Importance of Textlines in Historical Document Classification

Importance of Textlines in Historical Document Classification

Paper in proceedings (conference paper)

This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the main findings. The solved tasks include script and font classification, document origin localization, and dating. We combined patch-level and line-level approaches, where the line-level system utilizes an existing, publicly available page layout analysis engine. In both systems, neural networks provide local predictions which are combined into page-level decisions, and the results of both systems are fused using linear or log-linear interpolation. We propose loss functions suitable for weakly supervised classification problem where multiple possible labels are provided, and we propose loss functions suitable for interval regression in the dating task. The line-level system significantly improves results in script and font classification and in the dating task. The full system achieved 98.48%, 88.84%, and 79.69% accuracy in the font, script, and location classification tasks respectively. In the dating task, our system achieved a mean absolute error of 21.91 years. Our system achieved the best results in all tasks and became the overall winner of the competition.

This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the main findings. The solved tasks include script and font classification, document origin localization, and dating. We combined patch-level and line-level approaches, where the line-level system utilizes an existing, publicly available page layout analysis engine. In both systems, neural networks provide local predictions which are combined into page-level decisions, and the results of both systems are fused using linear or log-linear interpolation. We propose loss functions suitable for weakly supervised classification problem where multiple possible labels are provided, and we propose loss functions suitable for interval regression in the dating task. The line-level system significantly improves results in script and font classification and in the dating task. The full system achieved 98.48%, 88.84%, and 79.69% accuracy in the font, script, and location classification tasks respectively. In the dating task, our system achieved a mean absolute error of 21.91 years. Our system achieved the best results in all tasks and became the overall winner of the competition.

Historical document classification, Script and font classification, Document origin localization, Document dating.

Historical document classification, Script and font classification, Document origin localization, Document dating.

KIŠŠ, M.; KOHÚT, J.; BENEŠ, K.; HRADIŠ, M.

2023

18.05.2022

Springer Nature Switzerland AG

La Rochelle

978-3-031-06554-5

Uchida, S., Barney, E., Eglin, V. (eds) Document Analysis Systems

Lecture Notes in Computer Science

13237

158

170

13

https://pero.fit.vutbr.cz/publications