MatchID
Facial recognition for the faces you can see. Jersey numbers for the helmets you can't. MatchID runs locally on your Mac or PC in GalleryID Desktop, and against the gallery you upload in GalleryID Cloud. Anything it misses is one press from the roster with CaptionID. Names write to the file.
The workflow
Desktop runs MatchID on the folder on your machine. Cloud runs it on the gallery you upload. Same engine, same names.
In GalleryID Desktop, that's a folder or a selection on your own computer — nothing is uploaded. In GalleryID Cloud, it's the gallery you dragged in. The roster is already bound and ready to match.
Trained for sports photography, with jersey numbers as the second signal. Confidence scores surface for review, or set auto-approve. In Desktop, Who Is This asks about a single photo on demand.
In Desktop the names are already written to the file before it leaves your machine. In Cloud they're written to the file on download. FTP, share link, ZIP, the names write to the file either way.
The math
Per-image pricing starts cheap. The bill compounds through the season. Ours doesn't move.
Math assumes 3¢ per image, the high end of typical per-credit pricing. Photo counts vary by sport, coverage, and photographer. The point: credits put a tax on volume. Unlimited removes it.
Facial recognition struggles with sports photography. Motion blur. Awkward angles. Hands in the frame. Eyes closed mid-stride. Most general-purpose face APIs trained on portrait photography. They don't translate.
We trained MatchID for the kind of photos you take. Sideline distance. Helmets pushed back. Fast pans. Threshold settings let you tune for your tolerance — relax it for helmet sports where you need recall, tighten it for face-visible sports where you need precision.
Football. Lacrosse. Hockey. Catchers in the dirt. The face is hidden but the number is visible. Jersey number reading reads it.
A helmeted face alone scores lower than a clean one. Fewer features, more occlusion. Jersey number reading closes the gap — when face confidence dips, the number raises the match. Together they push helmet-sport accuracy well past what facial recognition can do alone.
We trained OCR to read numbers off jerseys, helmet decals, chest plates, and shoulder patches. Numbers match to roster positions. Names attach.
In GalleryID Desktop the names are written to the file right on your machine; in GalleryID Cloud they write to the file on download. Standard IPTC and XMP, not a proprietary format. Photo Mechanic reads them. Lightroom reads them. Capture One reads them. Photoshop reads them.
Names write to the file, so they go wherever it goes. Not stuck in an app. Not behind a login. Not lost when you switch tools. If the photo gets emailed, archived, or republished, the metadata goes with it.
This is the only way we want to deliver identification.
Sports first
Sports is where we started. The product works wherever you need names attached to faces.
Plus dance studios, school productions, music groups, conferences, corporate events, and wedding parties.
Per-client by design
No global index. MatchID identifies players against your roster. There's no cross-client database of athletes. There's no shared face library. There's no model trained on your photos for someone else's benefit.
Each account is its own MatchID context. And in GalleryID Desktop the question doesn't even come up: the photos, the headshots you index, and the face data never leave your computer at all.
What we don't charge for
MatchID at $20/mo. Same features at $800/mo.
See Pricing →Common questions
In both GalleryID products. In GalleryID Desktop it runs locally on your Mac or PC against headshots you index there — nothing is uploaded, and it's unmetered because it's your machine doing the work. In GalleryID Cloud it runs against the gallery you uploaded, unlimited on all plans. Both write the same names into the same metadata fields.
Depends on the photos. Face-visible sports like volleyball and basketball: high accuracy out of the box. Helmet sports: depends on how often jersey numbers are visible. We let you tune the confidence thresholds for your tolerance.
You catch them in review. The interface shows pending matches with confidence scores and the source crop. Reject the bad ones. Approve the good ones. The auto-approve threshold lives in your settings.
In Cloud, photos process in parallel and a typical Saturday college football gallery (a few hundred photos) is done in under 30 minutes; larger galleries scale proportionally. In Desktop it runs on your own machine whenever you trigger it — the usual pattern is to cull first and run MatchID only on the keepers.
For MatchID, yes — it matches faces against the headshots on your roster. But you don't need MatchID to caption: CaptionID writes the name and the full caption line from the roster in one press or a shortcode, no headshots at all. MatchID is the accelerator on top of that.
Facial recognition still works on partial occlusions. Sunglasses and masks reduce accuracy but don't break it. Jersey number reading is your backup when the face isn't legible.