DocumentCode
3021006
Title
Omnilingual segmentation-free word spotting for ancient manuscripts indexation
Author
Leydier, Yann ; Le Bourgeois, Frank ; Emptoz, Hubert
Author_Institution
Archimed, Villeurbanne, France
fYear
2005
fDate
29 Aug.-1 Sept. 2005
Firstpage
533
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.
Keywords
character recognition; document image processing; feature extraction; history; image matching; image segmentation; natural languages; word processing; George Washington manuscripts; Latin manuscripts; ancient manuscripts indexation; gradient feature; omnilingual segmentation-free word spotting; Character recognition; Cultural differences; Design methodology; Image coding; Image retrieval; Image segmentation; Text recognition; Transform coding; Vocabulary; Writing;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
ISSN
1520-5263
Print_ISBN
0-7695-2420-6
Type
conf
DOI
10.1109/ICDAR.2005.171
Filename
1575602
Link To Document