Why trust this

The output is only as good as the method behind it.

Any tool that makes claims about human behaviour owes its users a complete account of how those claims are made. Here is ours.

01

The science predates us by decades

Paul Ekman spent more than twenty years building the Facial Action Coding System. It maps every measurable movement of the face to a numbered action unit. Clinicians use it. Researchers use it. We did not invent it. We implemented it at scale, in a browser, on any video you hand us. The leap was engineering, not science.

FACS, Ekman and Friesen, first published 1978. Adopted across clinical, security, and performance psychology since the 1990s.

02

The pipeline is open to inspection

We use Google's open source face mesh, which maps 468 points across the face at up to 30 frames per second. From those points we compute eye openness, head pose, and action unit proxies from published geometric relationships. Every formula has a citation. Every output has a source.

Face mesh, Kartynnik et al. 2019. Eye aspect ratio, Soukupova and Cech 2016.

03

Your video is never retained

This is an architecture decision, not a policy line. On The Read, the entire vision pipeline runs in your browser. The video does not touch a server. For large group analysis, video is sent to compute, processed, and deleted within minutes. Only numbers come back. We never keep the footage.

Open your network inspector during The Read. You will see no upload of your video. The data sent is numerical only.

04

Confidence is shown, not hidden

Every finding carries a level. High, Medium, Low, or Abstain. Abstain means the engine did not have enough reliable data to say anything, so it says nothing. A finding from twelve shaky frames is not the same as one from four hundred stable ones, and the report tells you which is which.

Quality gate runs before any output. Minimum thresholds for duration, face detection rate, and quality. Below threshold, the engine abstains.

05

Probabilistic language is not weakness

A brow furrow is associated with cognitive effort. We write findings in probabilistic language, with a confidence level on every reading, because that is what the evidence supports. A tool that speaks in absolutes about people is not more powerful. It is less honest.

Probabilistic findings carry a flag and a plain language note on what the signal measures and what it does not claim.

06

What the engine does not do

It does not diagnose psychological or clinical conditions. It does not make the decision for you. It needs a usable face, with adequate light, facing the camera.

The output is data to inform a human decision, never to replace one.

Want the full methodology, the calibration sources, and the compliance detail? We keep the long version, with confidence intervals and limitations, on the methodology page.

Read the full methodologySee all 8 scores
Research basis

The work this is built on.

  1. Ekman, P. and Friesen, W. V. (1978). Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting Psychologists Press.
  2. Kartynnik, Y., Ablavatski, A., Grishchenko, I. and Grundmann, M. (2019). Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs (MediaPipe FaceMesh, 468 landmarks). arXiv:1907.06724
  3. Soukupova, T. and Cech, J. (2016). Real-Time Eye Blink Detection using Facial Landmarks. 21st Computer Vision Winter Workshop. PDF
Common questions

How the method holds up.

How does the GRW engine actually measure behaviour from a video?

It returns proprietary scores, each with a confidence level. To get there it implements the Facial Action Coding System, a method Paul Ekman built over more than twenty years, on top of Google's open source 468 point face mesh, which maps the face at up to 30 frames per second. From those points it computes eye openness, head pose, and action unit proxies using published geometric formulas, each with a citation. Larger files route to a server pipeline that adds more channels.

What are the five channels GRW reads?

Face, body, voice, language, and heart rate. GRW reads the face channel on device through Google's 468 point mesh, and tracks body pose on the same footage. A server path adds voice, language, and heart rate, with heart rate read from subtle skin color variation. The report tells you when the channels agree, when they disagree, and how confident the reading is.

What is FACS, and did GRW invent it?

FACS is the Facial Action Coding System, published by Ekman and Friesen in 1978 and used across clinical and performance psychology. It maps every measurable facial movement to a numbered action unit. GRW did not invent it. We implemented it at scale on Google's open source 468 point face mesh, in a browser, on any video you hand us. The leap was engineering, not science.

What do the confidence levels mean, and when does it abstain?

Every finding carries High, Medium, Low, or Abstain. A quality gate runs before any output, checking minimum thresholds for clip duration, face detection rate, and quality. When the data falls below threshold the engine abstains, meaning it did not have enough reliable evidence to say anything, so it says nothing rather than guess.

Scrutinise it. Then decide.

The people who check the method before they trust the output get the most from it.

Book a DemoSee all 8 scores