Photo checks for photo contests and stock-photo submissions
Photo contests and stock libraries can check every submission for AI generation and missing camera metadata before judging. PhotoCheck returns the AI score, the camera and lens from EXIF, the capture time, and any declared AI provenance, which is the evidence most contest rules already ask for.
The problem
AI images have won photography prizes, and stock libraries now hold millions of them. Most contests ask for the original camera file, and a quick check of that file's EXIF and its AI score catches most rule breaks before a judge looks.
The checks that matter
| Camera EXIF | Make, model and lens from the original file, the evidence contests already request. |
|---|---|
| AI score | Flags generated entries in categories that forbid them. |
| Declared AI | Edits recorded by C2PA-aware editors show up as composites. |
A decision rule
Built on POST /api/v1/analyze. Thresholds are starting points; tune them to what a mistake costs you.
const r = await check(entry);
if (!r.metadata.exif.present) return "request_original";
if (r.summary.ai_generated === "declared") return "disqualify_or_move_category";
if (r.ai.score >= 0.8) return "judge_review";
return "accept";Questions
Can entrants fake EXIF?
Yes, with some effort. Treat EXIF as one piece of evidence alongside the score and your own requirement for raw files.
Does the detector work on edited photos?
Heavy retouching can raise the score. Judges should see the score as a prompt, not a verdict.