[Dataset] A dataset for 19th-century French land registry pages classification

Initial registers pages classification dataset overview This dataset is prepared to train classification models for French 19th-century land registry pages. It deals only with initial registers pages (états de sections in French). Images have been provided by the Val de Marne Archive and they can be associated with two former French departements : the Seine and the Seine-et-Oise (departements that were rounded Paris before 1968). There are three main layouts in these registers which are presents here. The dataset counts 1016 pages and has been split into training, validation, and test sets with stratification based on the type of page. It is structured according to YOLO Classification format. The metadata file gives more information on the pages. 📊 Dataset Splits | Split | Size ||--------|------|| Train | 745 || Val | 123 || Test | 148 | --- 🔠 Stratification by type of page Train Set | Class | Count ||--------------------|-------|| ets_tab_p1 | 413 || ets_recap_inter | 198 || ets_tab_p2 | 89 || ets_resume | 30 || ets_couv | 15 | Validation Set | Class | Count ||--------------------|-------|| ets_tab_p1 | 57 || ets_recap_inter | 38 || ets_tab_p2 | 22 || ets_resume | 3 || ets_couv | 3 | Test Set | Class | Count ||--------------------|-------|| ets_tab_p1 | 86 || ets_tab_p2 | 30 || ets_recap_inter | 27 || ets_resume | 4 || ets_couv | 1 | --- 🏙️ Grouped by municipality Communes are distinct across splits (useful to test geographic generalization), as land registry were produced for each municipality under the supervision of each departement. Train Set - VINCENNES : 76- IVRY : 72- GENTILLY : 68- VITRY : 60- LEPLESSIS : 52- SAINTMANDE : 48- NOGENT : 40- LHAY : 31- BRY : 28- JOINVILLE : 28- LEPERREUX : 24- ORMESSON : 24- MAROLLES : 24- MAISONSALFORT : 20- FRESNES : 20- CHARENTON : 20- CHOISY : 16- VILLIERS : 16- SAINTMAURICE : 12- VALENTON : 12- CRETEIL : 10- FONTENAY : 8- SANTENY : 8- SUCY : 8- VILLENEUVESTG : 8- BONNEUIL : 8- CHEVILLY : 4 Validation Set - VILLEJUIF: 24- ARCUEIL: 20- RUNGIS: 20- MANDRES: 16- PERIGNY: 16- VILLECRESNES: 12- SAINTMAUR: 11- CHAMPIGNY: 4 Test Set - ALFORTVILLE: 32- ORLY: 32- VILLENEUVELEROI: 24- THIAIS: 16- BOISSY: 12- LIMEIL: 12- NOISEAU: 12- ABLON: 8 --- 🎨 Color Distribution Indication on digitisation color of the images| Split | COLOR | GREY ||--------|-------|------|| Train | 473 | 272 || Val | 40 | 83 || Test | 64 | 84 | --- 📁 Usage This dataset is intended for training a YOLO-v11 classification model. ---