Exploiting Existing Modern Transcripts for Historical Handwritten Text Recognition
Authors:
- Mauricio VillegasMVMauricio Villegas
- Alejandro H. ToselliATAlejandro H. Toselli
- Veronica RomeroVRVeronica Romero
- Enrique VidalEVEnrique Vidal
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21676445,p. 66-71
Abstract
Existing transcripts for historic manuscripts are a very valuable resource for training models useful for automatic recognition, aided transcription, and/or indexing of the remaining untranscribed parts of these collections. However, these existing transcripts generally exhibit two main problems which hinder their convenience: a) text of the transcripts is seldom aligned with manuscript lines, and b) text often deviate very significantly from what can be seen in the manuscript, either because writing style has been modernized or abbreviations have been expanded, or both. This work presents an analysis of these problems and discusses possible solutions for minimizing human effort needed to adapt existing transcripts in order to render them usable. Empirical results presented show the huge performance gain that can be obtained by adequately adapting the transcripts, thus motivating future development of the proposed solutions.Keywords
This publication has 10 references indexed in Scilit:
- Handwriting Transcription and Keyword Spotting in Historical Daily Records Documents2016
- On the Modification of Binarization Algorithms to Retain Grayscale Information for Handwritten Text Recognition2015
- Handwritten text recognition for historical documents in the transcriptorium project2014
- Moment-Based Image Normalization for Handwritten Text Recognition2012
- Multimodal Interactive Handwritten Text Transcription2012
- Alignment between Text Images and their Transcripts for Handwritten Documents2011
- Multimodal interactive transcription of text imagesPattern Recognition, 2010
- A new interpretation of average precision2008
- Introduction to Information Retrieval2008
- INTEGRATED HANDWRITING RECOGNITION AND INTERPRETATION USING FINITE-STATE MODELSInternational Journal of Pattern Recognition and Artificial Intelligence, 2004