Output File Formats

Facial Feature Extraction

The output file for the facial feature extraction is always a .csv file with ; as a chosen separator. The file will be created automatically next to the video file with the current timestamp. The file only uses ASCII symbols and contains a header row. Each column in the header describes the extracted facial feature and gives a state of the extraction validity. Each row represents a single frame incl, including according to the frame id inside the video.

In the image below, you can see such an extraction result:

• frame: the actual frame id inside the video
• EAR2D6_l: the according EAR2D6 score for the left eye at the according frame
• EAR2D6_r: the according EAR2D6 score for the right eye at the according frame
• EAR2D6_valid: is True or False if the computation of the EAR score was valid, e.g., all landmarks were in the image, values were within a logical range, etc.
• BS_Valid: is True or False if the extraction of the facial blendshapes was valid, e.g., the face was unmistakable.

Eye Blinking Extraction

For the eye blinking extraction, the saving of the extracted blinks matched blinks, and summary statistics is the same data as in the GUI. Therefore, if you understand the GUI tables, the saved tables match them one-to-one.

However, the only difference is the file format used. For the Excel file type, all information and data are stored in a single file via subsheets accessible (see the image below). For the CSV file type, all information would be a dedicated .csv file for each table.

Additionally, the visual summary can be exported via GUI (see the tutorial on how to do it).