论文标题
文本线在历史文档分类中的重要性
Importance of Textlines in Historical Document Classification
论文作者
论文摘要
本文介绍了BRNO技术大学为ICDAR 2021竞赛的历史文档分类竞赛，导致其设计的实验以及主要发现的系统。解决的任务包括脚本和字体分类，文档原始本地化和约会。我们结合了补丁级和线路级别的方法，在该方法中，线路级系统利用现有的公开页面布局分析引擎。在这两个系统中，神经网络都提供了局部预测，这些预测合并为页面级决策，并且使用线性或对数线性插值融合了两个系统的结果。我们提出适用于提供多个可能标签的弱监督分类问题的损失功能，我们提出适合于约会任务中间隔回归的损失功能。线路级系统可显着改善脚本和字体分类和约会任务的结果。整个系统在字体，脚本和位置分类任务中分别达到了98.48％，88.84％和79.69％的精度。在约会任务中，我们的系统达到了21.91年的平均绝对误差。我们的系统在所有任务中都取得了最佳成果，并成为了比赛的总体冠军。
This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the main findings.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.
