{"url":"/dataset/diva-hisdb","name":"DIVA-HisDB","full_name":null,"description_markdown":"The database consists of 150 annotated pages of three different medieval manuscripts with challenging layouts. Furthermore, we provide a layout analysis ground-truth which has been iterated on, reviewed, and refined by an expert in medieval studies.","description_withheld":null,"homepage":"https://diuf.unifr.ch/main/hisdoc/diva-hisdb","introduced_date":"2016-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/diva-hisdb-a-precisely-annotated-large","title":"DIVA-HisDB: A Precisely Annotated Large Dataset of Challenging Medieval Manuscripts","first_author":"Fotini Simistira","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Document Layout Analysis","url":"/task/document-layout-analysis","datasets_with_task":"/datasets/task/document-layout-analysis"},{"name":"Text-Line Extraction","url":"/task/text-line-extraction","datasets_with_task":"/datasets/task/text-line-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DIVA-HisDB"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-diva-hisdb","task":"Semantic Segmentation","dataset_variant":"DIVA-HisDB","rows":3,"metrics":["Mean IoU (class)"],"first_row_in_archive_order":{"model":"U-Net","paper":"/paper/diva-daf-a-deep-learning-framework-for","metrics":{"Mean IoU (class)":"97.26"},"code_links":[{"title":"DIVA-DIA/DIVA-DAF","url":"https://github.com/DIVA-DIA/DIVA-DAF"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-line-extraction-on-diva-hisdb","task":"Text-Line Extraction","dataset_variant":"DIVA-HisDB","rows":1,"metrics":["Line IoU","Pixel IoU"],"first_row_in_archive_order":{"model":"Semantic Seg Preprocessing","paper":"/paper/labeling-cutting-grouping-an-efficient-text","metrics":{"Line IoU":"99.42","Pixel IoU":"96.11"},"code_links":[{"title":"DIVA-DIA/Text-Line-Segmentation-Method-for-Medieval-Manuscripts","url":"https://github.com/DIVA-DIA/Text-Line-Segmentation-Method-for-Medieval-Manuscripts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/few-shot-pixel-precise-document-layout","title":"Few-shot pixel-precise document layout segmentation via dynamic instance generation and local thresholding","date":"2023-08-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-few-shot-learning-for-pixel-precise","title":"Efficient few-shot learning for pixel-precise handwritten document layout analysis","date":"2022-10-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diva-daf-a-deep-learning-framework-for","title":"DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis","date":"2022-01-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/labeling-cutting-grouping-an-efficient-text","title":"Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts","date":"2019-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}