Skip to ContentSkip to Navigation
Over onsNieuws en agendaNieuwsberichten

NWO grant for designing pattern-recognition algorithm

29 januari 2014

Prof. Lambert Schomaker (ALICE institute) obtained a NWO grant of EUR 400,000 in the 'Digging into Data' round with a joint proposal by McGill University (Montreal), Stanford University (USA) and Ecole de technologie supérieure (Montréal). ALICE’s task in this project is the design of pattern-recognition algorithms for the induction of semantic concepts from historical document images.

Apart from text itself, there is a wealth of visual information available on each of the scans: author markings, illuminated capitals, schematic drawings, special symbols and glyphs that can give an insight into the underlying meaning and provenance of a piece of text. Data mining allows for tracing 'visual memes' over networks of authors. In this project ALICE will apply and extend the knowledge that has been developed in the Monk system for googling in large historical manuscript image collections.

NWO granted 6 projects in total in the 'Digging into Data' round.

More information:

Project website

Prof. L.R.B. Schomaker

Drawings and diagrams in historical documents are usually related to the surrounding words. This text is about bubbles, 'bullae'. There is a relation between that word and the round shape of the diagram. There are other related words such as 'forma circulari' (see manually annotated version on the right).
Drawings and diagrams in historical documents are usually related to the surrounding words. This text is about bubbles, 'bullae'. There is a relation between that word and the round shape of the diagram. There are other related words such as 'forma circulari' (see manually annotated version on the right).
Modern methods of pattern recognition and machine learning allow to relate the visual and textual elements. (Example from letter by Gisbert Cuper (1674), Royal Library (The Hague), ms. 72 C 18, f. 20 recto, courtesy of dr. Jetze Touber).
Modern methods of pattern recognition and machine learning allow to relate the visual and textual elements. (Example from letter by Gisbert Cuper (1674), Royal Library (The Hague), ms. 72 C 18, f. 20 recto, courtesy of dr. Jetze Touber).
Laatst gewijzigd:01 februari 2017 00:45

Meer nieuws