Document detection in videos captured by smartphones using a saliency-based method - Archive ouverte HAL
Communication Dans Un Congrès Année : 2019

Document detection in videos captured by smartphones using a saliency-based method

Résumé

Smartphones are now widely used to digitizepaper documents. Document detection is the first importantstep of the digitization process. Whereas many methods extractlines from contours as candidates for the document boundary, we present in this paper a region-based approach. A key feature of our method is that it relies on visual saliency, using a recent distance existing in mathematical morphology. We show that the performance of our method is competitive with state-of-the-art methods on the ICDAR Smartdoc 2015 Competition dataset.
Fichier non déposé

Dates et versions

hal-04579610 , version 1 (17-05-2024)

Identifiants

Citer

Minh On Vu Ngoc, Jonathan Fabrizio, Thierry Géraud. Document detection in videos captured by smartphones using a saliency-based method. International Conference on Document Analysis and Recognition Workshops (ICDARW), Sep 2019, Sydney, Australia. pp.19--24, ⟨10.1109/ICDARW.2019.30059⟩. ⟨hal-04579610⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

More