Face Recognition in Surveillance — One-Page Reference

Detection vs recognition, the four-step pipeline (detect, align, embed, match), 1:1 verification vs 1:N identification with the false-positive scaling math, the honest field accuracy (cooperative ~99% vs CCTV ~65–85%, never 100%, with demographic differentials), how a face event surfaces via ONVIF Profile M and where it runs, and the legal gate (GDPR Art. 9 · EU AI Act Art. 5 · Illinois BIPA · Texas CUBI) — on one page.