Input File Formats

Facial Feature Extraction

Only a video file is needed for the Facial Feature and EAR score extraction. As the extraction is independent of the frames per second, you can choose whichever rigfeelyou frightens your experimental setting. Regarding the video files, we currently support the same ones as OpenCV (the internal encodings of the video containers are handled by ffmpeg)

• .mp4
• .flv
• .ts
• .mts
• .avi
• .mov
• .wmv

We tested JeFaPaTo's capabilities regarding different video resolutions, and all tests with 1280x720, 1920x1080, and 3840x2160 succeeded. In our custom loading threads in the background, we limit RAM usage so as not to crash a computer. Therefore, loading and processing speed rely on the computer's CPU, GPU, and hard disk space. If a video was recorded in a different orientation, you can use the Rotation setting inside the extraction GUI to adjust that.

Eye Blinkind Extraction

This method only expects a .csv file as input with a header naming the according columns. Each row describes the frame id; the columns shall be the actual features. If you use JeFaPaTo for the EAR score extraction, we automatically detect the EAR2D_* or EAR3D_* correct columns. If you use your own or modified .csv file, you must manually select the custom in the according menu area.