Title: (Standard Data Acquisition Process) - A standardised and optimised process for data acquisition from digital images of herbarium specimens

Funded by: DFG German Research Foundation, Literaturversorgung und Information / Erschließung und Digitalisierung, Call: Standardbildung zur Erschließung und / oder Digitalisierung von Objektgattungen in wissenschaftlichen Sammlungen

Duration: 3 Years (from July 2014)

Aim: The project develops and documents a software-driven standard process for extracting metadata from images of herbarium specimens

Summary: On herbarium sheets, data like plant name, collection site, collector, barcode, accession number, etc. are found mostly on labels glued on the sheet. The data is thus visible on images taken from the specimen. Currently, they are entered manually into collection databases. The StanDAP-Herb Project funded by the DFG (German Research Foundation) develops a standard process for (semi-) automatic detection of meta-data on Herbarium specimens to replace the time consuming manual data input as much as possible. Image processing and other software detects objects such as labels or barcodes on the digitized record and classifies them. Text objects are transformed into structured information using text mining algorithms. For handwriting, author identification is attempted. The project evaluates and enhances existing software to comply with standard interfaces and integrates them into an open software architecture based on established IT standards. The software modules thus become available for work flow processing, in order to verify data quality, facilitate data discovery and enhance the application of collection data in research. The project addresses a large proportion of scientific collections: approximately 22 million herbarium specimens exist as botanical reference objects in Germany, about 500 million worldwide.