This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the main findings.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.
翻译:本文介绍了布尔诺理工大学为ICDAR 2021历史文件分类竞赛准备的系统、导致其设计的实验以及主要结论。 已经解决的任务包括脚本和字体分类、文件源本地化和约会。 我们将补丁和线级方法结合起来, 线级系统使用现有公开的页面布局分析引擎。 在这两个系统中, 神经网络提供地方预测, 并结合到页级决定中, 两种系统的结果都使用线性或线性线性内插法结合。 我们建议了适合低监管分类问题的损失功能, 在提供多种可能标签的情况下, 我们提出适合低监管分类问题的丢失功能, 我们提出适合约会任务中间隔回归的损失功能。 线级系统极大地改进了脚本和字体分类以及约会任务的结果。 整个系统分别实现了98.48%、88.84%和79.69%的字体、脚本和地点分类任务的准确度。 在约会任务中, 我们的系统在21.91年中取得了最差的绝对错误。 我们的系统在所有任务中都取得了最佳的结果, 并且成为了竞争的总赢家。