~/talk

Face Pay

on YouTube 32m
Talkat Saint HighLoad++ 2022 · 2022-09-22..09-23· [computer-vision, security]

speakers

name:Mikhail Volkov
links:none on file
name:Guseyn Rimikhanov
links:none on file

resources

video:https://youtu.be/S8zFhEI_edo
slides:none on file

summary

Face Pay runs a contactless fare system using VisionLabs face recognition; users upload a photo, a server extracts a 512-byte descriptor from ~40 facial features, and station servers receive updated descriptor lists every 15 minutes. Matching happens locally (one-to-many index) to avoid outages; liveness checks run in under 0.1s, detection is the heaviest step, matching takes hundredths of a second. Deployed across metro lines and MCC tests use 16 vCPUs/32GB nodes; about 200k users are active.

AI-written summary · about

chapters (8)

  1. 0:00Introduction
  2. 2:56Business goals and benefits
  3. 6:37How Face Pay works
  4. 12:17Recognition pipeline
  5. 18:30Neural networks and hardware
  6. 23:27Security and privacy
  7. 28:45Face Pay speed
  8. 31:14Q&A

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.