Saltar a la navegació principal Saltar a la cerca Vés al contingut principal

Can one deep learning model learn script-independent multilingual word-spotting?

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

Resum

Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.

Idioma originalAnglès
Títol de la publicacióProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Pàgines260-267
Nombre de pàgines8
ISBN (electrònic)9781728128610
DOIs
Estat de la publicacióPublicada - de set. 2019

Sèrie de publicacions

NomProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (imprès)1520-5363

Fingerprint

Navegar pels temes de recerca de 'Can one deep learning model learn script-independent multilingual word-spotting?'. Junts formen un fingerprint únic.

Com citar-ho