0020.jpg
0020.jpg
ARK
Name
2DbczcW5cvbkiwcnMBZtD2
https://n2t.net/ark:/11635/2DbczcW5cvbkiwcnMBZtD2
https://scanstation.ai/ark/11635/2DbczcW5cvbkiwcnMBZtD2
File
| Order | 20 |
|---|---|
| Dimensions | 7968 × 5984 |
| Orientation | 0 |
| S3 Key | marac/003/derivatives/0020.jpg |
| Source Path | marac/003/derivatives/0020.jpg |
AI Enrichment
Summary
Thumbnail shows the reverse of a mailed postcard on a black calibration background, with a handwritten message, address to a recipient in the USA, postage stamp and postmark, and small printed postcard-back text that requires high-resolution review for full transcription.
OCR Excerpt
anme
Places
USA
Finland digitization setting
Type
people_photo
tag_or_label
document
photo
text_page
postcard
Tags
No tags assigned.
Primary: postcard
Subject: image:01KQHXQP3AHWBDFN0RC8987PYE
18 predicates
| Predicate | Best value | Conf. | Source |
|---|---|---|---|
| ai:denseSummary |
Thumbnail shows the reverse of a mailed postcard on a black calibration background, with a handwritten message, address to a recipient in the USA, postage stamp and postmark, and small printed postcard-back text that requires high-resolution review for full transcription.
|
1% | [email protected] |
| ai:documentLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
1% | [email protected] |
| ai:handwrittenText | yes | 1% | [email protected] |
| ai:hasText | yes | 1% | [email protected] |
| ai:highResGoal |
read_handwriting
Loss of searchable names, place/date from the postmark, sender and recipient details, and any printed postcard publisher or series information.
|
1% | [email protected] |
| ai:highResTarget |
left-side handwritten message
High-resolution target from thumbnail enrich
|
1% | [email protected] |
| ai:isFilledForm | |||
| ai:isForm | |||
| ai:ocrText |
anme
Tesseract via ai-tools (1 words, mean conf 68.0)
|
1% | [email protected] |
| ai:peopleLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
1% | [email protected] |
| ai:photoLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
1% | [email protected] |
| ai:photoWithTextLikely | |||
| ai:pixelsDone | |||
| ai:speculation |
This is the reverse of a tourist or personal-view postcard rather than a government or business card.
The standard divided postcard back, informal cursive message, and personal address format are typical of leisure or personal correspondence.
|
1% | [email protected] |
| ai:typedText | yes | 1% | [email protected] |
| dcterms:spatial |
USA
Finland digitization setting
|
1% | aggregated |
| dcterms:type |
people_photo
found 6 face(s)
|
5% | [email protected] |
| foaf:Person |
unidentified postcard sender
|
1% | [email protected] |
Subject: image:01KQHXQP3AHWBDFN0RC8987PYE
0 claims
No claims recorded yet for this subject.
closed
— No more image calls. Item workflow consumes image claims/text/metadata for catalog-level analysis.
| Transition | Description | |
|---|---|---|
| upload async |
Pushes realPath (the ai-tools crop) to S3 as the canonical image. When defaults.full_frame_key is present, also archives the original mat under originals/ on S3 for re-processing / QR re-extraction during Python dev. The full-frame archive is planned to drop for real-client tenants.
Available from: triaged
|
|
| external_upload |
Sets defaults["storage"]["mode"] = "external_url". Used by IIIF imports so the image remains accessible via its external URL and subsequent transitions can run against it directly. Skips triage — the UPLOADED place lets enrich run against the remote URL.
Available from: new
|
|
| triage async |
When fired from NEW: local-file mode. ai-tools reads defaults.full_frame_key + defaults.sidecar_key from the shared dir, produces the canonical crop + thumbnail in derivatives/, and returns deskew/type/detections. realPath is repointed at the crop. When re-run from TRIAGED: same, idempotent. Non-URL mode is the only path browser captures take. Failures keep the image in NEW (async retry).
Available from: new, triaged
|
|
| enrich async |
Single cheap AI call (~$0.0004) against a ≤512px thumbnail, with triage OCR + flags in context. Populates title/description/subjects/people/places/dense_summary and text-type flags. Can run from TRIAGED (using ssai image_view via imgProxy, skipping S3 upload) or from UPLOADED. Re-runnable from enriched for debugging.
Available from: triaged, uploaded, enriched
|
|
| extract async |
The optional second image call. Runs only when enrich_from_thumbnail sets pixelsDone=false. Dispatches by extraction goal/signals: filled forms → ExtractMetadata; handwriting → TranscribeHandwriting; dense print/layout → OcrMistral. Re-runnable.
Available from: enriched, extracted
|
|
| close | Bookkeeping only. Requires pixelsDone=true. The item workflow performs text-only catalog analysis across all images. | |
| ignore | Operator triage from the narrate screen. Hides the image from narration immediately and queues it for permanent deletion at intake close. No AI transition lists IGNORED in its `from`, so an ignored image can never be sent for enrichment -- the workflow itself is the guard, no separate check needed. |
Subject: image:01KQHXQP3AHWBDFN0RC8987PYE
29 claims
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:denseSummary |
Thumbnail shows the reverse of a mailed postcard on a black calibration background, with a handwritten message, address to a recipient in the USA, postage stamp and postmark, and small printed postcard-back text that requires high-resolution review for full transcription.
|
1% | — |
| ai:handwrittenText | yes | 1% | — |
| ai:hasText | yes | 1% | — |
| ai:highResGoal |
read_handwriting
|
1% |
Loss of searchable names, place/date from the postmark, sender and recipient details, and any printed postcard publisher or series information.
|
| ai:highResTarget |
left-side handwritten message
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
address on right side
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
postmark and stamp details
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
small printed text along the top edge of the postcard back
|
1% |
High-resolution target from thumbnail enrich
|
| ai:isFilledForm | — | ||
| ai:isForm | — | ||
| ai:pixelsDone |
Thumbnail clearly identifies a postcard back, but the handwritten message, postmark, and small printed publisher text are too small to read reliably.
|
||
| ai:speculation |
This is the reverse of a tourist or personal-view postcard rather than a government or business card.
|
1% |
The standard divided postcard back, informal cursive message, and personal address format are typical of leisure or personal correspondence.
|
| ai:speculation |
The postcard was sent internationally to the United States.
|
1% |
The address side visibly includes 'USA', and the stamp/postmark placement indicates actual mailing.
|
| ai:typedText | yes | 1% | — |
| dcterms:spatial | USA | 1% |
The destination line visibly ends with 'USA'.
|
| dcterms:spatial | Finland digitization setting | 1% |
The surrounding calibration board includes the text 'StereoStation.fi', indicating the postcard was photographed or scanned in Finland, though this is not the postcard's original place.
|
| dcterms:type |
postcard
|
1% | — |
| foaf:Person |
unidentified postcard sender
|
1% | — |
| foaf:Person |
unidentified postcard recipient
|
1% | — |
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:documentLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
| ai:hasText | yes | 1% |
Tesseract via ai-tools (1 words, mean conf 68.0)
|
| ai:peopleLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
| ai:photoLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
| ai:photoWithTextLikely |
ai-tools heuristic on scan.storage:marac/003/0020.jpg
|
||
| dcterms:type |
people_photo
|
5% |
found 6 face(s)
|
| dcterms:type |
tag_or_label
|
5% |
found 3 machine-readable code(s); small text footprint matches labels or tags
|
| dcterms:type |
document
|
3% |
document outline covers 38% of frame; visual text regions suggest document-like content
|
| dcterms:type |
photo
|
2% |
face detection usually implies a photograph
|
| dcterms:type |
text_page
|
1% |
visual text regions suggest text blocks
|