Efficient indexing for Query by String text retrieval

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

11 Cites (Scopus)

Resum

This paper deals with Query By String word spotting in scene images. A hierarchical text segmentation algorithm based on text specific selective search is used to find text regions. These regions are indexed per character n-grams present in the text region. An attribute representation based on Pyramidal Histogram of Characters (PHOC) is used to compare text regions with the query text. For generation of the index a similar attribute space based Pyramidal Histogram of character n-grams is used. These attribute models are learned using linear SVMs over the Fisher Vector [1] representation of the images along with the PHOC labels of the corresponding strings.

Idioma originalAnglès
Títol de la publicació13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
Pàgines1236-1240
Nombre de pàgines5
ISBN (electrònic)9781479918058
DOIs
Estat de la publicacióPublicada - 20 de nov. 2015

Sèrie de publicacions

NomProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volum2015-November
ISSN (imprès)1520-5363

Fingerprint

Navegar pels temes de recerca de 'Efficient indexing for Query by String text retrieval'. Junts formen un fingerprint únic.

Com citar-ho