Omnilingual Segmentation-freeWord Spotting for Ancient Manuscripts Indexation

Authors:
Yann LEYDIER;Frank Le BOURGEOIS;Hubert EMPTOZ
Affiliations:
Archimed Lyon, 6 place Charle Hernu, 69100 Villeurbanne, France;LIRIS, 20 av. Albert Einstein, 69621 Villeurbanne, France;LIRIS, 20 av. Albert Einstein, 69621 Villeurbanne, France
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 3
Cited 3

Word Spotting: A New Approach to Indexing Handwriting

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Word Spotting in Chinese Document Images without Layout Analysis

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Features for Word Spotting in Historical Manuscripts

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1

"Inside the bible": segmentation, annotation and retrieval for a new browsing experience

MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Handwritten word-spotting using hidden Markov models and universal vocabularies

Pattern Recognition
Indexation of Syriac manuscripts using directional features

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing

Quantified Score

Hi-index	0.00

Visualization

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.