Home

PAGE XML

PAGE (Page Analysis and Ground Truth Elements) is a collection of XML formats, developed and maintained by the PRImA Research Lab at the University of Salford, UK.

See also: http://www.primaresearch.org/tools/PAGELibraries http://www.primaresearch.org/publications/ICPR2010_Pletschacher_PAGE

The most actively used XML formats are:

• PAGE XML for page content (regions, text lines, words, glyphs, reading order, text content, ...)
• PAGE XML for layout analysis evaluation (evaluation profiles, evaluation results, ...)
• PAGE XML for document image dewarping (dewarping grids)

All formats are defined by an XML schema, hosted officially on primaresearch.org: http://www.primaresearch.org/schema/PAGE/gts/pagecontent/2018-07-15/pagecontent.xsd http://www.primaresearch.org/schema/PAGE/eval/layout/2013-07-15/layouteval.xsd http://www.primaresearch.org/schema/PAGE/gts/dewarping/2014-08-26/dewarping.xsd

Documentation on each schema can be found in the respective folders in this GitHub repository.