# trishume/eyeLike

A webcam based pupil tracking implementation.

Repository: https://github.com/trishume/eyeLike
Canonical: https://ross.abutalabs.com/products/eyelike
Language: C++
License: MIT
License Family: permissive
Topics: opencv, eye-tracking
Last push: 2019-03-31T17:09:40+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 5065, "days_push": 2712, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1015, forks 334 (observed 2026-08-28T04:03:14.154163+00:00)

## What it is
eyeLike is an OpenCV-based C++ implementation of Fabian Timm's gradient-based eye center localization algorithm for webcam pupil tracking. It is a developer reference implementation that displays debugging windows with detected pupil points, not a complete gaze tracker.

## Use cases
- detect eye centers from a webcam feed
- implement pupil tracking with OpenCV in C++
- study Fabian Timm's gradient-based eye center algorithm
- prototype webcam-based eye tracking
- find pupil positions in video frames

## When to choose
- you need a reference implementation of Timm's eye center localization algorithm
- you want to build your own gaze tracker starting from pupil detection
- you are experimenting with OpenCV-based eye tracking on macOS or Linux

## When to avoid
- you need actual gaze point estimation on screen - it explicitly does not track gaze
- you need a production-ready or maintained eye tracking solution
- you need Windows support or a polished build process
- you want hardware-free gaze tracking out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing
- domain: computer-vision, artificial-intelligence
- platform: cpp, cross-platform
- tags: opencv, eye-tracking, pupil-detection, gaze-tracking, webcam, macos, linux

## Member repositories
- trishume/eyeLike (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:14.154163+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:11:29.160517+00:00, confidence not recorded.
  - readme: https://github.com/trishume/eyeLike (fetched 2026-08-28T04:03:14.154163+00:00, sha 5cb07b63065d)
- Data as of 2026-08-30T08:39:29.467469+00:00.