Paper Info
Title
Confidence Measures for Error Correction in Interactive Transcription Handwritten Text
Abstract
An effective approach to transcribe old text documents is to follow an interactive-predictive paradigm in which both, the system is guided by the human supervisor, and the supervisor is assisted by the system to complete the transcription task as efficiently as possible. In this paper, we focus on a particular system prototype called GIDOC, which can be seen as a first attempt to provide user-friendly, integrated support for interactive-predictive page layout analysis, text line detection and handwritten text transcription. More specifically, we focus on the handwriting recognition part of GIDOC, for which we propose the use of confidence measures to guide the human supervisor in locating possible system errors and deciding how to proceed. Empirical results are reported on two datasets showing that a word error rate not larger than a 10% can be achieved by only checking the 32% of words that are recognised with less confidence.
Year
DOI
Venue
2009
10.1007/978-3-642-04146-4_61
ICIAP
Keywords
Field
DocType
particular system prototype,possible system error,interactive transcription handwritten text,interactive-predictive page layout analysis,interactive-predictive paradigm,human supervisor,confidence measure,transcription task,handwritten text transcription,text line detection,old text document,confidence measures,error correction,user interfaces,handwriting recognition,user interface,word error rate
Supervisor,Confidence measures,Pattern recognition,Computer science,Word error rate,Page layout analysis,Handwriting recognition,Error detection and correction,Speech recognition,Artificial intelligence,User interface
Conference
Volume
ISSN
Citations 
5716
0302-9743
5
PageRank 
References 
Authors
0.56
9
7
Name
Order
Citations
PageRank
Lionel Tarazón191.03
Daniel Pérez2978.91
Nicolás Serrano327732.84
Vicent Alabau49012.21
Oriol Ramos Terrades515018.36
Alberto Sanchis6737.67
alfons juan757261.45