NIST · ИТ · 3b20567c50c82a3d137a
Federal Register Document Image Database 25, Volume 1
A new, fully-automated process has been developed at NIST to derive ground truth for document images. The method involves matching optical character recognition (OCR) results from a page with typesetting files for an entire book. Public domain software
NIST · ИТОфициальный источник · 1998-10-01
{
"title_en": "Federal Register Document Image Database 25, Volume 1",
"designation": "",
"series": "",
"status": "",
"date": "1998-10-01",
"date_original": "October 1, 1998",
"url": "https://www.nist.gov/publications/federal-register-document-image-database-25-volume-1",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael D. Garris , Stanley Janet , W Klein",
"abstract_excerpt_en": "A new, fully-automated process has been developed at NIST to derive ground truth for document images. The method involves matching optical character recognition (OCR) results from a page with typesetting files for an entire book. Public domain software",
"id": "3b20567c50c82a3d137a",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Federal Register Document Image Database 25, Volume 1",
"designation": "",
"series": "",
"status": "",
"date": "1998-10-01",
"date_original": "October 1, 1998",
"url": "https://www.nist.gov/publications/federal-register-document-image-database-25-volume-1",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael D. Garris , Stanley Janet , W Klein",
"abstract_excerpt_en": "A new, fully-automated process has been developed at NIST to derive ground truth for document images. The method involves matching optical character recognition (OCR) results from a page with typesetting files for an entire book. Public domain software"
}
],
"translation_state": "none"
}