About

What was broken. What we built.

Six problems sports photographers and athletic departments live with, and the six things we did about them.

GalleryID was built around the work photographers and athletic departments were already doing, and the unpaid hours they spent doing it. It is two products, not one: GalleryID Desktop captions on your own Mac or PC with nothing uploaded, and GalleryID Cloud is the hosted, searchable archive.

Each section below is a problem we lived with. What follows it is what we built in response.

Problem

Hundreds of photos. Zero names.

The game ends and the tagging starts. A Saturday in October, or a regional tournament weekend. The deliverable goes out named, and getting it there took the next morning.

Nobody pays for that hour. The deliverable does. The labour underneath it does not.

What we built

CaptionID names them. MatchID finds them.

CaptionID writes the athlete’s name and the full caption line from the roster bound to the folder, in one press or from a shortcode, with no headshots needed. Index headshots and MatchID starts making those presses for you: it reads each frame, finds the faces and the numbers, and matches them against your roster.

The post-game hour goes. The named photos stay.

Problem

Names belong in the file.

Most platforms hold the tag in their own database. Export the file to Photo Mechanic, to Lightroom, or to a wire service, and the names do not come with it.

The name was never in the photo. It was in a row you stop having access to.

What we built

Names are written to the file in XMP and IPTC.

Both products write athlete names to XMP and IPTC PersonInImage metadata. GalleryID Desktop writes them as you tag, on your own machine. GalleryID Cloud writes them on download. Open the file in Photo Mechanic and the names are already there. Send it to a wire service and they go with it.

The file is yours, and the names are in it.

Problem

Facial recognition fails behind a mask.

Football helmets. Catcher’s masks. Goalie visors. Ski goggles. Facial recognition on its own gives up on the hardest frame of the night, which is the action photo under the helmet.

That is where most identification tools stop.

What we built

MatchID reads more than the face.

Jersey numbers are read off the frame, and the roster bound to that folder or gallery narrows who it could be. A frame the face alone would miss can still come back named.

The uncertain ones wait in the review queue. No silent wrong answers.

Problem

A meter on identification taxes the season.

Platforms that meter identification usually charge one to three cents an image. Hundreds of photos a game becomes thousands by the playoffs.

The bill compounds as the season gets bigger. The harder you work, the more they take.

What we built

Unlimited identification. No meter.

MatchID is included in both products and neither meters it. In GalleryID Cloud it is unlimited on all plans and storage is the only thing that scales. In GalleryID Desktop it runs on your own machine, so there is nothing to meter in the first place.

All features, all plans. The Cloud tier decides how much storage you have and nothing else, and Desktop is one price for two computers.

Problem

Charging per seat penalizes the team.

Per-seat pricing for this kind of software commonly runs $25 to $50 per user per month. Add the photographer, the comms staff, the marketing lead, the design intern, the freelancer covering Saturday.

By the time the department is connected, the bill is built on people rather than on work.

What we built

Unlimited users. Roles control access.

In GalleryID Cloud, add the whole department, the freelance team, and whoever runs the social channel. Adding the next person does not change the bill, and folder-level permissions decide what each of them sees.

Storage scales, seats do not. GalleryID Desktop is one subscription covering two computers instead, because it runs on yours.

Problem

Your photos should not train someone else’s model.

A lot of tools improve by training on customer uploads. Your photography becomes part of their next release, and your athletes become part of their training set.

Their model gets sharper. You get nothing.

What we built

Trained on our own archive. Yours stays yours.

The base MatchID model was trained on our own photographic archive, hundreds of thousands of sports photos, before any client uploaded a frame.

In GalleryID Cloud your photos and rosters stay scoped to your account. They do not flow back to our model and do not show up in another client’s results. In GalleryID Desktop the question does not arise: identification runs on your machine and nothing is uploaded at all.

Find photos by athlete,

not by filename.

Cloud from $20/mo, storage only. Desktop $20/mo, two computers included.

Start the 14-day trial See pricing

14 days free, card required · Cancel any time · Book a 30-min demo