Handwritting Keyword Indexing and Search
PRHLT Demonstrators

Laboratory, small & medium-scale datasets (many with ground truth):

Various collections indexed together



Jane Austen


La contienda (HMMs)

Lope and the Spanish Theatre Golden Age (OLD)

Passau miscellaneous collection

Chancery-Guerin (95 Acts, with GT)

Chancery-Guerin (444 Acts, without GT)

Chancery-Guerin lemmatized (444 Acts, without GT)

Handwritten music symbol indexing and symbol-sequence search:

Vorau-253 Music manuscript(490 page images, 44 with partial GT)

Large scale (no ground truth):

Chancery (Tr´esor des Chartes registers -- 199 manuscripts, 82,000 page images)

Bentham papers (193 boxes, 90,000 page images)

Teatro del Siglo de Oro (Spanish Golden Eage Theatre -- 328 manuscripts 41,000 page images)