Vahid Rezanezhad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vahid Rezanezhad has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Clemens Neudecker
Berlin State Library, Germany
3 shared publications - Konstantin Baierer
Berlin State Library, Germany
3 shared publications Doris \V{S}Kari\'{C
1 shared publication- Doris Škarić
Department for Information and Data Management Berlin State Library Berlin Germany
1 shared publication J\Org Lehmann
1 shared publication- Kai Labusch
Berlin State Library, Germany
1 shared publication
Latest Publications
- Open Access
- 21 November 2025
- Published by The Association for Computers and the Humanities
- Vol. 3, 1285-1309
How Scalable is Quality Assessment of Text Recognition? A Combination of Ground Truth and Confidence Scores
Vast amounts of historical documents are being digitized with subsequent optical character recognition (OCR), but the quality assessment of the results is challenging for larger quantities. Ground Truth-based evaluation requires sufficient and representative data that are expensive to create. Following recent work, we investigate whether confidence scores automatically provided by text recognition systems can serve as a proxy. Based on an analysis of the relationship between word error rates and word confidence scores for several OCR engines, we find that the latter can serve as a useful indicator of OCR quality. In a second step, we explore the scalability and reliability of combining Ground Truth and confidence scores for quality assessment of text recognition in several experiments on a heterogeneous dataset comprising almost 5 million pages of historical documents from 1456–2000. The deeper analysis of the evaluation results provides insights into typical issues for OCR of historical documents, suggesting potential directions for future work.
- 21 November 2025
- Published by The Association for Computers and the Humanities
- Vol. 3, 1285-1309
Open AccessHow Scalable is Quality Assessment of Text Recognition? A Combination of Ground Truth and Confidence Scores
Vast amounts of historical documents are being digitized with subsequent optical character recognition (OCR), but the quality assessment of the results is challenging for larger quantities. Ground Truth-based evaluation requires sufficient and representative data that are expensive to create. Following recent work, we investigate whether confidence scores automatically provided by text recognition systems can serve as a proxy. Based on an analysis of the relationship between word error rates and word confidence scores for several OCR engines, we find that the latter can serve as a useful indicator of OCR quality. In a second step, we explore the scalability and reliability of combining Ground Truth and confidence scores for quality assessment of text recognition in several experiments on a heterogeneous dataset comprising almost 5 million pages of historical documents from 1456–2000. The deeper analysis of the evaluation results provides insights into typical issues for OCR of historical documents, suggesting potential directions for future work.
- Open Access
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 73-78
Document Layout Analysis with Deep Learning and Heuristics
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 73-78
Open AccessDocument Layout Analysis with Deep Learning and Heuristics
- Open Access
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 79-84
A hybrid CNN-Transformer model for Historical Document Image Binarization
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 79-84
Open AccessA hybrid CNN-Transformer model for Historical Document Image Binarization