidance mechanisms. Preliminary results that compare model generated scanpaths with those eye-tracked from human subjects are presented.
Towards modelling an attention-based text localization process / A. Clavelli, D. Karatzas, J. Lladós, M. Ferraro, G. Boccignone - In: Pattern recognition and image analysis : 6th iberian conference, IbPRIA 2013 : Funchal, Madeira, Portugal, june 5-7, 2013 : proceedings / [a cura di] J. Sanches, L. Micò, J.S. Cardoso. - Berlin : Springer, 2013. - ISBN 9783642386275. - pp. 296-303 (( Intervento presentato al 6. convegno Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) tenutosi a Funchal, Madeira, Portugal nel 2013 [10.1007/978-3-642-38628-2_35].
Towards modelling an attention-based text localization process
G. BoccignoneUltimo
2013
Abstract
This note introduces a visual attention model of text localization in real-world scenes. The core of the model built upon the proto-object concept is discussed. It is shown how such dynamic mid-level representation of the scene can be derived in the framework of an action-perception loop engaging salience, text information value computation, and eye guidance mechanisms. Preliminary results that compare model generated scanpaths with those eye-tracked from human subjects are presented.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
