We propose a novel procedure to speed-up the content transcription of handwritten documents in digital historical archives when a keyword spotting system is used for the purpose. Instead of performing the validation of the system outputs in a single step, as it is customary, the proposed methodology envisaged a multi-step validation process to be embedded into a human-in-the-loop approach. At each step, the system outputs are validated and, whenever an image word that does not correspond to any entry of the keyword list is mistakenly returned by the system, its correct transcription is entered and used to query the system in the next step. The performance of our approach has been experimentally evaluated in terms of the total time to achieve the complete transcription of a subset of documents from the Bentham dataset. The results confirm that interleaving keyword spotting by the system and validation by the user leads to a significant reduction of the time required to transcribe the document content with respect to both the manual transcription and the traditional end-of-the-loop validation process.

A novel procedure to speed up the transcription of historical handwritten documents by interleaving keyword spotting and user validation

Adolfo Santoro
;
Angelo Marcelli
2019

Abstract

We propose a novel procedure to speed-up the content transcription of handwritten documents in digital historical archives when a keyword spotting system is used for the purpose. Instead of performing the validation of the system outputs in a single step, as it is customary, the proposed methodology envisaged a multi-step validation process to be embedded into a human-in-the-loop approach. At each step, the system outputs are validated and, whenever an image word that does not correspond to any entry of the keyword list is mistakenly returned by the system, its correct transcription is entered and used to query the system in the next step. The performance of our approach has been experimentally evaluated in terms of the total time to achieve the complete transcription of a subset of documents from the Bentham dataset. The results confirm that interleaving keyword spotting by the system and validation by the user leads to a significant reduction of the time required to transcribe the document content with respect to both the manual transcription and the traditional end-of-the-loop validation process.
978-1-7281-3014-9
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11386/4729217
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact