Recognition: people & faces

This is what sets SnapFlow apart for sports and event work: it automatically finds the people in your photos and groups every shot of the same person. For team and race events it goes further — reading jersey, bib and car numbers, matching team kits, and clustering vehicles and helmets. That turns "2,000 photos" into "here's every shot of athlete #23" in minutes.

Recognition is five pipelines that build on each other. This chapter covers the foundation — face detection and the People page. The next four cover the rest:

• Numbers — jersey, bib, car, sail, saddle and bike numbers.
• Teams & kits — uniforms and liveries.
• Vehicles — cars, bikes, boats and horses.
• Helmets — drivers and riders by helmet paint.

Turn it on

Recognition runs per album. On the Edit → Workflows page, switch on People detection — this is the master toggle that every other pipeline nests under. Detection then runs automatically as photos are ingested. Web

The People page

Open an album and go to People. As photos come in, SnapFlow scans them and this page fills with the people it finds — here it's detected 17 faces and grouped them into clusters.

Each card is a face cluster — every shot of the same person, grouped together. The actions across the top let you re-run detection:

• Re-scan matches — re-check already-detected faces against your named people and athlete registry. Fast; run it after you add or rename someone.
• Re-group — re-cluster the faces when the same person is split across two cards, or two people landed on one.
• Resume detection — fill any gaps if detection was paused mid-run.
• Re-detect all — start the whole pipeline over (your named and registered people are preserved).

Photos SnapFlow is unsure about collect under "… photos need your attention" so you can confirm them in one place.

Naming and correcting faces

SnapFlow does the heavy lifting; you stay in control. On a cluster card or its detail page you can:

• Rename — name a face group once and it labels every photo of that person.
• Merge into… — combine two clusters that are really the same person.
• Reassign or Remove a stray photo that was grouped by mistake.
• Ignore — hide a cluster you don't care about (a bystander, a marshal).
• Set team — pin a face to a team (see Teams & kits).
• Save as athlete — promote the cluster to your registry so the match follows that person across every album.

The athlete registry

Naming a cluster labels it in this album. Save as athlete promotes it to the global People destination so SnapFlow recognises that person in future events too. Open any registered athlete to see the Appears in panel — every album they show up in, with photo counts — and pin reference photos the cross-album matcher anchors on.

Set the stage: expected athletes & teams

For a known fixture you can tell SnapFlow who to expect before you shoot. Collapsible panels on the People page let you:

• Expected athletes — pre-tag athletes from your registry so they become priority matches.
• Expected teams — pin the teams playing today and pick each team's active kit. This resolves clashes (e.g. both sides in red) and auto-adds every team member to your expected athletes.

Why it's worth it

Once people are recognised you can deliver each athlete their own gallery, find every shot of one person instantly, and auto-caption and tag photos for social posting. Next: teaching SnapFlow to read numbers.