Omnilingual Segmentation-freeWord Spotting for Ancient Manuscripts Indexation

Abstract : This article introduces a new word spotting method designed for ancient manuscripts. We take advantage of the robustness of the gradient feature and propose a new segmentation-free matching algorithm that tolerates spatial variations. We test our algorithm on ancient Latin manuscripts and on George Washington's manuscripts.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01592821
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Monday, September 25, 2017 - 2:30:04 PM
Last modification on : Wednesday, October 31, 2018 - 12:24:07 PM

Identifiers

Citation

Yann Leydier, Frank Le Bourgeois, Hubert Emptoz. Omnilingual Segmentation-freeWord Spotting for Ancient Manuscripts Indexation. 8th International Conference on Document Analysis and Recognition, ICDAR'05, Aug 2005, Séoul, South Korea. pp.533-537, ⟨10.1109/ICDAR.2005.171⟩. ⟨hal-01592821⟩

Share

Metrics

Record views

110