- -

Lexicon-based probabilistic indexing of handwritten text images

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Lexicon-based probabilistic indexing of handwritten text images

Mostrar el registro sencillo del ítem

Ficheros en el ítem

dc.contributor.author Vidal, Enrique es_ES
dc.contributor.author Toselli, Alejandro Héctor es_ES
dc.contributor.author Puigcerver, Joan es_ES
dc.date.accessioned 2024-05-31T18:17:35Z
dc.date.available 2024-05-31T18:17:35Z
dc.date.issued 2023-08 es_ES
dc.identifier.issn 0941-0643 es_ES
dc.identifier.uri http://hdl.handle.net/10251/204629
dc.description.abstract [EN] Keyword Spotting (KWS) is here considered as a basic technology for Probabilistic Indexing (PrIx) of large collections of handwritten text images to allow fast textual access to the contents of these collections. Under this perspective, a probabilistic framework for lexicon-based KWS in text images is presented. The presentation aims at providing formal insights which help understanding classical statements of KWS (from which PrIx borrows fundamental concepts), as well as the relative challenges entailed by these statements. The development of the proposed framework makes it clear that word recognition or classification implicitly or explicitly underlies any formulation of KWS. Moreover, it suggests that the same statistical models and training methods successfully used for handwriting text recognition can advantageously be used also for PrIx, even though PrIx does not generally require or rely on any kind of previously produced image transcripts. Experiments carried out using these approaches support the consistency and the general interest of the proposed framework. Results on three datasets traditionally used for KWS benchmarking are significantly better than those previously published for these datasets. In addition, good results are also reported on two new, larger handwritten text image datasets (Bentham and Plantas), showing the great potential of the methods proposed in this paper for indexing and textual search in large collections of untranscribed handwritten documents. Specifically, we achieved the following Average Precision values: IAMDB: 0.89, George Washington: 0.91, Parzival: 0.95, Bentham: 0.91 and Plantas: 0.92. es_ES
dc.description.sponsorship Work partially supported by ValgrAI-Valencian Graduate School and Research Network of Artificial Intelligence (Generalitat Valenciana) co-funded by the European Union; and by a Maria Zambrano grant of the Spanish Ministerio de Universidades and the European Union NextGenerationEU/PRTR. es_ES
dc.language Inglés es_ES
dc.publisher Springer-Verlag es_ES
dc.relation.ispartof Neural Computing and Applications es_ES
dc.rights Reconocimiento (by) es_ES
dc.subject Pattern recognition es_ES
dc.subject Posteriorgram es_ES
dc.subject Relevance probability es_ES
dc.subject Hidden Markov model es_ES
dc.subject Recurrent neural network es_ES
dc.subject Handwritten text analysis and recognition es_ES
dc.subject Keyword spotting es_ES
dc.subject Large-scale indexing and search es_ES
dc.title Lexicon-based probabilistic indexing of handwritten text images es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1007/s00521-023-08620-y es_ES
dc.rights.accessRights Abierto es_ES
dc.description.bibliographicCitation Vidal, E.; Toselli, AH.; Puigcerver, J. (2023). Lexicon-based probabilistic indexing of handwritten text images. Neural Computing and Applications. 35(24):17501-17520. https://doi.org/10.1007/s00521-023-08620-y es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.1007/s00521-023-08620-y es_ES
dc.description.upvformatpinicio 17501 es_ES
dc.description.upvformatpfin 17520 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 35 es_ES
dc.description.issue 24 es_ES
dc.relation.pasarela S\497255 es_ES
dc.contributor.funder European Commission es_ES
dc.contributor.funder Universitat Politècnica de València es_ES
dc.contributor.funder Valencian Graduate School and Research Network of Artificial Intelligence es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem