0049.jpg
0049.jpg
ARK
Name
2DbdJpoLV8QvgiJtEVeFKa
https://n2t.net/ark:/11635/2DbdJpoLV8QvgiJtEVeFKa
https://scanstation.ai/ark/11635/2DbdJpoLV8QvgiJtEVeFKa
File
| Order | 49 |
|---|---|
| Dimensions | 7968 × 5984 |
| Orientation | 0 |
| S3 Key | marac/002/derivatives/0049.jpg |
| Source Path | marac/002/derivatives/0049.jpg |
AI Enrichment
Summary
Very dark thumbnail showing a nearly featureless black, slightly textured surface with narrow top and left borders; no readable text, figures, or scene are visible, so the item is most likely an object surface or cover but remains uncertain from this image alone.
Type
graphic_or_artwork
object
Tags
No tags assigned.
Primary: object
No description yet.
Subject: image:01KQJBCZVRZSMW5Y4YK7C4C18Y
16 predicates
| Predicate | Best value | Conf. | Source |
|---|---|---|---|
| ai:denseSummary |
Very dark thumbnail showing a nearly featureless black, slightly textured surface with narrow top and left borders; no readable text, figures, or scene are visible, so the item is most likely an object surface or cover but remains uncertain from this image alone.
|
1% | enrich_from_thumbnail@1.0 |
| ai:documentLikely | |||
| ai:handwrittenText | |||
| ai:hasText | |||
| ai:highResGoal |
inspect_detail
The item could be misclassified, and any faint text, embossing, image content, or object-identifying features not visible in the thumbnail would be missed.
|
1% | enrich_from_thumbnail@1.0 |
| ai:highResTarget |
entire dark central surface
High-resolution target from thumbnail enrich
|
1% | enrich_from_thumbnail@1.0 |
| ai:isFilledForm | |||
| ai:isForm | |||
| ai:ocrText |
Tesseract via ai-tools (0 words, mean conf 95.0)
|
1% | ai-tools@1.0 |
| ai:peopleLikely | |||
| ai:photoLikely | |||
| ai:photoWithTextLikely | |||
| ai:pixelsDone | |||
| ai:speculation |
This may be the cover or binding board of an album, book, or case photographed/scanned at close range.
Uniform dark textured field with straight edge borders at the top and left is consistent with a bound cover, but there are no visible titles, hinges, or other confirming details.
|
0% | enrich_from_thumbnail@1.0 |
| ai:typedText | |||
| dcterms:type |
graphic_or_artwork
moderate colorfulness 8.3 looks visual rather than textual
|
2% | ai-tools@1.0 |
Subject: image:01KQJBCZVRZSMW5Y4YK7C4C18Y
0 claims
No claims recorded yet for this subject.
enriched
— enrich_from_thumbnail ran with OCR in context. Emits title/description/subjects/people/places/dense_summary and pixelsDone/high-res extraction routing claims.
| Transition | Description | |
|---|---|---|
| upload | 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. | |
| 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. | |
| triage | 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). | |
| enrich | 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. | Apply |
| extract | 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. | Apply |
| close | Bookkeeping only. Requires pixelsDone=true. The item workflow performs text-only catalog analysis across all images. |
Subject: image:01KQJBCZVRZSMW5Y4YK7C4C18Y
21 claims
enrich_from_thumbnail@1.0
15
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:denseSummary |
Very dark thumbnail showing a nearly featureless black, slightly textured surface with narrow top and left borders; no readable text, figures, or scene are visible, so the item is most likely an object surface or cover but remains uncertain from this image alone.
|
1% | — |
| ai:handwrittenText | — | ||
| ai:hasText | — | ||
| ai:highResGoal |
inspect_detail
|
1% |
The item could be misclassified, and any faint text, embossing, image content, or object-identifying features not visible in the thumbnail would be missed.
|
| ai:highResTarget |
entire dark central surface
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
left edge vertical border
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
top edge strip
|
1% |
High-resolution target from thumbnail enrich
|
| ai:highResTarget |
any faint marks or embossed details in the dark field
|
1% |
High-resolution target from thumbnail enrich
|
| ai:isFilledForm | — | ||
| ai:isForm | — | ||
| ai:pixelsDone |
Thumbnail is too dark and low-detail to determine what the item is; important visual evidence may be hidden in the surface and edges.
|
||
| ai:speculation |
This may be the cover or binding board of an album, book, or case photographed/scanned at close range.
|
0% |
Uniform dark textured field with straight edge borders at the top and left is consistent with a bound cover, but there are no visible titles, hinges, or other confirming details.
|
| ai:speculation |
The image may be underexposed or poorly scanned, obscuring the actual subject.
|
0% |
Most of the frame is near-black with only faint tonal variation, leaving open the possibility that content exists but is not recoverable at thumbnail scale.
|
| ai:typedText | — | ||
| dcterms:type |
object
|
1% | — |
ai-tools@1.0
6
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:documentLikely |
ai-tools heuristic on scan.storage:marac/002/0049.jpg
|
||
| ai:hasText |
Tesseract via ai-tools (0 words, mean conf 95.0)
|
||
| ai:peopleLikely |
ai-tools heuristic on scan.storage:marac/002/0049.jpg
|
||
| ai:photoLikely |
ai-tools heuristic on scan.storage:marac/002/0049.jpg
|
||
| ai:photoWithTextLikely |
ai-tools heuristic on scan.storage:marac/002/0049.jpg
|
||
| dcterms:type |
graphic_or_artwork
|
2% |
moderate colorfulness 8.3 looks visual rather than textual
|