Uporedite metode

	Handwritten Text Recognition for Archives	Historical GIS
Oblast	Digital History	Historical Geography
Porodica	Machine learning	Process / pipeline
Godina nastanka	2019	2007
Tvorac	Transkribus and the READ project	Ian Gregory and Paul Ell
Tip	ml-recognition-pipeline	spatial-analysis-pipeline
Temeljni izvor	Muehlberger, G., Seaward, L., Terras, M., et al. (2019). Transforming scholarship in the archives through handwritten text recognition: Transkribus as a case study. Journal of Documentation, 75(5), 954-976.	Gregory, I. N., & Ell, P. S. (2007). Historical GIS: Technologies, Methodologies, and Scholarship. Cambridge University Press. ISBN: 9780521855631
Drugi nazivi	HTR, Manuscript transcription AI, Automatic handwriting transcription, Neural archival transcription	HGIS, Spatial history, Geohistorical information systems, Time-aware historical GIS
Srodne	3	3
Sažetak	Handwritten text recognition for archives converts digital images of manuscript pages into searchable, machine-readable text, unlocking the vast holdings of handwritten material that optical character recognition, designed for print, cannot read. Exemplified by platforms such as Transkribus, developed in the READ project, modern HTR uses deep neural networks trained on transcribed examples to recognize the highly variable scripts of letters, registers, charters, and notebooks across centuries and languages. The pipeline first analyzes page layout and segments the image into text regions and lines, then a recurrent or transformer-based recognizer decodes each line into characters, typically using connectionist temporal classification to align pixels with text without needing character-level segmentation. Crucially, recognition models are trained and improved on ground-truth transcriptions supplied by scholars, so accuracy rises as more material is annotated. By making manuscripts machine-readable at scale, HTR is the gateway technology of digital archival history, feeding full-text search, named-entity recognition, and large-corpus text mining of sources that were previously legible only page by page.	Historical GIS brings the spatial-analytic power of geographic information systems to the study of the past, building databases in which historical places, boundaries, and phenomena are tied to coordinates and to the dates at which they held. Systematized in Ian Gregory and Paul Ell's foundational treatment, the approach addresses a problem ordinary GIS ignores: the geography of the past was not fixed. Administrative units split and merged, borders shifted, towns rose and vanished, so a historical GIS must represent geometry that changes through time. Researchers georeference old maps, digitize past boundaries, encode places in gazetteers, and link tabular historical data, censuses, tax rolls, trade figures, to these time-varying geographies. The result supports genuinely spatial questions: how phenomena were distributed, how patterns clustered or diffused, how distance and terrain shaped historical life. It operationalizes the Annales attention to geography as a force in history, letting scholars map and measure the spatial structures within which past societies acted.