Computer Vision Group Jena
JeFaPaTo
A joint toolbox for blinking analysis and facial features extraction
A joint toolbox for blinking analysis and facial features extraction
See facial landmarks and blendshapes as they happen. Get instant visual feedback during your analysis sessions with our optimized real-time processing engine.
Instant processing at up to 60 FPS
Analyzes 468 facial landmarks and 52 blendshapes with precision. Our advanced algorithms ensure accurate detection and measurement of facial features.
468 landmarks + 52 blendshapes
Select specific landmarks and blendshapes for analysis. Customize your workflow by choosing exactly which features matter for your research.
Choose your analysis parameters
Optimized for standard CPUs, processing up to 60 FPS. No expensive hardware required - works efficiently on regular computers.
CPU-optimized processing
Uses Eye Aspect Ratio (EAR) score for blinking analysis. Advanced detection algorithms automatically identify and measure blink patterns.
EAR-based blink analysis
Processes videos with any FPS, optimized for 240 FPS. Handle high-speed cameras and slow-motion footage with ease.
Up to 240 FPS support
Works on Windows, Linux, and macOS. One tool for all your devices - consistent performance across all major operating systems.
Windows • Linux • macOS
Access previous releases of JeFaPaTo for compatibility or testing purposes.
For older versions, specific builds, or development releases, please visit our GitHub releases page where you can find the complete version history and changelogs.