A Reproducible Multimodal AI Workflow for Improving Discovery in Historical Digital Archives: OCR Correction, Visual Classification, and Metadata Enrichment

Historical digital archives are increasingly searchable, but discovery remains limited when OCR errors, visually heterogeneous document types, and sparse metadata are handled separately. This study aimed to provide a reproducible protocol for evaluating whether a conservative multimodal workflow can improve archival retrieval without replacing archivist review. A corpus of 1,600 digitized archival records from eight document classes was assembled, and a 420-query benchmark was used to compare five retrieval conditions: baseline indexing, OCR correction alone, visual classification alone, metadata enrichment alone, and full multimodal integration. Record-level outcomes included character error rate (CER), word error rate (WER), named-entity recall, document-type classification accuracy, prediction confidence, metadata completeness, and subject-heading match. Query-level outcomes included P@10, R@10, nDCG@10, time to first relevant result, and successful-search rate. OCR correction reduced WER most strongly for handwritten letters, ledgers, and registry books; visual fine-tuning improved classification accuracy most for maps, posters, newspapers, and registry books; and metadata enrichment increased completeness across all historical periods. The full multimodal condition achieved the highest retrieval performance (P@10 = 0.624, R@10 = 0.492, nDCG@10 = 0.634) and reduced mean time to first relevant result from 156.079 s to 58.485 s. These results support a modular, auditable workflow in which text, image, and descriptive signals are combined under explicit thresholds and human review.