An open-source OCR evaluation tool
Author:
Open Access
- 19 May 2014
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 179-184
Abstract
This paper describes an open-source tool which computes statistics of the differences between a reference text an the output of an OCR engine. It also facilitates the spotting of mismatches by generating an aligned bitext where the differences are highlighted and cross linked. The tool accepts a variety of input formats (both for the reference and the OCR) and can also be also used to compare the output of two different OCR engines. Some considerations on the criteria to compare the textual content of two files, at character and word level, are also discussed here.Keywords
This publication has 8 references indexed in Scilit:
- The Significance of Reading Order in Document Recognition and Its Evaluation2013
- ICDAR 2013 Competition on Historical Book Recognition (HBR 2013)2013
- The PAGE (Page Analysis and Ground-Truth Elements) Format Framework2010
- A comprehensive evaluation methodology for noisy historical document recognition techniques2009
- Measuring Mass Text Digitization Quality and UsefulnessD-Lib Magazine, 2009
- A geometric approach for accurate and efficient performance evaluation of layout analysis methods2008
- Automated evaluation of OCR zoningIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
- The String-to-String Correction ProblemJournal of the ACM, 1974