Generation of a Skeleton Corpus of Digital Objects for the Validation and Evaluation of Format Identification Tools and Signatures.
Ross SpencerPublished in: Int. J. Digit. Curation (2013)
Keyphrases
- digital collections
- digital objects
- metadata
- digital libraries
- cultural heritage
- electronic documents
- digital content
- digital preservation
- signature recognition
- multimedia
- pdf files
- stored data
- end users
- endpoints
- complex objects
- document analysis
- binary images
- plain text
- data model
- feature selection
- model validation
- databases