Fisher kernels for handwritten word-spotting

Florent Perronnin, Jose A. Rodriguez-Serrano

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

35 Cites (Scopus)


The Fisher kernel is a generic framework which combines the benefits of generative and discriminative approaches to pattern classification. In this contribution, we propose to apply this framework to handwritten word-spotting. Given a word image and a keyword generative model, the idea is to generate a vector which describes how the parameters of the keyword model should be modified to best fit the word image. This vector can then be used as the input of a discriminative classifier. We compare the performance of the proposed approach with that of a generative baseline on a challenging real-world dataset of customer letters. When the kernel used by the classifier is linear, the performance improvement is marginal but the proposed system is approximately 15 times faster than the baseline. If we use a non-linear kernel devised for this task, we obtain a 15% relative reduction of the error but the detector is approximately 15 times slower.

Idioma originalAnglès
Títol de la publicacióICDAR2009 - 10th International Conference on Document Analysis and Recognition
Nombre de pàgines5
Estat de la publicacióPublicada - 2009
Publicat externament
EsdevenimentICDAR2009 - 10th International Conference on Document Analysis and Recognition - Barcelona, Spain
Durada: 26 de jul. 200929 de jul. 2009

Sèrie de publicacions

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


ConferènciaICDAR2009 - 10th International Conference on Document Analysis and Recognition


Navegar pels temes de recerca de 'Fisher kernels for handwritten word-spotting'. Junts formen un fingerprint únic.

Com citar-ho