Menu

Document processing

What EDS has read from each document, how it read it, and where it refused.

Demonstration project - no figure here describes a real facilityChanges are not saved
Why

Each row is the document's recorded processing state and the readings actually held against it. No job is running: there is no worker in this environment.

Writes are validated against the engineering rules and then refused, because no database has been configured for this environment.

Documents read

22

Not yet read

2

Refused

1

Pages read

23

Readings held

131

Nothing is running

No worker in this environment. Each row is a recorded state.

Per document

Document processing state
DocumentRead byPagesState
ZRF-PID-1201native_text
ZRF-PID-1201 pages1 of 1
Read
ZRF-PID-1202native_text
ZRF-PID-1202 pages1 of 1
Read
ZRF-PID-1101ocr
ZRF-PID-1101 pages1 of 1
Read
ZRF-PID-3101both
ZRF-PID-3101 pages1 of 1
Read
ZRF-PID-3201native_text
ZRF-PID-3201 pages1 of 1
Read
ZRF-PFD-1200native_text
ZRF-PFD-1200 pages1 of 1
Read
ZRF-PFD-1100native_text
ZRF-PFD-1100 pages1 of 1
Read
ZRF-SLD-6001native_text
ZRF-SLD-6001 pages1 of 1
Read
ZRF-DS-P-1201Anative_text
ZRF-DS-P-1201A pages1 of 1
Read
ZRF-DS-PT-1201native_text
ZRF-DS-PT-1201 pages1 of 1
Read
ZRF-DS-PSV-1210native_text
ZRF-DS-PSV-1210 pages1 of 1
Read
ZRF-REG-EQ-001structured
ZRF-REG-EQ-001 pagesprogress not measurable
Read
ZRF-REG-LL-001structured
ZRF-REG-LL-001 pagesprogress not measurable
Read
ZRF-REG-II-001structured
ZRF-REG-II-001 pagesprogress not measurable
Read
ZRF-REG-VR-001structured
ZRF-REG-VR-001 pagesprogress not measurable
Read
ZRF-REG-CS-001structured
ZRF-REG-CS-001 pagesprogress not measurable
Read
ZRF-REG-MDR-001structured
ZRF-REG-MDR-001 pagesprogress not measurable
Read
ZRF-SPC-3300native_text
ZRF-SPC-3300 pages2 of 2
Read
ZRF-SPC-4100native_text
ZRF-SPC-4100 pages1 of 1
Read
ZRF-CTR-APX-Anative_text
ZRF-CTR-APX-A pages1 of 1
Read
ZRF-CTR-APX-Dnative_text
ZRF-CTR-APX-D pages1 of 1
Read
ZRF-CTR-APX-Fnone
ZRF-CTR-APX-F pages0 of 14
Queued
ZRF-VND-P-1201native_text
ZRF-VND-P-1201 pages0 of 1
Queued
ZRF-SCH-0001structured
ZRF-SCH-0001 pagesprogress not measurable
Read
ZRF-PID-9001ocr
ZRF-PID-9001 pages0 of 1 — failed
RefusedA scan too faint to read. Processing refuses it and states why; nothing is extracted.

Ask for a document to be read again

A document measured as unreadable is refused, not queued.

The engines, and what they are worth

  • native_textpdf-native 0.1.0 — nothing it produces exceeds 80%
  • ocreds-stroke-ocr 0.1.0 — nothing it produces exceeds 60%
  • bothpdf-native+eds-stroke-ocr 0.1.0 — nothing it produces exceeds 70%
  • structuredxlsx-reader 0.1.0 — nothing it produces exceeds 100%
  • nonenone 0.1.0 — reads nothing

The ceiling belongs to the method. Why

Cloud OCR is not active

No external recognition service has been activated and no page has been sent to one. The OCR figures here are the in-house engine’s, measured on a synthetic corpus. They are not a claim about any commercial service.