

















Abstract:Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)
| Comments: | 69 pages, 68 figures, 30 tables. Master's thesis |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| MSC classes: | 68T10, 68T09, 62H30 |
| ACM classes: | I.7.5; H.3.7 |
| Cite as: | arXiv:2507.21114 [cs.IR] |
| (or arXiv:2507.21114v4 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2507.21114 arXiv-issued DOI via DataCite |
From: Kateryna Lutsai Bc [view email]
[v1]
Fri, 11 Jul 2025 08:30:12 UTC (46,637 KB)
[v2]
Thu, 19 Mar 2026 14:03:08 UTC (49,951 KB)
[v3]
Sat, 2 May 2026 14:20:19 UTC (49,954 KB)
[v4]
Mon, 25 May 2026 08:19:39 UTC (49,954 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。