Classification of incunable glyphs and out-of-distribution detection with joint energy-based models
Classification of incunable glyphs and out-of-distribution detection with joint energy-based models
复制标题
DOI：
10.1007/s10032-023-00442-x
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Florian Kordon;Nikolaus Weichselbaumer;Randall Herz;Stephen Mossman;Edward Potten;Mathias Seuret;Martin Mayr;Vincent Christlein
中科院分区：
文献类型：
--
作者：
Florian Kordon;Nikolaus Weichselbaumer;Randall Herz;Stephen Mossman;Edward Potten;Mathias Seuret;Martin Mayr;Vincent Christlein
光学字符识别（OCR）已被证明是一个强大的工具，用于数字分析印刷的历史文件。然而，它定位和识别单个字形的能力受到历史字体设计、印刷过程的物理性和保护状态的巨大变化的挑战。我们建议通过下游微调步骤来缓解这些问题，该步骤校正病理和不期望的提取结果。我们通过使用一个联合的基于能量的模型来实现这个想法，该模型对单个字形进行分类，同时修剪潜在的分布外（OOD）样本，如rubrications，缩写或连字。在模型训练过程中，我们在能量谱中引入特定的余量来帮助这种分离，并探索能量分布的典型集合来稳定优化过程。我们观察到强大的分类在0.972 AUPRC在42个较低和较低的类型上的挑战性的数字再现约翰内斯·巴尔布斯的Catholicon，匹配的性能，纯粹的歧视性的方法。同时，我们实现了OOD检测率为0.989 AUPRC和0.946 AUPRC的OOD“杂波”和“连字”，这大大提高了最近提出的OOD检测技术。所提出的方法可以很容易地集成到当前OCR的后处理阶段，以帮助再现和形状分析研究。
Optical character recognition (OCR) has proved a powerful tool for the digital analysis of printed historical documents. However, its ability to localize and identify individual glyphs is challenged by the tremendous variety in historical type design, the physicality of the printing process, and the state of conservation. We propose to mitigate these problems by a downstream fine-tuning step that corrects for pathological and undesirable extraction results. We implement this idea by using a joint energy-based model which classifies individual glyphs and simultaneously prunes potential out-of-distribution (OOD) samples like rubrications, initials, or ligatures. During model training, we introduce specific margins in the energy spectrum that aid this separation and explore the glyph distribution’s typical set to stabilize the optimization procedure. We observe strong classification at 0.972 AUPRC across 42 lower- and uppercase glyph types on a challenging digital reproduction of Johannes Balbus’Catholicon, matching the performance of purely discriminative methods. At the same time, we achieve OOD detection rates of 0.989 AUPRC and 0.946 AUPRC for OOD ‘clutter’ and ‘ligatures’ which substantially improves upon recently proposed OOD detection techniques. The proposed approach can be easily integrated into the postprocessing phase of current OCR to aid reproduction and shape analysis research.