iTrace : boîte à outils d'analyse des mouvements oculaires par webcam

Boîte à outils Python sous licence MIT pour le diagnostic du regard, des saccades, de la pupille et de la qualité à partir d'une webcam. Version 0.4.1 vérifiée algorithmiquement.

Spar Skills Guide Bot
Data & IAIntermédiaire
1025/07/2026
Claude CodeCopilotCodex
#eye-tracking#webcam#gaze#saccades#pupillometry#open-source#diagnostic-pilot

Recommandé pour


name: "iTrace: verification-first webcam eye-movement analysis" description: "iTrace is an MIT-licensed Python toolkit for webcam-derived gaze, saccade, pupil, and quality diagnostics. Version 0.4.1 is a diagnostic v1 release: the pure NumPy/SciPy core is algorithmically verified against synthetic and closed-loop oracles, the ..." tags: ["eye-tracking", "webcam", "gaze", "saccades", "pupillometry", "open-source", "diagnostic-pilot"] domain: "Computational" citation: "Daniel Ari Friedman (2026). iTrace: verification-first webcam eye-movement analysis. Computational." doi: "10.5281/zenodo.20614909"

iTrace: verification-first webcam eye-movement analysis

Daniel Ari Friedman (2026) · Computational

Context

This work addresses topics in Computational: eye-tracking, webcam, gaze, saccades.

Methods

Primary methods and techniques applied in this work:

  • Software pipeline design
  • Data-driven analysis

Key Findings

Core contributions and results:

  • iTrace is an MIT-licensed Python toolkit for webcam-derived gaze, saccade, pupil, and quality diagnostics.
  • Version 0.4.1 is a diagnostic v1 release: the pure NumPy/SciPy core is algorithmically verified against synthetic and closed-loop oracles, the optional webcam shell exports derived records, and the em

Related Works

Validation

Verification points for this work:

  • DOI: 10.5281/zenodo.20614909
  • PDF SHA-256: See zenodo_record
  • Pairing confidence: needs_review
  • Last checked: 2026-06-09T18:22:02Z

Prerequisites

  • Familiarity with eye-tracking, webcam, gaze
  • Background in Computational fundamentals
  • Access to source repository: N/A

Instructions

When working with this paper:

  1. Reference the DOI for citation: 10.5281/zenodo.20614909
  2. Apply methods listed in the Methods section for related analysis.
  3. Validate findings against the original PDF and metadata.
Skills similaires