jbaruch/face-recognition-calibration
Production-grade dlib face_recognition toolkit: piecewise confidence formula, enrollment quality diagnostics, and producer-side persistence for flicker suppression.
69
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
README.md
face-recognition-calibration
A Tessl plugin that encodes a perceptually-correct confidence
formula for the face_recognition (dlib) library, plus enrollment best practices
and the Python 3.14 install trap.
What this plugin provides
| Kind | Name | Purpose |
|---|---|---|
| Skill | face-recognition-confidence | Piecewise distance → confidence mapping, enrollment workflow, validation checks. |
| Rule | face-recognition-calibration-rules | Concise in-context reminder card. |
| Script | scripts/confidence.py | Reference implementation of the mapping and enrollment helpers. |
Why it exists
The textbook 1 - distance / tolerance mapping is technically correct and empirically
useless — a strong match at d = 0.38 shows up as 0.37 on a UI meter and the demo
looks broken. This plugin uses a piecewise mapping that reflects how operators actually
read the numbers:
d <= 0.30 -> 1.0 (strong match)
d >= 0.60 -> 0.0 (reject)
else -> (0.60 - d) / 0.30Same d = 0.38 now scores 0.73. The meter matches the vibe.
It also documents the Python 3.14 install trap: face_recognition_models depends on
pkg_resources, which setuptools removed in 82+. Pin setuptools==75.8.0.
Install
tessl install jbaruch/face-recognition-calibrationOr from this repo:
tessl install github:jbaruch/face-recognition-calibrationUsage (quick)
from scripts.confidence import confidence, best_match, load_enrollment
enrolled = load_enrollment("faces.pkl")
name, distance, conf = best_match(live_encoding, enrolled)
print(f"{name} d={distance:.2f} conf={conf:.2f}")See skills/face-recognition-confidence/SKILL.md for the full guidance and
rules/face-recognition-calibration-rules.md for the short version.
License
MIT — see LICENSE.